diff --git a/src/content/docs/agent-platform/capabilities/index.mdx b/src/content/docs/agent-platform/capabilities/index.mdx index 76c6459d..058e312a 100644 --- a/src/content/docs/agent-platform/capabilities/index.mdx +++ b/src/content/docs/agent-platform/capabilities/index.mdx @@ -13,7 +13,6 @@ Agent capabilities are the core building blocks that define how Warp's agents op * [Skills](/agent-platform/capabilities/skills/) - Reusable, scoped instructions that teach agents how to perform specific tasks in your codebase. * [Planning](/agent-platform/capabilities/planning/) - Turn agent requests into organized, editable plans that execute step-by-step with full visibility. * [Task Lists](/agent-platform/capabilities/task-lists/) - Track complex workflows with automatic task lists that update progress in real time. -* [Model Choice](/agent-platform/capabilities/model-choice/) - Pick your preferred LLM from a curated set of top models, or let Warp choose the optimal one. * [Rules](/agent-platform/capabilities/rules/) - Define global and project-level guidelines that shape agent behavior and responses. * [Full Terminal Use](/agent-platform/capabilities/full-terminal-use/) - Let the agent drive interactive terminal apps, seeing live output and running commands. * [Computer Use](/agent-platform/capabilities/computer-use/) - Let agents interact with desktop environments by taking screenshots, clicking, typing, and controlling the GUI. @@ -24,4 +23,5 @@ Agent capabilities are the core building blocks that define how Warp's agents op ## Related -For hands-on agent interactions, see [Local Agents](/agent-platform/local-agents/overview/). +* [Inference & providers](/agent-platform/inference/model-choice/) - Pick the model that powers your agents, bring your own API key, or connect a custom inference endpoint. +* [Local Agents](/agent-platform/local-agents/overview/) - Hands-on agent interactions in Warp. diff --git a/src/content/docs/agent-platform/cloud-agents/faqs.mdx b/src/content/docs/agent-platform/cloud-agents/faqs.mdx index 374e737b..6962ebdf 100644 --- a/src/content/docs/agent-platform/cloud-agents/faqs.mdx +++ b/src/content/docs/agent-platform/cloud-agents/faqs.mdx @@ -60,7 +60,7 @@ The cloud agents platform supports self-hosting the **agent sandbox** (the execu Self-hosted execution is available on **Enterprise** plans. See [Self-hosting](/agent-platform/cloud-agents/self-hosting/) and [Deployment patterns](/agent-platform/cloud-agents/deployment-patterns/) for details. :::note -[Bring Your Own Key (BYOK)](/support-and-community/plans-and-billing/bring-your-own-api-key/) does not apply to cloud agents. BYOK keys are stored locally on your device and cannot be passed to cloud-hosted or self-hosted agent runs. All cloud agent runs consume [Warp credits](/support-and-community/plans-and-billing/credits/). +[Bring Your Own Key (BYOK)](/agent-platform/inference/bring-your-own-api-key/) does not apply to cloud agents. BYOK keys are stored locally on your device and cannot be passed to cloud-hosted or self-hosted agent runs. All cloud agent runs consume [Warp credits](/support-and-community/plans-and-billing/credits/). ::: ## Models diff --git a/src/content/docs/agent-platform/cloud-agents/harnesses/authentication.mdx b/src/content/docs/agent-platform/cloud-agents/harnesses/authentication.mdx index c5f95ed7..eb65b7c7 100644 --- a/src/content/docs/agent-platform/cloud-agents/harnesses/authentication.mdx +++ b/src/content/docs/agent-platform/cloud-agents/harnesses/authentication.mdx @@ -12,7 +12,7 @@ Third-party cloud agent authentication in Oz stores provider credentials for clo Auth secrets can be scoped to a **team** (available to all teammates' runs) or **personal** (only your own runs), like any other Warp-managed secret. :::note -[Bring Your Own Key (BYOK)](/support-and-community/plans-and-billing/bring-your-own-api-key/) configured in the Warp desktop app applies to local agent runs only. Cloud runs of Claude Code and Codex always use Warp-managed secrets. +[Bring Your Own Key (BYOK)](/agent-platform/inference/bring-your-own-api-key/) configured in the Warp desktop app applies to local agent runs only. Cloud runs of Claude Code and Codex always use Warp-managed secrets. ::: ## Connecting Claude Code credentials diff --git a/src/content/docs/agent-platform/cloud-agents/harnesses/warp-agent.mdx b/src/content/docs/agent-platform/cloud-agents/harnesses/warp-agent.mdx index 1dcc1376..8b817546 100644 --- a/src/content/docs/agent-platform/cloud-agents/harnesses/warp-agent.mdx +++ b/src/content/docs/agent-platform/cloud-agents/harnesses/warp-agent.mdx @@ -13,7 +13,7 @@ Warp Agent is the same agent runtime that powers Agent Mode in the Warp terminal ## Key features -* **Multi-model auto-routing** - Routes between Anthropic, OpenAI, Google, and Fireworks-hosted models. Choose a specific model, or let Warp pick via `auto`, `auto-efficient`, `auto-genius`, or `auto-open`. See [Model choice](/agent-platform/capabilities/model-choice/) for the full catalog. +* **Multi-model auto-routing** - Routes between Anthropic, OpenAI, Google, and Fireworks-hosted models. Choose a specific model, or let Warp pick via `auto`, `auto-efficient`, `auto-genius`, or `auto-open`. See [Model choice](/agent-platform/inference/model-choice/) for the full catalog. * **Full terminal and tool access** - Runs commands, edits files, reads logs, executes tests, navigates repos, and calls MCP servers — the same toolbelt Warp Agent uses locally. * **Platform-native context** - Reads [Codebase Context](/agent-platform/capabilities/codebase-context/), applies [Rules](/agent-platform/capabilities/rules/), reuses saved [Skills](/agent-platform/capabilities/skills/), and respects Memory and Warp Drive context with no extra setup. * **Multi-repo execution** - Clones every repo configured on the [environment](/agent-platform/cloud-agents/environments/) and works across them in a single run. @@ -28,7 +28,7 @@ Team admins can disable any harness for their workspace. Users on that team can ### Available models -Warp Agent supports the full Warp model catalog. Configure the model per [Agent Profile](/agent-platform/capabilities/agent-profiles-permissions/), or pick one at run time. See [Model choice](/agent-platform/capabilities/model-choice/) for the supported model IDs, including the `auto`, `auto-efficient`, `auto-genius`, and `auto-open` routing options. +Warp Agent supports the full Warp model catalog. Configure the model per [Agent Profile](/agent-platform/capabilities/agent-profiles-permissions/), or pick one at run time. See [Model choice](/agent-platform/inference/model-choice/) for the supported model IDs, including the `auto`, `auto-efficient`, `auto-genius`, and `auto-open` routing options. ### Cross-harness orchestration @@ -64,6 +64,6 @@ For a complete walkthrough, see the [Cloud agents quickstart](/agent-platform/cl * [Harnesses in Oz](/agent-platform/cloud-agents/harnesses/) — pick between Warp Agent, Claude Code, and Codex. * [Claude Code with Oz](/agent-platform/cloud-agents/harnesses/claude-code/) — Claude Code as a cloud harness. * [Codex with Oz](/agent-platform/cloud-agents/harnesses/codex/) — Codex as a cloud harness. -* [Model choice](/agent-platform/capabilities/model-choice/) — the model catalog Warp Agent routes across. +* [Model choice](/agent-platform/inference/model-choice/) — the model catalog Warp Agent routes across. * [Agent Profiles and permissions](/agent-platform/capabilities/agent-profiles-permissions/) — configure the default model, autonomy, and tool access for Warp Agent. * [Skills as agents](/agent-platform/cloud-agents/skills-as-agents/) — turn a saved skill into a reusable Warp Agent run. diff --git a/src/content/docs/agent-platform/cloud-agents/overview.mdx b/src/content/docs/agent-platform/cloud-agents/overview.mdx index 97340907..744c68fe 100644 --- a/src/content/docs/agent-platform/cloud-agents/overview.mdx +++ b/src/content/docs/agent-platform/cloud-agents/overview.mdx @@ -110,7 +110,7 @@ If your team also uses Warp's terminal, you get an additional workflow: tasks la Cloud agents and [integrations](/agent-platform/cloud-agents/integrations/) run on the [Oz Platform](/agent-platform/cloud-agents/platform/) control plane, and usage is billed using credits. :::note -[Bring Your Own Key (BYOK)](/support-and-community/plans-and-billing/bring-your-own-api-key/) is not supported for cloud agent runs. BYOK keys are stored locally on your device and are not accessible to cloud-hosted agents. All cloud agent runs consume Warp credits. +[Bring Your Own Key (BYOK)](/agent-platform/inference/bring-your-own-api-key/) is not supported for cloud agent runs. BYOK keys are stored locally on your device and are not accessible to cloud-hosted agents. All cloud agent runs consume Warp credits. ::: #### For cloud agents via CLI/API @@ -128,7 +128,7 @@ Integrations require you to be part of a [Warp team](/knowledge-and-collaboratio * **Plan requirements** * **Supported plans**: Build, Max, Business * Not supported: Pro, Turbo, Lightspeed, legacy Business - * Your plan must support Add-on Credits. + * Your plan must support add-on credits. * **Credit requirements** * Your team must have at least 20 credits available to run cloud agents and integrations. diff --git a/src/content/docs/agent-platform/cloud-agents/team-access-billing-and-identity.mdx b/src/content/docs/agent-platform/cloud-agents/team-access-billing-and-identity.mdx index 2c9c768d..4215b5fb 100644 --- a/src/content/docs/agent-platform/cloud-agents/team-access-billing-and-identity.mdx +++ b/src/content/docs/agent-platform/cloud-agents/team-access-billing-and-identity.mdx @@ -76,12 +76,16 @@ Integrations and [cloud agents](/agent-platform/cloud-agents/overview/) run insi Your team must meet the following requirements to run integrations: -* You must be on a plan that supports **[Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/)**. - * Supported: **Build, Max, Business** - * Not supported: Pro, Turbo, Lightspeed, legacy Business. +* You must be on a **Build, Max, or Business** plan with [add-on credits](/support-and-community/plans-and-billing/add-on-credits/) enabled, or on an **Enterprise** plan with a team credit pool per your contract. * Your team needs at least **20 credits** available to run cloud agents and integrations -When a user triggers an agent through an integration (like Slack or Linear), the run draws from credits in a specific order. It starts with any [cloud agent credits](/support-and-community/plans-and-billing/credits/#compute-credits) the user has, then moves to the user's base credits, followed by the team's Add-on Credits, and finally the user's own Add-on Credits. Enterprises may have different payment options and credit plans that affect this flow. If all applicable credit sources are exhausted, integrations and cloud agents will not work until credits are added. +When a user triggers an agent through an integration (like Slack or Linear), the run draws from credits based on who the run is billed to: + +* **User-triggered runs on Build, Max, or Business** - Warp draws from any [cloud agent credits](/support-and-community/plans-and-billing/credits/#compute-credits) the user has, then the user's plan-included credits, then the user's Add-on credits. Add-on credits are scoped to the individual user and are not shared across the team. +* **Team API key or scheduled cloud agent runs on Build, Max, or Business** - Warp bills the team owner. The waterfall is: the owner's plan-included credits, then the owner's Add-on credits. With auto-reload off, the request is blocked when both pools are depleted. With auto-reload on, usage can trigger a reload on the owner's pool subject to the team-wide monthly spend cap. +* **Enterprise plans** - Runs draw from the team-scoped credit pool, per your Enterprise contract terms. + +If all applicable credit sources are exhausted and no auto-reload is configured, integrations and cloud agents will not run until credits are added. See [add-on credits](/support-and-community/plans-and-billing/add-on-credits/) for the full self-serve waterfall and [platform credits](/support-and-community/plans-and-billing/platform-credits/) for the third bucket that applies to every cloud agent run. :::note If you're on an Enterprise plan, please reach out to [warp.dev/contact-sales](https://www.warp.dev/contact-sales) with any billing questions related to integrations. @@ -211,14 +215,16 @@ How credits are consumed depends on how the agent run is triggered and authentic **User-triggered runs** (CLI with personal API key, Slack, Linear, or the Warp app): -* Runs are tied to the triggering user's identity -* Credits are consumed starting with any credit grants specifically allocated for cloud agent usage, then the user's base credits, followed by the team's Add-on Credits, and finally the user's own Add-on Credits +* Runs are tied to the triggering user's identity. +* On Build, Max, and Business plans, credits are consumed starting with any [cloud agent credits](/support-and-community/plans-and-billing/credits/#compute-credits) allocated to the user, then the user's plan-included credits, then the user's Add-on credits. Add-on credits are scoped to the individual user. +* On Enterprise plans, runs draw from the team-scoped credit pool, per your Enterprise contract terms. -**Team API key runs** (fully automated or headless workflows): +**Team API key and scheduled cloud agent runs** (fully automated or headless workflows): -* Runs are not tied to any individual user -* Only the team's Add-on Credit pool is used—no individual base credits are available -* Ideal for CI/CD pipelines, scheduled tasks, and other automated workflows +* Runs are not tied to any individual user. +* On Build, Max, and Business plans, Warp bills the team owner: the owner's plan-included credits, then the owner's Add-on credits. With auto-reload off, the request is blocked when both pools are depleted. With auto-reload on, usage can trigger a reload on the owner's Add-on credit pool subject to the team-wide monthly spend cap. +* On Enterprise plans, these runs draw from the team-scoped credit pool, per your Enterprise contract terms. +* Ideal for CI/CD pipelines, scheduled tasks, and other automated workflows. * For workflows that require code changes (opening pull requests, pushing branches, or writing to a repository), configure [team GitHub authorization](#team-github-authorization) so the agent can authenticate with the Oz by Warp GitHub App. Alternatively, use a [personal API key](/reference/cli/api-keys/) to authenticate as an individual user. For more details on creating and using API keys, see [API Keys](/reference/cli/api-keys/). @@ -236,7 +242,17 @@ All triggers and instructions used by cloud agents are defined and controlled by #### Staying aware of usage -Because triggers and instructions are configured by your team, any credits used when an agent runs are billed to your team's Add-on Credit balance. +Because triggers and instructions are configured by your team, the credits consumed when an agent runs are billed according to the model above: + +* **Build, Max, Business** - User-triggered runs draw from the triggering user's pools (plan-included credits, then their Add-on credits). Team API key and scheduled cloud agent runs are billed to the team owner (the owner's plan-included credits, then the owner's Add-on credits, subject to the team-wide spend cap when auto-reload is on). +* **Enterprise** - All runs draw from the team-scoped credit pool, per your Enterprise contract terms. + +It's the team's responsibility to manage triggers, confirm they behave as intended, and monitor usage. Reviewing triggers, prompts, and agent behavior periodically helps ensure that credit usage aligns with expectations. + +--- + +## Related resources -* It’s the team’s responsibility to manage triggers, confirm they behave as intended, and monitor usage. -* Reviewing triggers, prompts, and agent behavior periodically helps ensure that credit usage aligns with expectations. +* [Add-on credits](/support-and-community/plans-and-billing/add-on-credits/) - How user-scoped add-on credits, auto-reload, and the team-wide spend cap work on self-serve plans. +* [Platform credits](/support-and-community/plans-and-billing/platform-credits/) - The third credit bucket that applies to every cloud agent run, alongside AI credits and compute credits. +* [Credits overview](/support-and-community/plans-and-billing/credits/) - The full credit model across plans. diff --git a/src/content/docs/agent-platform/getting-started/faqs.mdx b/src/content/docs/agent-platform/getting-started/faqs.mdx index a400fed2..206f18ef 100644 --- a/src/content/docs/agent-platform/getting-started/faqs.mdx +++ b/src/content/docs/agent-platform/getting-started/faqs.mdx @@ -25,11 +25,11 @@ Warp reserves the right to use data collected to train models and improve Warp. ### What model are you using for Agent Mode? -Warp supports a curated list of LLMs from providers like OpenAI, Anthropic, and Gemini. To view the full list of supported models and learn how to switch between them, visit the [Model Choice](/agent-platform/capabilities/model-choice/) page. +Warp supports a curated list of LLMs from providers like OpenAI, Anthropic, and Gemini. To view the full list of supported models and learn how to switch between them, visit the [Model Choice](/agent-platform/inference/model-choice/) page. ### Can I use my own LLM API key? -Warp supports [Bring Your Own Key (BYOK)](/support-and-community/plans-and-billing/bring-your-own-api-key/) for users on paid plans (starting with Build). You can connect your own Anthropic, OpenAI, or Google API keys to route requests directly through your account. Organizations on the Enterprise plan can additionally enable managed "Bring Your Own LLM" configurations to meet strict security or compliance requirements. +Warp supports [Bring Your Own Key (BYOK)](/agent-platform/inference/bring-your-own-api-key/) for users on paid plans (starting with Build). You can connect your own Anthropic, OpenAI, or Google API keys to route requests directly through your account. Organizations on the Enterprise plan can additionally enable managed "Bring Your Own LLM" configurations to meet strict security or compliance requirements. ## Billing @@ -52,7 +52,7 @@ To fix this, try: #### "Monthly request limit exceeded" or "Monthly credit limit exceeded" errors -Once you exceed your monthly credit limit (see [pricing](https://www.warp.dev/pricing) for current limits), premium models will be disabled until your quota resets at the start of your next billing cycle. On paid plans with Add-on Credits, you can continue using AI with usage-based billing. +Once you exceed your monthly credit limit (see [pricing](https://www.warp.dev/pricing) for current limits), premium models will be disabled until your quota resets at the start of your next billing cycle. On paid plans with add-on credits, you can continue using AI with usage-based billing. **Request failed with error: QuotaLimit** diff --git a/src/content/docs/support-and-community/plans-and-billing/bring-your-own-api-key.mdx b/src/content/docs/agent-platform/inference/bring-your-own-api-key.mdx similarity index 52% rename from src/content/docs/support-and-community/plans-and-billing/bring-your-own-api-key.mdx rename to src/content/docs/agent-platform/inference/bring-your-own-api-key.mdx index 69aa1dfe..bcd48a5f 100644 --- a/src/content/docs/support-and-community/plans-and-billing/bring-your-own-api-key.mdx +++ b/src/content/docs/agent-platform/inference/bring-your-own-api-key.mdx @@ -1,29 +1,39 @@ --- title: Bring Your Own API Key description: >- - Warp's paid plans include the ability to bring your own API keys (BYOK) for - OpenAI, Anthropic, and Google AI models. + Warp lets you bring your own API keys (BYOK) for OpenAI, Anthropic, and + Google AI models. --- -Warp supports **Bring Your Own Key (BYOK)** for users who want to connect Warp’s agent to their own Anthropic, OpenAI, or Google API accounts. +Warp supports **Bring Your Own API Key (BYOK)** for users who want to connect Warp's agents to their own Anthropic, OpenAI, or Google API accounts. -This lets you use your own API keys to access models directly, giving you full control over model selection, billing, and data routing. See [Model Choice](/agent-platform/capabilities/model-choice/) for a list of supported models. +This lets you use your own API keys to access models directly, giving you full control over model selection, billing, and data routing. See [Model Choice](/agent-platform/inference/model-choice/) for a list of supported models. -BYOK provides greater flexibility in model access and ensures Warp **never consumes your** [credits](/support-and-community/plans-and-billing/credits/) for requests routed through your own keys. +BYOK provides greater flexibility in model access and ensures Warp **never consumes your** [AI credits](/support-and-community/plans-and-billing/credits/) for requests routed through your own keys. :::note -BYOK is currently only available on Warp's paid plans, starting with Build. Learn more about plans and pricing [warp.dev/pricing](https://www.warp.dev/pricing). +BYOK is available on Free and all eligible paid plans for individual users and organizations with 10 or fewer employees, subject to Warp's [Terms of Service](https://www.warp.dev/terms-of-service). Larger organizations need a Business or Enterprise plan. See [warp.dev/pricing](https://www.warp.dev/pricing) for current availability. ::: -:::caution -BYOK and customer-supplied inference (BYOLLM via Amazon Bedrock or Google Vertex, plus custom endpoints) are available to individual users and organizations with 10 or fewer employees or users on any plan. Organizations with more than 10 employees or users must be on a Warp Business or Enterprise plan to use BYOK or customer-supplied inference. See Warp's [Terms of Service](https://www.warp.dev/terms-of-service) for details. -::: +## How BYOK differs from custom inference endpoints and BYOLLM + +Warp offers three ways to bring your own AI infrastructure. Use this table to pick the right one, and follow the links for full details. + +| Name | Meaning | Plans | +| --- | --- | --- | +| **Bring your own API key** (BYOK) | Use your own API key for OpenAI, Anthropic, or Google models. Keys are stored locally on your device. | Free and all eligible paid plans | +| **[Custom inference endpoint](/agent-platform/inference/custom-inference-endpoint/)** | Connect Warp to an OpenAI-compatible endpoint such as OpenRouter, LiteLLM, z.ai, or an internal gateway. | Free and all eligible paid plans | +| **[Bring your own LLM](/enterprise/enterprise-features/bring-your-own-llm/)** (BYOLLM) | Enterprise-managed inference through your cloud provider (AWS Bedrock today; Azure Foundry and Google Vertex coming soon), with Warp handling routing, orchestration, governance, and observability. | Enterprise only | + +See [warp.dev/pricing](https://www.warp.dev/pricing) for current plan availability. + +Platform credits apply to every cloud agent run on any plan, and to local agent runs on Business and Enterprise when using BYOK, a custom inference endpoint, or BYOLLM. See [platform credits](/support-and-community/plans-and-billing/platform-credits/) for the full breakdown. -## How does BYOK work? +## How BYOK works When you add your own model API keys in Warp, those keys are stored **locally on your device** and are **never synced to the cloud**. -Warp uses these API keys to directly route your agent requests to the model provider you've configured. +Warp uses these API keys when routing your agent requests to the model provider you've configured. :::caution BYOK does not apply to [Cloud Agents](/agent-platform/cloud-agents/overview/). Because your API keys are stored locally on your device, they are not available to cloud-hosted agent runs. Cloud agent runs always consume [Warp credits](/support-and-community/plans-and-billing/credits/). @@ -57,21 +67,20 @@ When you explicitly select a model with a key icon, Warp routes requests through ### Auto Model -Warp's **Auto** models dynamically route requests across different models based on context and performance. Because this routing logic depends on Warp’s infrastructure, **Auto always consumes Warp's credits**, even if you’ve configured your own API keys. +Warp's **Auto** models dynamically route requests across different models based on context and performance. Because this routing logic depends on Warp's infrastructure, **Auto always consumes Warp's credits**, even if you've configured your own API keys. -To use your own key, select a specific provider model (for example, Claude Sonnet 4.5, GPT-5, or Gemini 2.5 Pro) directly from the model picker with a key icon. +To use your own key, select a specific provider model (for example, Claude Opus 4.7, Claude Sonnet 4.6, GPT-5.5, or Gemini 3.1 Pro) directly from the model picker with a key icon. ### Credit usage -When you select a model with the key icon in your model picker, Warp routes the request through your API key. +When you select a model with the key icon in your model picker, Warp routes the request through your API key. In that case: -In this case: +* Inference is billed directly through your provider account rather than drawing from your Warp AI credits. +* Agent Mode prioritizes BYOK over any available Warp credits. -* No Warp credits are consumed. -* The cost of the request is billed directly through your provider account. -* Core Agent Mode always **prioritizes BYOK usage** over any available credits. - -The credit transparency footer will show “0 credits used”, and the `Billing & Usage` page will reflect no deductions from your monthly credit total. +:::note +On Business and Enterprise plans, local agent runs that use BYOK still consume platform credits for Warp's platform infrastructure (run lifecycle, integrations, observability). See [platform credits](/support-and-community/plans-and-billing/platform-credits/) for what's covered. +::: **Other AI features in Warp** @@ -93,11 +102,12 @@ If your key: * Is invalid: Warp notifies you and halts the request. * Hits usage or rate limits: Warp will not retry using credits. -* You can update or replace your keys anytime by opening **Settings** and searching for `API keys`. + +You can update or replace your keys anytime by opening **Settings** and searching for `API keys`. **Failover and fallback:** -By default, Warp does not fall back to your credits when a BYOK (Bring Your Own Key) request fails. +By default, Warp does not fall back to your credits when a BYOK request fails. You can choose to enable **Warp credit fallback**. When enabled, if an agent request fails with your BYOK model (for example, due to an API error or quota limit), Warp will automatically route the request to one of Warp’s provided models. Warp always prioritizes your API keys first and only uses Warp credits when necessary. @@ -117,12 +127,17 @@ Warp itself never stores your LLM API keys. ### BYOK on Enterprise and Business plans -Organizations with more than 10 employees or users must be on a Warp Business or Enterprise plan to use BYOK or customer-supplied inference. See Warp's [Terms of Service](https://www.warp.dev/terms-of-service) for the full eligibility rule. +BYOK is configured at the **user level** on every plan, including Enterprise and Business: + +* Each team member adds and manages their own API keys locally on their device. +* Centrally configured, admin-managed BYOK is not yet available — admins cannot enforce or share API keys across team members from a single place. +* There is no organization-level Admin Panel for BYOK management today. -Currently, BYOK is configured at the **user level**, not the team or admin level: +If your organization needs centrally managed model routing today, see [Bring your own LLM](/enterprise/enterprise-features/bring-your-own-llm/) for the Enterprise-managed option, or [contact sales](https://www.warp.dev/contact-sales). -* Each team member can add and manage their own API keys locally. -* Team admins cannot yet enforce or share API keys across members. -* There is currently no organization-level Admin Panel for BYOK management. +## Related resources -If your organization has specific needs for managed keys or enterprise-level control, please contact us at [warp.dev/contact-sales](https://www.warp.dev/contact-sales). +* [Custom inference endpoint](/agent-platform/inference/custom-inference-endpoint/) — Route Warp through any OpenAI-compatible endpoint, such as OpenRouter, LiteLLM, z.ai, or an internal gateway. +* [Bring your own LLM](/enterprise/enterprise-features/bring-your-own-llm/) — Enterprise-managed inference through your cloud provider or approved infrastructure. +* [Model Choice](/agent-platform/inference/model-choice/) — Full list of supported models and `model_id` values. +* [Credits](/support-and-community/plans-and-billing/credits/) — How Warp credits work and when they're consumed. diff --git a/src/content/docs/agent-platform/inference/custom-inference-endpoint.mdx b/src/content/docs/agent-platform/inference/custom-inference-endpoint.mdx new file mode 100644 index 00000000..7248661d --- /dev/null +++ b/src/content/docs/agent-platform/inference/custom-inference-endpoint.mdx @@ -0,0 +1,112 @@ +--- +title: Custom inference endpoint +description: >- + Connect Warp's agents to any OpenAI-compatible inference endpoint — + OpenRouter, LiteLLM, z.ai, or an internal gateway you already run. +--- + +Warp supports **custom inference endpoints** for users who want to power Warp's agents with any OpenAI-compatible inference endpoint — a model router, hosted gateway, or internal infrastructure they already run. + +This lets you route AI requests through your preferred provider, run inference behind your own gateway, or use a router like OpenRouter or LiteLLM, while keeping the agent experience inside Warp. + +:::note +Custom inference endpoints are available on Free and all eligible paid plans for individual users and organizations with 10 or fewer employees, subject to Warp's [Terms of Service](https://www.warp.dev/terms-of-service). Larger organizations need a Business or Enterprise plan. See [warp.dev/pricing](https://www.warp.dev/pricing) for current availability. +::: + +## Key features + +* **OpenAI-compatible** - Works with any endpoint that implements the OpenAI Chat Completions API. +* **Provider flexibility** - Use a model router (OpenRouter, LiteLLM), a model provider with an OpenAI-compatible surface (z.ai), or your own internal gateway. +* **No AI credits consumed for inference** - Inference is billed directly by your endpoint provider. On Business and Enterprise, local agent runs that route through a custom inference endpoint still consume [platform credits](/support-and-community/plans-and-billing/platform-credits/) for Warp's platform infrastructure. +* **Local configuration** - Endpoint URLs and credentials are stored locally on your device and never synced to the cloud. + +## How it works + +A custom inference endpoint expects your endpoint to implement the **OpenAI Chat Completions API** (`POST /v1/chat/completions`). Any service that exposes a compatible surface can be used as a target: + +* **OpenRouter** - Aggregates many model providers behind a single OpenAI-compatible API and consolidated billing. +* **LiteLLM** - A self-hosted proxy that exposes a unified, OpenAI-compatible API across providers. +* **z.ai** - A model provider with an OpenAI-compatible API surface for its models. +* **Internal gateways** - Any in-house service that fronts model providers behind an OpenAI-compatible endpoint (for example, a corporate AI gateway with logging, redaction, or access control). + +When you configure a custom inference endpoint, Warp stores the endpoint URL, model identifiers, and credentials **locally on your device**. They are never synced to Warp's servers. + +:::caution +Custom inference endpoints don't apply to [Cloud Agents](/agent-platform/cloud-agents/overview/). Because the configuration is stored locally, it isn't available to cloud-hosted agent runs. Cloud agent runs always consume [Warp credits](/support-and-community/plans-and-billing/credits/). +::: + +When a model routed through your endpoint is selected: + +* Warp **doesn't consume** your [AI credits](/support-and-community/plans-and-billing/credits/) for that request. +* Costs are billed directly by your endpoint provider. +* Warp doesn't retain or store your endpoint credentials on any of its servers. + +## Enabling a custom inference endpoint + +To enable and configure a custom inference endpoint: + +1. In Warp, open **Settings** and search for `inference endpoint` to jump to the configuration. +2. Add your endpoint URL (the base URL that exposes `/v1/chat/completions`) and any required credentials (typically an API key). +3. Specify the model identifier(s) you want to route through this endpoint. +4. Save the configuration. Once added, you'll see your custom models appear in the model picker. + +When you explicitly select an endpoint-routed model from the model picker, Warp routes the request through your endpoint instead of consuming Warp's AI credits. + +The configuration flow mirrors the [Bring your own API key](/agent-platform/inference/bring-your-own-api-key/) setup, so the steps will feel familiar if you've already configured BYOK. + +## Billing behavior + +### Warp AI credits + +When you select an endpoint-routed model from the model picker, inference is billed directly by your endpoint provider, according to their pricing, rather than drawing from your Warp AI credits. + +:::note +On Business and Enterprise plans, local agent runs that route through a custom inference endpoint still consume platform credits for Warp's platform infrastructure. See [platform credits](/support-and-community/plans-and-billing/platform-credits/) for the full breakdown. +::: + +### Auto routing still uses Warp credits + +Warp's **Auto** models dynamically route across providers using Warp's infrastructure. Because Auto routing depends on Warp, **Auto always consumes Warp's credits**, even if you've configured a custom inference endpoint. + +To use your endpoint, select the specific endpoint-routed model from the model picker rather than an Auto option. + +### Other AI features in Warp + +Some AI-powered features (Codebase Context, Active AI recommendations, cloud agent runs) rely on Warp's infrastructure and are unaffected by a custom inference endpoint. See the [feature breakdown on the BYOK page](/agent-platform/inference/bring-your-own-api-key/#byok-usage-and-billing-behavior) for which features still consume Warp credits. + +## Zero Data Retention (ZDR) + +Warp is **SOC 2 compliant** and has **Zero Data Retention (ZDR)** agreements with all of its contracted LLM providers. + +When you use a custom inference endpoint: + +* Data retention is determined by **your endpoint provider** and any upstream model providers they route to. +* Warp **cannot enforce ZDR** for requests sent through a custom inference endpoint. +* If your endpoint provider does not have ZDR with the underlying model provider, your requests may be retained according to their terms. + +Review your endpoint provider's data handling and retention policies before routing sensitive prompts through a custom inference endpoint. + +## Centrally managed configuration + +Custom inference endpoints are configured at the **user level** on every plan. Each user adds their own endpoint locally; centrally configured, admin-managed endpoints for teams are not yet available. + +Enterprise teams that need centrally managed model routing today should see [Bring your own LLM](/enterprise/enterprise-features/bring-your-own-llm/). + +## How custom inference endpoints differ from BYOK and BYOLLM + +Warp offers three ways to bring your own AI infrastructure. Use this table to pick the right one, and follow the links for full details. + +| Name | Meaning | Plans | +| --- | --- | --- | +| **[Bring your own API key](/agent-platform/inference/bring-your-own-api-key/)** (BYOK) | Use your own API key for OpenAI, Anthropic, or Google models. Keys are stored locally on your device. | Free and all eligible paid plans | +| **Custom inference endpoint** | Connect Warp to an OpenAI-compatible endpoint such as OpenRouter, LiteLLM, z.ai, or an internal gateway. | Free and all eligible paid plans | +| **[Bring your own LLM](/enterprise/enterprise-features/bring-your-own-llm/)** (BYOLLM) | Enterprise-managed inference through your cloud provider (AWS Bedrock today; Azure Foundry and Google Vertex coming soon), with Warp handling routing, orchestration, governance, and observability. | Enterprise only | + +Platform credits may apply for local agent runs on Business and Enterprise when using BYOK, a custom inference endpoint, or BYOLLM. See [platform credits](/support-and-community/plans-and-billing/platform-credits/). + +## Related resources + +* [Bring your own API key](/agent-platform/inference/bring-your-own-api-key/) — Use your own OpenAI, Anthropic, or Google API keys. +* [Bring your own LLM](/enterprise/enterprise-features/bring-your-own-llm/) — Enterprise-managed inference through your cloud provider or approved infrastructure. +* [Model Choice](/agent-platform/inference/model-choice/) — Full list of supported models and `model_id` values. +* [Credits](/support-and-community/plans-and-billing/credits/) — How Warp credits work and when they're consumed. diff --git a/src/content/docs/agent-platform/capabilities/model-choice.mdx b/src/content/docs/agent-platform/inference/model-choice.mdx similarity index 100% rename from src/content/docs/agent-platform/capabilities/model-choice.mdx rename to src/content/docs/agent-platform/inference/model-choice.mdx diff --git a/src/content/docs/agent-platform/local-agents/agent-context/images-as-context.mdx b/src/content/docs/agent-platform/local-agents/agent-context/images-as-context.mdx index 6e7adfde..fd3062ad 100644 --- a/src/content/docs/agent-platform/local-agents/agent-context/images-as-context.mdx +++ b/src/content/docs/agent-platform/local-agents/agent-context/images-as-context.mdx @@ -40,7 +40,7 @@ You can attach up to **5 images per request**, and up to **20 images across a si ### Model behavior and image handling -All supported models listed in [Model Choice](/agent-platform/capabilities/model-choice/) can interpret image input. +All supported models listed in [Model Choice](/agent-platform/inference/model-choice/) can interpret image input. Attaching images will consume additional requests, proportional to the number of images added. To stay within model limits, Warp will intelligently resize images before passing them as context, minimizing token usage and respecting the model's maximum image dimensions. diff --git a/src/content/docs/agent-platform/local-agents/overview.mdx b/src/content/docs/agent-platform/local-agents/overview.mdx index c1cf191f..5a96c27d 100644 --- a/src/content/docs/agent-platform/local-agents/overview.mdx +++ b/src/content/docs/agent-platform/local-agents/overview.mdx @@ -26,7 +26,7 @@ This section covers how to interact with Warp's agents and the capabilities avai * [Interacting with Agents](/agent-platform/local-agents/interacting-with-agents/) - Manage AI conversations tied to sessions, attach context, continue previous threads, or start new ones. * [Agent Context](/agent-platform/local-agents/agent-context/) - Attach images, URLs, files, code blocks, and selections as context for your prompts. -* [Model Choice](/agent-platform/capabilities/model-choice/) - Pick your preferred LLM from a curated set of top models, or let Warp choose the optimal one. +* [Model Choice](/agent-platform/inference/model-choice/) - Pick your preferred LLM from a curated set of top models, or let Warp choose the optimal one. * [Full Terminal Use](/agent-platform/capabilities/full-terminal-use/) - Let the agent drive interactive terminal apps, seeing live output and running commands. * [Interactive Code Review](/agent-platform/local-agents/interactive-code-review/) - Review agent-generated diffs, leave inline comments, and have the agent address your feedback. * [Task Lists](/agent-platform/capabilities/task-lists/) - Track complex workflows with automatic task lists that update progress in real time. diff --git a/src/content/docs/enterprise/enterprise-features/bring-your-own-llm.mdx b/src/content/docs/enterprise/enterprise-features/bring-your-own-llm.mdx index 6b4fc6b9..c0b662ff 100644 --- a/src/content/docs/enterprise/enterprise-features/bring-your-own-llm.mdx +++ b/src/content/docs/enterprise/enterprise-features/bring-your-own-llm.mdx @@ -54,7 +54,7 @@ BYOLLM supports the intersection of models that Warp supports and models availab To determine which models you can use with BYOLLM: -* [Model Choice](/agent-platform/capabilities/model-choice/) - Full list of Warp-supported models. +* [Model Choice](/agent-platform/inference/model-choice/) - Full list of Warp-supported models. * [Supported models in Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) - AWS Bedrock model availability. A model must appear on both lists to be available through BYOLLM. @@ -222,7 +222,7 @@ Yes. Admins can configure routing policies to require specific models to use BYO ## Related resources -* [Bring Your Own API Key](/support-and-community/plans-and-billing/bring-your-own-api-key/) -* [Model Choice](/agent-platform/capabilities/model-choice/) — Full list of supported models +* [Bring Your Own API Key](/agent-platform/inference/bring-your-own-api-key/) +* [Model Choice](/agent-platform/inference/model-choice/) — Full list of supported models * [Admin Panel](/enterprise/team-management/admin-panel/) — Configure team settings * [Contact Sales](https://www.warp.dev/contact-sales) — Get help with enterprise setup diff --git a/src/content/docs/enterprise/support-and-resources/billing.mdx b/src/content/docs/enterprise/support-and-resources/billing.mdx index b9f91462..f4a8ab3f 100644 --- a/src/content/docs/enterprise/support-and-resources/billing.mdx +++ b/src/content/docs/enterprise/support-and-resources/billing.mdx @@ -70,7 +70,11 @@ Enterprise administrators can set monthly spending limits across the following f * **Total spending limit** - Cap combined monthly spend across both cloud and local agents. * **Per-user spending limit** - Cap monthly spend for any individual user. Set a default that applies to all users, or configure limits on a per-user basis for predictable individual spend. -Spending is tracked across all payment types (Add-on Credits, pay-as-you-go usage) so limits apply consistently regardless of how usage is funded. +Spending is tracked across all payment types (add-on credits, pay-as-you-go usage) so limits apply consistently regardless of how usage is funded. + +:::note +Team-wide spending limits (cloud, local, and total) are also available on Warp's self-serve paid plans through admin-managed Add-on credit settings. **Per-user spending limits are Enterprise-only.** For deeper visibility into how individual users consume credits, see the [Enterprise Analytics API](/enterprise/enterprise-features/analytics-api/). +::: #### Monthly spend alerts @@ -83,7 +87,9 @@ For enterprises with credit pools, administrators receive alerts as the team cre ## Related resources * [Credits](/support-and-community/plans-and-billing/credits/) - How credits are calculated and consumed -* [Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/) - Purchase additional credits and configure auto-reload +* [Add-on credits](/support-and-community/plans-and-billing/add-on-credits/) - Purchase additional credits and configure auto-reload +* [Platform credits](/support-and-community/plans-and-billing/platform-credits/) - The third credit bucket alongside AI credits and compute credits, covering Warp's platform infrastructure * [Pricing FAQs](/support-and-community/plans-and-billing/pricing-faqs/) - Common billing questions * [Bring Your Own LLM](/enterprise/enterprise-features/bring-your-own-llm/) - BYOLLM billing and configuration +* [Enterprise Analytics API](/enterprise/enterprise-features/analytics-api/) - Programmatic access to team usage and spend data * [Admin Panel](/enterprise/team-management/admin-panel/) - Configure spending limits and billing settings diff --git a/src/content/docs/enterprise/team-management/teams.mdx b/src/content/docs/enterprise/team-management/teams.mdx index 544aa3ef..e645e04f 100644 --- a/src/content/docs/enterprise/team-management/teams.mdx +++ b/src/content/docs/enterprise/team-management/teams.mdx @@ -21,7 +21,6 @@ Each Warp user can be an admin or member of one team at a time. You can create a new team in two ways: -{/* TODO: Add screenshots for both team creation entry points */} * From the **Warp Drive** side panel, click **+ Create a team**. * In Warp, navigate to **Settings** > **Teams** and follow the prompts. @@ -64,6 +63,16 @@ If you've received an invite link, use it to sign up or log in and join the team If you're a Team Owner and choose to [delete your Warp account](/support-and-community/privacy-and-security/privacy/#delete-your-account-and-data), you'll need to assign a team member as the new owner before your account can be deleted. ::: +### Add-on credit consequences when leaving or removing members + +On Build, Max, and Business plans, [add-on credits](/support-and-community/plans-and-billing/add-on-credits/) are scoped to each individual user but **tied to the team** they were purchased under. Membership changes affect access: + +* **A user leaves a team** - You lose access to any add-on credits tied to that team. If you rejoin the same team later, you regain access to any unused, non-expired credits. The admin pays a prorated rate for your seat on rejoin. +* **An admin removes a member** - That member loses access to any add-on credits tied to the team. If they rejoin later, they regain access to any unused, non-expired credits. The admin pays a prorated rate for the seat when the user rejoins. +* **An admin deletes the team** - Any remaining add-on credits tied to the team are no longer usable. + +Add-on credits require an active subscription. Downgrading to the Free plan forfeits access to add-on credits tied to your team. + ## Team discoverability Team admins can make their team discoverable to colleagues who share the same email domain. When enabled, new users with a matching domain can find and join the team without needing a direct invite link. @@ -78,7 +87,6 @@ While discoverability is enabled, any new user who joins the team will add a pro Team Owners can transfer ownership to another team member: -{/* TODO: Add screenshot of transfer ownership flow */} 1. Navigate to **Settings** > **Teams** > **Team Members**. 2. Click the three-dot menu icon next to the member you want to transfer ownership to. 3. Click **Transfer ownership**. @@ -103,13 +111,13 @@ We recommend having at least one Team Admin in addition to the Team Owner to pre ### Permissions overview -| | Owner | Admin | Member | +| Action | Owner | Admin | Member | | --- | --- | --- | --- | -|| Create a team | ✓ | ✓ | ✓ | +| Create a team | ✓ | ✓ | ✓ | | Restrict invites by domain | ✓ | ✓ | | | Invite members | ✓ | ✓ | ✓ | | Remove team members | ✓ | ✓ | | -|| Leave a team | | ✓ | ✓ | +| Leave a team | | ✓ | ✓ | | Delete a team | ✓ | | | | Transfer ownership | ✓ | | | | Promote/demote admins | ✓ | ✓ | | @@ -122,7 +130,6 @@ Teams on the **Enterprise** plan can have multiple admins, enabling distributed To promote or demote a team admin: -{/* TODO: Add screenshot of promote/demote admin flow */} 1. Navigate to **Settings** > **Teams** > **Team Members**. 2. Find the user you want to modify and click the three-dot menu icon next to their name. 3. Click **Promote to Admin** or **Demote from Admin**. diff --git a/src/content/docs/getting-started/migrate-to-warp/migrate-to-warp-from-claude-code.mdx b/src/content/docs/getting-started/migrate-to-warp/migrate-to-warp-from-claude-code.mdx index d1ccffca..b480f0e4 100644 --- a/src/content/docs/getting-started/migrate-to-warp/migrate-to-warp-from-claude-code.mdx +++ b/src/content/docs/getting-started/migrate-to-warp/migrate-to-warp-from-claude-code.mdx @@ -67,7 +67,7 @@ Warp's agent also pulls context from several other explicit sources: * **Bring over your `CLAUDE.md`.** Rename it to `AGENTS.md` (or copy it into a Warp [Rule](/agent-platform/capabilities/rules/) if you want it scoped beyond the repo). Warp applies it automatically to new conversations. * **Set up [MCP servers](/agent-platform/capabilities/mcp/)** you relied on in Claude Code. -* **Pick a model** per conversation using the model selector. See [model choice](/agent-platform/capabilities/model-choice/). Warp supports Claude, GPT, Gemini, and Auto. +* **Pick a model** per conversation using the model selector. See [model choice](/agent-platform/inference/model-choice/). Warp supports Claude, GPT, Gemini, and Auto. * **Configure [agent profiles and permissions](/agent-platform/capabilities/agent-profiles-permissions/)** for what the agent can auto-execute. ### Key differences from Claude Code diff --git a/src/content/docs/getting-started/migrate-to-warp/migrate-to-warp-from-cursor.mdx b/src/content/docs/getting-started/migrate-to-warp/migrate-to-warp-from-cursor.mdx index fa431f3c..60584305 100644 --- a/src/content/docs/getting-started/migrate-to-warp/migrate-to-warp-from-cursor.mdx +++ b/src/content/docs/getting-started/migrate-to-warp/migrate-to-warp-from-cursor.mdx @@ -40,7 +40,7 @@ Cursor's Composer and Agent features don't have a one-to-one migration path - th ### Model choice -Cursor lets you pick a model per conversation. Warp does the same - use the model selector in any agent conversation. See [model choice](/agent-platform/capabilities/model-choice/). +Cursor lets you pick a model per conversation. Warp does the same - use the model selector in any agent conversation. See [model choice](/agent-platform/inference/model-choice/). ### Keybindings @@ -71,7 +71,7 @@ Cursor features and their Warp counterparts: | Agent tabs | Multiple [agents in parallel](/agent-platform/local-agents/overview/) across tabs | | `.cursorrules` | `AGENTS.md` / `WARP.md` at the project root, picked up as a [Rule](/agent-platform/capabilities/rules/) | | MCP servers | [MCP](/agent-platform/capabilities/mcp/) | -| Model choice per conversation | [Model selector](/agent-platform/capabilities/model-choice/) | +| Model choice per conversation | [Model selector](/agent-platform/inference/model-choice/) | | Codebase indexing | [Codebase Context](/agent-platform/capabilities/codebase-context/) | | Inline diff review | [Code Review](/code/code-review/) | diff --git a/src/content/docs/getting-started/quickstart/customizing-warp.mdx b/src/content/docs/getting-started/quickstart/customizing-warp.mdx index 3864595f..aa1a77bf 100644 --- a/src/content/docs/getting-started/quickstart/customizing-warp.mdx +++ b/src/content/docs/getting-started/quickstart/customizing-warp.mdx @@ -63,7 +63,7 @@ Configure how you type and interact with the terminal input. Control how Warp's agents behave and which models they use. -* **[Model choice](/agent-platform/capabilities/model-choice/)** - Choose your preferred AI model (Claude, GPT, Gemini, or Auto) from the model selector in any agent conversation. +* **[Model choice](/agent-platform/inference/model-choice/)** - Choose your preferred AI model (Claude, GPT, Gemini, or Auto) from the model selector in any agent conversation. * **[Agent profiles and permissions](/agent-platform/capabilities/agent-profiles-permissions/)** - Configure how much autonomy the agent has: what it can auto-execute, what requires approval, and command allowlists/denylists. * **Default mode for new sessions** - Choose whether new tabs open in terminal mode or Agent Mode by default. Set this in **Settings** > **Agents** > **Warp Agent** > **Input**. diff --git a/src/content/docs/index.mdx b/src/content/docs/index.mdx index 9e489ea2..a93be368 100644 --- a/src/content/docs/index.mdx +++ b/src/content/docs/index.mdx @@ -79,7 +79,7 @@ Warp and Oz provide a unified experience across local and cloud development: ## Multi-model support -Oz is multi-model by design. You can [choose your preferred LLM](/agent-platform/capabilities/model-choice/) from a curated set of top models. +Oz is multi-model by design. You can [choose your preferred LLM](/agent-platform/inference/model-choice/) from a curated set of top models. --- diff --git a/src/content/docs/knowledge-and-collaboration/teams.mdx b/src/content/docs/knowledge-and-collaboration/teams.mdx index 7c3f8f76..70b7dc12 100644 --- a/src/content/docs/knowledge-and-collaboration/teams.mdx +++ b/src/content/docs/knowledge-and-collaboration/teams.mdx @@ -24,10 +24,10 @@ You can create a new team in the following ways: * Warp Drive, + Create a team * **Settings** > **Teams** -Before you can invite team members, you will need to give your team a meaningful name. We suggest using a name to represent your organization, company, or project. +Before you can invite team members, you will need to give your team a meaningful name. We suggest using a name to represent your organization, company, or project. :::note -You can rename the team by going to **Settings** > **Teams** and clicking on the team name, entering the new name, and pressing `ENTER` to accept. +You can rename the team by going to **Settings** > **Teams** and clicking on the team name, entering the new name, and pressing `Enter` to accept. ::: ![Teams settings panel with a team name input field and Create button](../../../assets/terminal/team-creation-settings.png) @@ -67,6 +67,14 @@ If you have received an invite link, you can use that link to sign up or log in If you’re a member of a team, you can visit **Settings** > **Teams** to leave a team at any time. Team admins (who created teams) may delete a team only after removing all team members. +On Build, Max, and Business plans, [add-on credits](/support-and-community/plans-and-billing/add-on-credits/) are scoped to each individual user but **tied to the team** they were purchased under. Membership changes affect access: + +* **A user leaves a team** - You lose access to any add-on credits tied to that team. If you rejoin the same team later, you regain access to any unused, non-expired credits. The admin pays a prorated rate for your seat on rejoin. +* **An admin removes a member** - That member loses access to any add-on credits tied to the team. If they rejoin later, they regain access to any unused, non-expired credits. The admin pays a prorated rate for the seat when the user rejoins. +* **An admin deletes the team** - Any remaining add-on credits tied to the team are no longer usable. + +Add-on credits require an active subscription. Downgrading to the Free plan forfeits access to add-on credits tied to your team. + ## Team discoverability Team admins can make their teams discoverable to colleagues from the same email domain. This feature is available under **Settings** > **Teams** > **Make team discoverable**. @@ -85,14 +93,14 @@ Team admins can transfer their role to another team member by going to **Setting If you're a Team admin, and you choose to [delete your Warp](/support-and-community/privacy-and-security/privacy/#manage-your-data) account, the deletion flow will require that you assign a team member as the new admin. ::: -| | Admin | Member | -| ------------------------------------------------------------- | ---------------------------------------------------------------- | -------------------------------------- | -| | This is the Warp user who created a team. There can only be one. | All team members who belong to a team. | -| Create a team | ✓ | | -| Restrict by domain | ✓ | | -| Invite members | ✓ | ✓ | -| Remove team members | ✓ | | -| Leave a team | | ✓ | -| Delete a team | ✓ | | -| Transfer admin | ✓ | | -| [Manage billing](/support-and-community/plans-and-billing/plans-pricing-refunds/) | ✓ | | +| Action | Admin | Member | +| --- | --- | --- | +| Description | The Warp user who created the team. There can only be one. | Team members who belong to the team. | +| Create a team | ✓ | | +| Restrict by domain | ✓ | | +| Invite members | ✓ | ✓ | +| Remove team members | ✓ | | +| Leave a team | | ✓ | +| Delete a team | ✓ | | +| Transfer admin | ✓ | | +| [Manage billing](/support-and-community/plans-and-billing/plans-pricing-refunds/) | ✓ | | diff --git a/src/content/docs/reference/api-and-sdk/troubleshooting/errors/index.mdx b/src/content/docs/reference/api-and-sdk/troubleshooting/errors/index.mdx index 5a7466cb..348dab0d 100644 --- a/src/content/docs/reference/api-and-sdk/troubleshooting/errors/index.mdx +++ b/src/content/docs/reference/api-and-sdk/troubleshooting/errors/index.mdx @@ -52,7 +52,7 @@ Errors are split into two categories based on what caused the failure: These indicate something the caller needs to fix. When a cloud agent task encounters a user error, the task transitions to the **FAILED** state. -* [`insufficient_credits`](/reference/api-and-sdk/troubleshooting/errors/insufficient-credits/) — Team has no remaining Add-on Credits +* [`insufficient_credits`](/reference/api-and-sdk/troubleshooting/errors/insufficient-credits/) — Team has no remaining add-on credits * [`feature_not_available`](/reference/api-and-sdk/troubleshooting/errors/feature-not-available/) — Feature not included in your current plan * [`external_authentication_required`](/reference/api-and-sdk/troubleshooting/errors/external-authentication-required/) — External service authorization needed * [`not_authorized`](/reference/api-and-sdk/troubleshooting/errors/not-authorized/) — Insufficient permissions for the operation diff --git a/src/content/docs/reference/api-and-sdk/troubleshooting/errors/insufficient-credits.mdx b/src/content/docs/reference/api-and-sdk/troubleshooting/errors/insufficient-credits.mdx index fab60455..34df8fe8 100644 --- a/src/content/docs/reference/api-and-sdk/troubleshooting/errors/insufficient-credits.mdx +++ b/src/content/docs/reference/api-and-sdk/troubleshooting/errors/insufficient-credits.mdx @@ -1,11 +1,11 @@ --- title: insufficient_credits description: >- - Your team has exhausted all Add-on Credits for cloud agent usage. Purchase + Your team has exhausted all add-on credits for cloud agent usage. Purchase more credits from your team's billing settings to continue. --- -The `insufficient_credits` error occurs when your team has no remaining Add-on Credits to run cloud agents or integrations. +The `insufficient_credits` error occurs when your team has no remaining add-on credits to run cloud agents or integrations. --- @@ -21,7 +21,7 @@ The `insufficient_credits` error occurs when your team has no remaining Add-on C This error is returned when: -* Your team's Add-on Credits balance has reached zero +* Your team's add-on credits balance has reached zero * A cloud agent task, scheduled run, or integration-triggered run (Slack, Linear) attempts to start but cannot be billed Cloud agent runs consume credits based on usage. When credits are depleted, no new runs can start until credits are replenished. @@ -33,7 +33,7 @@ Cloud agent runs consume credits based on usage. When credits are depleted, no n ```json { "type": "/reference/api-and-sdk/troubleshooting/errors/insufficient-credits/", - "title": "Your team has run out of Add-on Credits. Purchase more credits in your team's billing settings to continue.", + "title": "Your team has run out of add-on credits. Purchase more credits in your team's billing settings to continue.", "status": 403, "instance": "/api/v1/agent/tasks", "title": "Your team has run out of add-on credits. Purchase more credits in your team's billing settings to continue.", @@ -49,7 +49,7 @@ Cloud agent runs consume credits based on usage. When credits are depleted, no n ## How to resolve 1. Go to your team's billing settings in the [Oz web app](https://oz.warp.dev) or Warp desktop app. -2. Purchase additional Add-on Credits. +2. Purchase additional add-on credits. 3. Retry the failed operation. If you are not a team admin, contact your team admin to purchase credits. diff --git a/src/content/docs/reference/cli/api-keys.mdx b/src/content/docs/reference/cli/api-keys.mdx index 0d2fb031..3a4eaac4 100644 --- a/src/content/docs/reference/cli/api-keys.mdx +++ b/src/content/docs/reference/cli/api-keys.mdx @@ -43,10 +43,10 @@ Team keys without GitHub App authorization are the right fit for automated workf Warp supports two types of API keys, each with different billing and identity behavior: -* **Personal API keys** - Cloud agent runs authenticate as you. These runs can use your personal base credits before drawing from team Add-on Credits, just like running an agent from the Warp app or triggering one via Slack or Linear. -* **Team API keys** - Cloud agent runs are not tied to any individual user. These runs can only draw from your team's pool of Add-on Credits. They cannot use any individual's base credits. When [team GitHub authorization](/agent-platform/cloud-agents/team-access-billing-and-identity/#team-github-authorization) is configured, team key runs can also clone repositories and open pull requests using the Oz by Warp GitHub App. +* **Personal API keys** - Cloud agent runs authenticate as you, just like running an agent from the Warp app or triggering one via Slack or Linear. On Build, Max, and Business plans, runs draw from your plan-included credits, then your Add-on credits — both scoped to your individual user. On Enterprise plans, runs draw from the team-scoped credit pool, per your Enterprise contract terms. +* **Team API keys** - Cloud agent runs are not tied to any individual user. On Build, Max, and Business plans, Warp bills the team owner: the owner's plan-included credits, then the owner's Add-on credits. With auto-reload on, usage can trigger a reload on the owner's pool subject to the team-wide monthly spend cap. On Enterprise plans, team API key runs draw from the team-scoped credit pool. When [team GitHub authorization](/agent-platform/cloud-agents/team-access-billing-and-identity/#team-github-authorization) is configured, team key runs can also clone repositories and open pull requests using the Oz by Warp GitHub App. -Team API keys are useful for fully automated workflows, CI/CD pipelines, and scheduled tasks where no specific user context is needed. For billing details, see [Access, Billing, and Identity Permissions](/agent-platform/cloud-agents/team-access-billing-and-identity/). +Team API keys are useful for fully automated workflows, CI/CD pipelines, and scheduled tasks where no specific user context is needed. For the full credit waterfall and how it interacts with Add-on credits, see [Access, billing, and identity permissions](/agent-platform/cloud-agents/team-access-billing-and-identity/) and [add-on credits](/support-and-community/plans-and-billing/add-on-credits/). ## Authenticating with API keys diff --git a/src/content/docs/reference/cli/index.mdx b/src/content/docs/reference/cli/index.mdx index 86022205..569f82f2 100644 --- a/src/content/docs/reference/cli/index.mdx +++ b/src/content/docs/reference/cli/index.mdx @@ -234,7 +234,7 @@ I'll run a few terminal commands to: * `--name ` (`-n`) — label the run for grouping and traceability. * `--share` — share the session with teammates (see [Collaboration](/reference/cli/#collaboration)). * `--profile ` — use a specific agent profile (see [Using Agent Profiles](/reference/cli/#using-agent-profiles)). -* `--model ` — override the default model (see [Model Choice](/agent-platform/capabilities/model-choice/)). +* `--model ` — override the default model (see [Model Choice](/agent-platform/inference/model-choice/)). * `--skill ` — use a skill as the base prompt (see [Using Skills](/reference/cli/#using-skills)). * `--mcp ` — start one or more MCP servers before execution (UUID, JSON file path, or inline JSON). Can be repeated. * `--environment ` (`-e`) — run in a specific cloud environment. diff --git a/src/content/docs/support-and-community/plans-and-billing/add-on-credits.mdx b/src/content/docs/support-and-community/plans-and-billing/add-on-credits.mdx index 193616e4..4fa79bd4 100644 --- a/src/content/docs/support-and-community/plans-and-billing/add-on-credits.mdx +++ b/src/content/docs/support-and-community/plans-and-billing/add-on-credits.mdx @@ -1,35 +1,33 @@ --- -title: Add-on Credits +title: Add-on credits description: >- - Purchase Add-on Credits to keep using premium AI models after reaching your + Purchase add-on credits to keep using premium AI models after reaching your monthly credit limit. --- -Add-on credits replace Warp's old [pay-as-you-go Overages](/support-and-community/plans-and-billing/overages-legacy/). They let you continue using premium AI models even after you've reached your monthly credit limit — at lower rates and with more control over spending. +Add-on credits let you continue using premium AI models even after you've reached your monthly credit limit — at lower rates and with more control over spending. -You can manage and purchase Add-on credits directly in **Settings** > **Billing and usage**. +You can manage and purchase add-on credits directly in **Settings** > **Billing and usage**. -![Add-on Credits management surface under Settings > Billing and usage.](../../../../assets/support-and-community/reload-credits.png) +![Add-on credits management surface under Settings > Billing and usage.](../../../../assets/support-and-community/reload-credits.png) -### How do Add-on credits work? +### How do add-on credits work? -Add-on credits extend your AI usage beyond the included monthly quota in your plan. Once your plan’s credits are used up, Warp will automatically begin drawing from your available Add-on credits. +Add-on credits extend your AI usage beyond the included monthly quota in your plan. Once your plan’s credits are used up, Warp will automatically begin drawing from your available add-on credits. -If you’ve enabled **Auto reload**, new credits will be added automatically and billed based on your selected configuration of monthly spending limit and selected purchase amount. +If you’ve enabled **auto-reload**, new credits will be added automatically and billed based on your selected configuration of monthly spending limit and selected purchase amount. -Add-on credits are available for Build, Business, and Enterprise plans (with custom pricing for Enterprise). These credits **roll over across billing cycles** and remain valid for **12 months from the purchase date**. +Add-on credits are available for Build, Max, Business, and Enterprise plans (with custom pricing for Enterprise). On self-serve plans (Build, Max, and Business), add-on credits are scoped to each individual user; Enterprise uses a team-pooled model. These credits **roll over across billing cycles** and remain valid for **12 months from the purchase date**. -:::caution -**Legacy plans (Pro, Turbo, Lightspeed) do not support Add-on Credits.** If you're on a legacy plan, you cannot purchase or auto-reload Add-on Credits. To access Add-on Credits, upgrade to the [Build plan](https://app.warp.dev/upgrade). For additional usage on legacy plans, see [Overages (Legacy)](/support-and-community/plans-and-billing/overages-legacy/). -::: +Add-on credits draw from the same pool as [platform credits](/support-and-community/plans-and-billing/platform-credits/) and compute credits, so a single balance covers all three credit types. -### Purchasing Add-on credits +### Purchasing add-on credits You have two options for purchasing more credits: #### 1. Buy on-demand -You can purchase additional Add-on credits at any time directly within the app under **Settings** > **Billing and usage**. Buying more credits upfront provides a larger discount. +You can purchase additional add-on credits at any time directly within the app under **Settings** > **Billing and usage**. Buying more credits upfront provides a larger discount. The table below shows the available credit denominations, their prices, and corresponding discounts: @@ -37,27 +35,23 @@ The table below shows the available credit denominations, their prices, and corr #### 2. Enable auto-reload -Auto reload automatically purchases more credits whenever your balance reaches **100 credits**, ensuring uninterrupted access to premium AI features. +Auto-reload automatically purchases more credits whenever your balance reaches **100 credits**, ensuring uninterrupted access to premium AI features. -By default, **Auto reload is disabled for new subscribers**. When you turn it on, it starts with a **$200 monthly spend limit**, which you can adjust anytime in **Settings** > **Billing and usage**. +By default, **auto-reload is disabled for new subscribers**. When you turn it on, it starts with a **$200 monthly spend limit**, which you can adjust anytime in **Settings** > **Billing and usage**. -Auto reload uses the same denominations and discounts as manual purchases. The denomination you select (e.g., 400, 1,000, 3,000, or 6,500 credits) will repeat each time your balance is depleted, up to your monthly spending limit. Larger denominations offer up to \~40% off per credit. +Auto-reload uses the same denominations and discounts as manual purchases. The denomination you select (e.g., 400, 1,000, 3,000, or 6,500 credits) will repeat each time your balance is depleted, up to your monthly spending limit. Larger denominations offer up to ~40% off per credit. :::note You can opt in and choose your reload amount when subscribing to a paid plan at [app.warp.dev/upgrade](https://app.warp.dev/upgrade), or change your configuration anytime in **Settings** > **Billing and usage**. ::: -:::caution -Add-on credit auto reload will be enabled by default for some legacy plan users when they transition to the Build plan. Please see more in our [Pricing FAQs](/support-and-community/plans-and-billing/pricing-faqs/#what-happens-to-my-current-plan-pro-turbo-lightspeed). -::: - #### **Configuring a monthly spend limit** -Your monthly spend limit sets the maximum amount you can spend on Add-on credits in a single calendar month. This ensures you have full control over your AI usage costs while still allowing flexibility for automatic top-ups when needed, keeping your workflow uninterrupted. +Your monthly spend limit sets the maximum amount you can spend on add-on credits in a single calendar month. This ensures you have full control over your AI usage costs while still allowing flexibility for automatic top-ups when needed, keeping your workflow uninterrupted. * The default limit is $200, but you can increase or decrease it anytime in **Settings** > **Billing and usage**. -* **If a credit purchase would exceed your limit, it won’t process** — you’ll need to either raise your limit or choose a smaller Add-on credit amount. -* Once your limit is reached, no additional Add-on Credit purchases (manual or automatic) will occur until: +* **If a credit purchase would exceed your limit, it won’t process** — you’ll need to either raise your limit or choose a smaller add-on credit amount. +* Once your limit is reached, no additional add-on credit purchases (manual or automatic) will occur until: * The next calendar month begins, or * You update your limit in settings. @@ -72,35 +66,41 @@ The limit resets automatically at the start of each calendar month, so you can m When your monthly credit balance renews: 1. Warp first consumes your included monthly credits (e.g., Build plan credits). -2. After those are used, Warp continues to draw from any available Add-on Credits. -3. If your Add-on Credits run out and Auto reload is enabled, Warp will automatically purchase more up to your monthly limit. +2. After those are used, Warp continues to draw from any available add-on credits. +3. If your add-on credits run out and auto-reload is enabled, Warp will automatically purchase more up to your monthly limit. You can track your remaining credits and spending in the credits transparency footer and in **Settings** > **Billing and usage**. -#### Teams using Add-on Credits +#### Teams using add-on credits -For teams on Build or Business plans, **Add-on Credits are shared across all members.** All team credit settings can be managed in `Settings → Billing and usage` by the admin of the team. +On Build, Max, and Business self-serve plans, add-on credits are scoped to individual users. Each team member's add-on credits draw down only for their own usage. -Team admins can manage: +Team admins manage add-on credit settings for the team in **Settings** > **Billing and usage**: -* Enabling or disabling Auto reload -* Adjusting monthly spend limits -* Choosing Add-on credit increments -* Viewing usage and spending breakdowns +* **Team-wide spend cap** — Sets the maximum amount the team can spend on add-on credits per calendar month, applied across all members. +* **Auto-reload** — When enabled, the admin selects an add-on credit denomination for the team. Warp automatically purchases that denomination for any user whose add-on credit balance drops below 100 credits, subject to the team-wide spend cap. While auto-reload is on, individual users cannot purchase add-on credits manually. +* **Manual purchases** — When auto-reload is off, eligible team members can purchase add-on credits for themselves, as long as the team stays below the team-wide spend cap. -Each user on the team has their own monthly credit limit, **but any usage beyond that personal quota draws from the shared team credits**. These shared credits are tracked and billed collectively at the team level. +For how cloud agent runs that aren't initiated by a specific team member (scheduled runs, team API key runs) are billed, see [How are cloud agent runs on team plans billed when no individual user triggered them?](/support-and-community/plans-and-billing/pricing-faqs/#how-are-cloud-agent-runs-on-team-plans-billed-when-no-individual-user-triggered-them) in the Pricing FAQs. -For example, if your plan includes 1,500 credits per team member: +### Plan changes and cancellations -* If **User A** reaches their 1,500 limit, any further usage will draw from shared Add-on Credits. -* If **User B** has only used 200 credits, their remaining quota is unaffected, but User A will consume the team's shared credits. +Any purchased add-on credits remain in your account and can continue to be used for up to 12 months after purchase, as long as you have an active subscription. -### Plan changes and cancellations +If you move to the Free plan, you'll lose access to any previously purchased add-on credits and won't be able to use them. You also can't buy additional add-on credits until you're subscribed again. + +:::caution +Add-on credits are tied to your team. Leaving the team, being removed by an admin, or having the team deleted revokes your access to any credits tied to that team. Premium models require an active paid plan. +::: + +#### When team membership changes -Any purchased Add-on Credits remain in your account and can continue to be used for up to 12 months after purchase, as long as you have an active subscription. +Add-on credits are tied to the team they were purchased under. The flows below describe what happens in common team-membership scenarios: -If you move to the Free plan, you'll lose access to any previously purchased Add-on Credits and won't be able to use them. You also can't buy additional Add-on Credits until you're subscribed again. +* **A user leaves a team** - You lose access to any add-on credits tied to that team. If you rejoin the same team later, you regain access to any unused, non-expired credits. The admin pays a prorated rate for your seat on rejoin. +* **An admin removes a member** - That member loses access to any add-on credits tied to the team. If they rejoin later, they regain access to any unused, non-expired credits. +* **An admin deletes the team** - Any remaining add-on credits tied to the team are no longer usable. :::note -All unused Add-on Credits remain valid for 12 months from purchase, as long as you have an active subscription. +All unused add-on credits remain valid for 12 months from purchase, as long as you have an active subscription. ::: diff --git a/src/content/docs/support-and-community/plans-and-billing/credits.mdx b/src/content/docs/support-and-community/plans-and-billing/credits.mdx index 17f7a569..8fe0030c 100644 --- a/src/content/docs/support-and-community/plans-and-billing/credits.mdx +++ b/src/content/docs/support-and-community/plans-and-billing/credits.mdx @@ -14,9 +14,9 @@ Warp meters credits across three types of infrastructure — inference, compute, * **AI credits** cover inference: the LLM call itself. Consumed when Warp pays for the model call through Warp-managed providers. * **Compute credits** cover compute: the sandbox an agent runs in. Consumed when an agent run uses Warp-hosted compute. In practice this is cloud agent runs; local agent runs use your own machine and don't consume compute credits. See [Compute credits](/support-and-community/plans-and-billing/credits/#compute-credits). -* **Platform credits** cover Warp's platform layer: run lifecycle, integrations, dashboard, APIs, and observability. Apply to every cloud agent run, plus local agent runs on Business and Enterprise plans that use customer-supplied inference (BYOK or BYOLLM via Amazon Bedrock or Google Vertex). See [platform credits](/support-and-community/plans-and-billing/platform-credits/). +* **Platform credits** cover Warp's platform layer: run lifecycle, integrations, dashboard, APIs, and observability. Apply to every cloud agent run, plus local agent runs on Business and Enterprise plans that use customer-supplied inference (BYOK, a custom inference endpoint, or BYOLLM). See [platform credits](/support-and-community/plans-and-billing/platform-credits/). -All three buckets draw from the same Warp credit pool and [Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/), so you can manage them as a single balance in the Warp app under **Settings** > **Billing and usage**. +All three buckets draw from the same Warp credit pool and [add-on credits](/support-and-community/plans-and-billing/add-on-credits/), so you can manage them as a single balance in the Warp app under **Settings** > **Billing and usage**. Each interaction consumes **at least one credit**, though more complex interactions may use **multiple credits**. Because of factors such as codebase size, model choice, number of tool calls, and the nature of LLMs, credit usage is **non-deterministic** — two similar prompts can still use a different number of credits. @@ -43,7 +43,7 @@ You can view your total credit usage, along with other billing details, in **Set * **Seat-level allocation**: On team plans, credit limits apply per seat — each team member has their own allowance. Individual users (not on a team) also have their own credit allocation. * **Cloud agents and integrations**: Individual users can run cloud agents via the CLI and API, drawing from their Warp credits. Slack and Linear integrations require team membership. -* **Hitting the credit limits**: Once you hit your monthly credit limit, your access will depend on your plan. On the Free plan, AI access stops until your next billing cycle. On paid plans, you can continue using AI with usage-based billing via [Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/). +* **Hitting the credit limits**: Once you hit your monthly credit limit, your access will depend on your plan. On the Free plan, AI access stops until your next billing cycle. On paid plans, you can continue using AI with usage-based billing via [add-on credits](/support-and-community/plans-and-billing/add-on-credits/). #### **Other features that use credits** @@ -68,7 +68,7 @@ Several factors influence how many credits are counted for a single interaction: Generally, smaller, faster models typically consume fewer credits than larger, reasoning-based models. -For example, **Claude Opus 4.6** and **Claude Opus 4.5** tend to consume the most tokens and credits in Warp, followed by **Claude Sonnet 4.6, GPT-5.4, GPT-5.3 Codex, Gemini 3 Pro**, and others in roughly that order. This generally correlates with model pricing as well. +For example, **Claude Opus 4.7** tends to consume the most tokens and credits in Warp, followed by **Claude Sonnet 4.6, GPT-5.5, Gemini 3.1 Pro**, and others in roughly that order. This generally correlates with model pricing as well. :::note **Tip**: If your task doesn't require deep reasoning, planning, or multi-step problem solving, choose a more lightweight model to reduce credit usage. @@ -134,10 +134,8 @@ The following scenarios use compute credits: #### Not eligible for compute credits -The following scenarios don't use compute credits because they don't run on Warp-hosted compute: - -* **Local agent runs** - Using `oz agent run` on your local machine -* **Self-hosted compute** - Using `oz agent run` on GitHub Actions, CI/CD pipelines, or other self-hosted infrastructure +* **Local agent runs** — Using `oz agent run` on your local machine +* **Self-hosted compute** — Using `oz agent run` on GitHub Actions, CI/CD pipelines, or other self-hosted infrastructure ### Platform credits @@ -148,7 +146,7 @@ Platform credits cover Warp's platform infrastructure — run lifecycle, schedul Platform credits are used in the following scenarios: * **Cloud agents on any plan** use platform credits for every cloud agent run, regardless of which agent runs the task or which inference source it uses. -* **Local agents on Business or Enterprise with customer-supplied inference** use platform credits when the local agent run uses [Bring Your Own API Key (BYOK)](/support-and-community/plans-and-billing/bring-your-own-api-key/) or BYOLLM via Amazon Bedrock or Google Vertex. +* **Local agents on Business or Enterprise with customer-supplied inference** use platform credits when the local agent run uses [Bring Your Own API Key (BYOK)](/agent-platform/inference/bring-your-own-api-key/), a [custom inference endpoint](/agent-platform/inference/custom-inference-endpoint/), or [BYOLLM](/enterprise/enterprise-features/bring-your-own-llm/). #### Not eligible for platform credits @@ -160,3 +158,9 @@ The following scenarios do **not** use platform credits: * **Third-party agent CLIs run directly** don't use platform credits when you run `claude`, `codex`, or another agent CLI outside of Oz. For a full breakdown of how platform credits work, see [platform credits](/support-and-community/plans-and-billing/platform-credits/). + +### Cloud agent runs on team plans + +Cloud agent runs that aren't initiated by a specific team member — for example, scheduled runs or runs triggered through a team API key — follow plan-specific billing rules. On self-serve plans (Build, Max, Business), these runs are billed to the team owner: the owner's plan-included credits first, then their add-on credits, with optional auto-reload subject to the team-wide spend cap. On Enterprise plans, these runs draw from the team-scoped credit pool per your contract. + +For the full waterfall, see [How are cloud agent runs on team plans billed when no individual user triggered them?](/support-and-community/plans-and-billing/pricing-faqs/#how-are-cloud-agent-runs-on-team-plans-billed-when-no-individual-user-triggered-them) in the Pricing FAQs. diff --git a/src/content/docs/support-and-community/plans-and-billing/index.mdx b/src/content/docs/support-and-community/plans-and-billing/index.mdx index 692b4fc9..d44581bf 100644 --- a/src/content/docs/support-and-community/plans-and-billing/index.mdx +++ b/src/content/docs/support-and-community/plans-and-billing/index.mdx @@ -5,11 +5,11 @@ description: >- billing settings. --- -Warp offers flexible plans for individual developers, teams, and enterprises, with credits powering all agent features. Choose from plan-included credits, add-on credit purchases, automatic reloads, or bring-your-own API keys. Compare plans, manage billing, and track credit usage from your account settings. +Warp offers flexible plans for individual developers, teams, and enterprises, with credits powering all agent features. Choose from plan-included credits, add-on credit purchases, or automatic reloads. Compare plans, manage billing, and track credit usage from your account settings. + +Looking for **Bring Your Own API Key** or **custom inference endpoints**? They've moved to [Inference & providers](/agent-platform/inference/model-choice/) under Warp Agents. * [**Plans & Pricing**](/support-and-community/plans-and-billing/plans-pricing-refunds/) - Compare plans, pricing tiers, and refund policies * [**Credits**](/support-and-community/plans-and-billing/credits/) - How credits are used and calculated across AI features -* [**Add-on Credits**](/support-and-community/plans-and-billing/add-on-credits/) - Purchase additional credits or enable automatic reloads -* [**Bring Your Own API Key**](/support-and-community/plans-and-billing/bring-your-own-api-key/) - Connect your own model provider API keys -* [**Overages (Legacy)**](/support-and-community/plans-and-billing/overages-legacy/) - Information for users on legacy plans with overages +* [**Add-on credits**](/support-and-community/plans-and-billing/add-on-credits/) - Purchase additional credits or enable automatic reloads * [**Pricing FAQs**](/support-and-community/plans-and-billing/pricing-faqs/) - Answers to common questions about plans and billing diff --git a/src/content/docs/support-and-community/plans-and-billing/overages-legacy.mdx b/src/content/docs/support-and-community/plans-and-billing/overages-legacy.mdx deleted file mode 100644 index 2aacddd7..00000000 --- a/src/content/docs/support-and-community/plans-and-billing/overages-legacy.mdx +++ /dev/null @@ -1,43 +0,0 @@ ---- -title: Overages (Legacy) -description: >- - Pay-as-you-go access to premium AI models after reaching your monthly - credits quota on Warps plans. ---- - -Warp offers usage-based pricing for Subscribers, allowing continued access to premium AI models even after reaching the monthly credits limit included in the plan (billed at $0.04 per additional credit). - -You can manage usage-based pricing directly in Warp under **Settings** > **Billing and usage**. - -
-![Billing and usage tab in settings, where admins can manage premium model usage overages](../../../../assets/support-and-community/overages-settings.png) -
Billing and usage settings.
-
- -### Enabling overages - -**Team admins** can enable or disable "premium model overages" and set a monthly spending limit from the settings dashboard. Individual subscribers can manage their own overage settings directly in the settings dashboard. - -:::note -Usage-based pricing only applies after you’ve reached the credit limit on your plan — you won’t be charged for any overages until that point, even if overages are enabled. -::: - -### How overages work - -Overages are managed **at the team level**, even if your team only has one member (i.e. individual users). Once overages are enabled, any team member who reaches their monthly credit quota can continue to have access to premium models — with **additional usage billed at cost ($0.04 per credit)**. - -Each user on the team has their **own credit limit**, but only **credits made beyond that personal quota** are considered overages. These charges are tracked and billed **collectively** at the team level. - -For example, if your plan includes 10,000 credits per team member: - -* If **User A** reaches their 10,000 limit, any further usage by them counts towards overages. -* If **User B** has only used 2,000 credits, they still have 8,000 included credits left. -* User A's overages **do not** consume User B's remaining quota. - -Overages are **billed monthly**, or when your team accumulates **$20 worth of charges**, whichever comes first. - -### Plan upgrades and cancellations - -If you upgrade from lower to a higher plan, your monthly credit limit will update immediately to match the higher plan. (For exact limits, see our [pricing page](https://www.warp.dev/pricing).) However, **any overages incurred while on the lower plan will still be billed** — upgrading does not retroactively remove or reduce existing overage charges. - -If you cancel your subscription, you’ll retain access to premium features until the end of your current billing period. Any usage-based overages accrued during that period will be charged at the time your plan ends.\\ diff --git a/src/content/docs/support-and-community/plans-and-billing/plans-pricing-refunds.mdx b/src/content/docs/support-and-community/plans-and-billing/plans-pricing-refunds.mdx index 10f9b086..f7df9460 100644 --- a/src/content/docs/support-and-community/plans-and-billing/plans-pricing-refunds.mdx +++ b/src/content/docs/support-and-community/plans-and-billing/plans-pricing-refunds.mdx @@ -19,10 +19,10 @@ Visit [warp.dev/pricing](https://www.warp.dev/pricing) to see the latest plans a **Explore the following sections for more details:** * [Credits](/support-and-community/plans-and-billing/credits/) — learn how credits are used and calculated across AI features. -* [Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/) — purchase additional credits or enable automatic reloads at discounted rates. +* [Add-on credits](/support-and-community/plans-and-billing/add-on-credits/) — purchase additional credits or enable automatic reloads at discounted rates. * [Platform credits](/support-and-community/plans-and-billing/platform-credits/) — learn how platform credits cover Warp's platform infrastructure for cloud agent runs and local runs with customer-supplied inference. -* [Bring Your Own API Key](/support-and-community/plans-and-billing/bring-your-own-api-key/) — connect your own model provider API keys for custom usage and billing. -* [Overages (Legacy)](/support-and-community/plans-and-billing/overages-legacy/) — information for users on legacy plans with overages enabled. +* [Bring Your Own API Key](/agent-platform/inference/bring-your-own-api-key/) — connect your own model provider API keys for custom usage and billing. +* [Custom inference endpoint](/agent-platform/inference/custom-inference-endpoint/) — connect an OpenAI-compatible endpoint such as OpenRouter, LiteLLM, z.ai, or an internal gateway. * [Pricing FAQs](/support-and-community/plans-and-billing/pricing-faqs/) — answers to common questions about plans, billing, and usage. Don’t have Warp yet? [Download Warp](https://www.warp.dev/download) and get started for free today. ### Warp’s refund policies @@ -47,10 +47,9 @@ If you signed up for an annual Warp subscription by mistake, we can issue a full After 15 days, we will refund you for the remaining full months on your subscription, excluding the first month. -#### Add-on Credits | Overages refund policy +#### Add-on credits refund policy -* If you purchased [Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/) by mistake, you can receive a refund **as long as none of the credits have been used**. Warp cannot refund Add-on Credits if there has been any usage. Add-on Credits remain available for up to **12 months** from the date of purchase, as long as you have an active subscription — if you move to the Free plan, you'll lose access to any remaining Add-on Credits. -* All [Overages (Legacy)](/support-and-community/plans-and-billing/overages-legacy/) credits are **non-refundable**. Because Overages are charges for credits that were already consumed, we cannot refund resources that have already been used. +* If you purchased [add-on credits](/support-and-community/plans-and-billing/add-on-credits/) by mistake, you can receive a refund **as long as none of the credits have been used**. Warp cannot refund add-on credits if there has been any usage. Add-on credits remain available for up to **12 months** from the date of purchase, as long as you have an active subscription — if you move to the Free plan, you'll lose access to any remaining add-on credits. :::caution Warp does not offer a formal guaranteed uptime Service Level Agreement (SLA). Live incidents can be monitored on our [**Status Page**](https://status.warp.dev/), and open issues are tracked on our [**GitHub Issues**](https://github.com/warpdotdev/Warp/issues). diff --git a/src/content/docs/support-and-community/plans-and-billing/platform-credits.mdx b/src/content/docs/support-and-community/plans-and-billing/platform-credits.mdx index 3509ceb4..5a5b059b 100644 --- a/src/content/docs/support-and-community/plans-and-billing/platform-credits.mdx +++ b/src/content/docs/support-and-community/plans-and-billing/platform-credits.mdx @@ -5,14 +5,14 @@ description: >- and on local runs with customer-supplied inference. Learn when they apply. --- -Platform credits cover Warp's platform infrastructure for coordinating, observing, and integrating agent runs. They apply to every cloud agent run, plus local agent runs on Business and Enterprise plans that use customer-supplied inference such as BYOK, Amazon Bedrock, or Google Vertex. +Platform credits cover Warp's platform infrastructure for coordinating, observing, and integrating agent runs. They apply to every cloud agent run, plus local agent runs on Business and Enterprise plans that use customer-supplied inference such as BYOK, a custom inference endpoint, or BYOLLM. Warp meters credits across three types of infrastructure: **inference** (the model call), **compute** (the sandbox an agent runs in), and **platform** (everything that runs around the agent — run lifecycle, integrations, dashboard, APIs, and observability). Each type maps to one credit bucket: [AI credits](/support-and-community/plans-and-billing/credits/), [Compute credits](/support-and-community/plans-and-billing/credits/#compute-credits), and platform credits. Credit types and where an agent runs (local or cloud) are independent. -Customer-supplied inference covers [Bring Your Own API Key (BYOK)](/support-and-community/plans-and-billing/bring-your-own-api-key/) and BYOLLM via Amazon Bedrock or Google Vertex. +Customer-supplied inference covers [Bring Your Own API Key (BYOK)](/agent-platform/inference/bring-your-own-api-key/), [custom inference endpoints](/agent-platform/inference/custom-inference-endpoint/), and [BYOLLM](/enterprise/enterprise-features/bring-your-own-llm/). :::caution -BYOK and customer-supplied inference (BYOLLM via Amazon Bedrock or Google Vertex, plus custom endpoints) are available to individual users and organizations with 10 or fewer employees or users on any plan. Organizations with more than 10 employees or users must be on a Warp Business or Enterprise plan to use BYOK or customer-supplied inference. See Warp's [Terms of Service](https://www.warp.dev/terms-of-service) for details. +BYOK and customer-supplied inference (custom inference endpoints, plus BYOLLM) are available to individual users and organizations with 10 or fewer employees on any plan. Organizations with more than 10 employees need a Warp Business or Enterprise plan to use BYOK or customer-supplied inference. See Warp's [Terms of Service](https://www.warp.dev/terms-of-service) for details. ::: ## The three credit buckets @@ -38,7 +38,7 @@ Whether platform credits apply depends on where the agent runs and who's paying ### Uses platform credits * **Cloud agents on any plan** use platform credits for every cloud agent run, regardless of which agent runs the task (Warp Agent, Claude Code, or Codex), inference source (Warp-managed, BYOK, or BYOLLM), or compute source (Warp-hosted or self-hosted workers). Warp's platform infrastructure coordinates every cloud agent run. -* **Local agents on Business or Enterprise with customer-supplied inference** use platform credits when the local agent run uses [BYOK](/support-and-community/plans-and-billing/bring-your-own-api-key/) or BYOLLM via Amazon Bedrock or Google Vertex. Warp isn't paying for the model call, but Warp's platform infrastructure is still running the local agent. BYOK and customer-supplied inference are subject to plan-size eligibility — see the callout above. +* **Local agents on Business or Enterprise with customer-supplied inference** use platform credits when the local agent run uses [BYOK](/agent-platform/inference/bring-your-own-api-key/), a [custom inference endpoint](/agent-platform/inference/custom-inference-endpoint/), or BYOLLM. Warp isn't paying for the model call, but Warp's platform infrastructure is still running the local agent. BYOK and customer-supplied inference are subject to plan-size eligibility — see the callout above. ### Doesn't use platform credits @@ -53,11 +53,12 @@ Platform credits appear in the same billing views as your other credit usage. * **Per-user credit totals** - In the Warp app, **Settings** > **Billing and usage** includes platform credits alongside AI credits and compute credits. * **Admin usage breakdown** - For team admins, the Admin Panel billing view shows a per-bucket breakdown for each member and for the team as a whole. Platform credits appear as their own segment in the stacked usage bar, distinct from the AI credits and compute credits segments. -* **Add-on Credits and limits** - Platform credits draw from the same pools as your other usage — your monthly Warp credits first, then [Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/) once those are exhausted. +* **Add-on credits and limits** - Platform credits draw from the same pools as your other usage — your monthly Warp credits first, then [add-on credits](/support-and-community/plans-and-billing/add-on-credits/) once those are exhausted. ## Related pages * [Credits](/support-and-community/plans-and-billing/credits/) - How AI credits are measured and calculated. -* [Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/) - Purchase additional credits or enable auto reload. -* [Bring Your Own API Key](/support-and-community/plans-and-billing/bring-your-own-api-key/) - Connect your own model provider keys. +* [Add-on credits](/support-and-community/plans-and-billing/add-on-credits/) - Purchase additional credits or enable auto-reload. +* [Bring Your Own API Key](/agent-platform/inference/bring-your-own-api-key/) - Connect your own model provider keys. +* [Custom inference endpoint](/agent-platform/inference/custom-inference-endpoint/) - Route Warp through any OpenAI-compatible endpoint. * [Plans, pricing, and refunds](/support-and-community/plans-and-billing/plans-pricing-refunds/) - Compare plans and refund policies. diff --git a/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx b/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx index 434d901e..c65ceab5 100644 --- a/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx +++ b/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx @@ -22,41 +22,31 @@ After entering your payment details, you’ll receive an invoice and confirmatio ### How can I get the most out of my Warp plan? -:::caution -Warp's legacy paid plans included Pro, Turbo, and Lightspeed. - -After **Oct 30, 2025**, we have rolled out the new Build plan to replace them. Existing subscribers will start to roll over onto the Build plan starting **Dec 1st, 2025**. For questions related to the new pricing changes, please refer to [Warp's pricing change FAQs](/support-and-community/plans-and-billing/pricing-faqs/#warps-pricing-change-faqs-oct-30-2025). - -To see more details on the latest plan, please visit [**warp.dev/pricing**](https://www.warp.dev/pricing). -::: - -Warp's plans are designed for developers who rely on AI to code, debug, and move faster with their team. - -* **Build**, one usage-based plan with a set of credits, ability to Bring Your Own API Key (BYOK), and access to [Add-on credits](/support-and-community/plans-and-billing/add-on-credits/) with volume-based discounts. See more on [Bring Your Own API Key](/support-and-community/plans-and-billing/bring-your-own-api-key/). -* **Business** includes everything in Build, with advanced features like automatically enforced team-wide Zero Data Retention, SAML-based SSO, and support for teams up to 50 seats. +Warp's plans are designed for developers who rely on AI to code, debug, and move faster with their team. Pick the plan that matches the scale of your usage and the controls your team needs: -Legacy plans (**No longer available for new subscribers**): +* **Build** — Usage-based plan for individuals or small teams with monthly credits, the ability to [Bring Your Own API Key (BYOK)](/agent-platform/inference/bring-your-own-api-key/) or point Warp at a [custom inference endpoint](/agent-platform/inference/custom-inference-endpoint/), and access to [add-on credits](/support-and-community/plans-and-billing/add-on-credits/) with volume-based discounts. +* **Max** — Plan for individuals or small teams with heavier AI usage. Includes a larger monthly credit allowance than Build, plus a better effective rate for credits than buying add-on credits on Build. +* **Business** — Multi-seat plan for teams. Includes everything in Build, plus admin-configurable data controls, SAML-based SSO, and centralized billing. Available up to the seat limit listed at [warp.dev/pricing](https://www.warp.dev/pricing). +* **Enterprise** — Custom plan for organizations that need higher seat counts, [Bring Your Own LLM (BYOLLM)](/enterprise/enterprise-features/bring-your-own-llm/) managed inference, granular admin controls, advanced security and compliance, and dedicated support. -* **Pro** included higher credit limits than the Free plan, support for larger codebases with [Codebase Context](/agent-platform/capabilities/codebase-context/), and access to premium models with optional pay-as-you-go [Overages (Legacy)](/support-and-community/plans-and-billing/overages-legacy/). -* **Turbo** included even higher credit limits, larger Codebase Context indexing, and the option to pay for additional usage beyond included credits via [Overages (Legacy)](/support-and-community/plans-and-billing/overages-legacy/). Add-on Credits were not available on this plan. -* **Lightspeed** was Warp's most powerful legacy plan, offering the highest credit limits, expanded codebase indexing, access to top-tier models, and pay-as-you-go [Overages (Legacy)](/support-and-community/plans-and-billing/overages-legacy/) so you could keep working without interruption. - -For the most up-to-date feature and usage details, visit [**warp.dev/pricing**](https://www.warp.dev/pricing). +For the most up-to-date feature and usage details — including current per-plan seat limits and monthly credit allowances — visit [warp.dev/pricing](https://www.warp.dev/pricing). ### How can I subscribe to a Warp Enterprise plan? Warp offers two options for larger teams and organizations: -* **Business Plan**: Supports up to 50 seats and is available for immediate upgrade. It includes automatically enforced team-wide Zero Data Retention by default and admin-controlled SAML-based SSO. -* **Enterprise Plan**: Offers custom pricing, credit limits, and terms. Along with support for larger engineering orgs or teams with advanced security, compliance, or support needs. +* **Business plan**: Self-serve multi-seat plan available for immediate upgrade. Includes admin-configurable data controls and admin-controlled SAML-based SSO. See [warp.dev/pricing](https://www.warp.dev/pricing) for the current seat limit. +* **Enterprise plan**: Custom pricing, credit allowances, and terms — built for larger engineering organizations or teams with advanced security, compliance, or support needs. Enterprise also includes [Bring Your Own LLM (BYOLLM)](/enterprise/enterprise-features/bring-your-own-llm/) managed inference, with routing, orchestration, governance, and observability provided by Warp. :::tip If you’d like to explore Enterprise, [contact our sales team](https://www.warp.dev/contact-sales) and someone from Warp will follow up. ::: +For Warp-managed model traffic (requests Warp routes to OpenAI, Anthropic, or Google on your behalf), all plans are covered by Warp's Zero Data Retention (ZDR) agreements with the underlying model providers. Traffic you route through your own API key or a custom inference endpoint is governed by that provider's data-retention policies, not Warp's agreements. Admin-configurable data controls — including team-wide retention policies and training opt-outs — are available on Business and Enterprise. + ### What counts as a team member and how does billing work for members? -In Warp, a _team member_ is any seat with access to your Team — including the shared Warp Drive, Notebooks, Workflows, and other team resources. All plans allow you to invite unlimited users, but to unlock higher limits and advanced features, you’ll need to upgrade your team to a plan. Upgrading applies to your entire team, including your own account and all active members. +In Warp, a _team member_ is any seat with access to your Team — including the shared Warp Drive, Notebooks, Workflows, and other team resources. All plans allow you to invite unlimited Warp Drive collaborators, but paid-plan features and credit allocation are governed by your plan's seat limit (see [Are there new seat limits per plan?](#are-there-new-seat-limits-per-plan) below). Upgrading applies to your entire team, including your own account and all active members. On the Free plan, you can share a limited number of Notebooks and Workflows with other Free users. If your team exceeds that limit, you’ll be prompted to [upgrade to a plan](https://app.warp.dev/upgrade).\ \ @@ -98,10 +88,6 @@ You can use your Warp account on multiple personal computers. Warp is designed t ### What happens when I downgrade during a billing cycle? -:::caution -Note this only applies when switching between legacy plans (Pro, Turbo, Lightspeed, or the Old Business) or switching the new plans (Build, New Business). When switching between legacy to new plans, the change is immediate, prorated, and the credits are reset. See more in [What happens when I change from my legacy plan to the new Build or Business plans?](/support-and-community/plans-and-billing/pricing-faqs/#what-happens-when-i-change-from-my-legacy-plan-to-the-new-build-or-business-plans). -::: - The subscription will downgrade to the lower plan limits at the end of the billing cycle. If you’re switching between paid plans, any AI usage you've already accumulated will carry over.\ \ You can downgrade at any point throughout your subscription through the billing portal by going to **Settings** > **Billing and usage** > **Manage billing**. @@ -138,18 +124,90 @@ Tokens are chunks of text, such as words, parts of code, or characters, that lar Warp now abstracts away token usage, so you don't need to manage or track it directly. You only need to monitor your **credit usage**, which is what’s measured against your plan limits. ::: -If you're curious, you can read the [OpenAI article on tokens](https://help.openai.com/en/articles/4936856-understanding-tokens), or refer to the pricing page for plan-level credit allocations. If you reach your monthly credit limits on a paid plan, premium models will be temporarily disabled until your quota resets at the start of your next billing cycle. - -If you’d like to continue using premium models beyond your included quota, purchase [Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/) in **Settings** > **Billing and usage** (users still on legacy Pro, Turbo, or Lightspeed plans continue to use [Overages (Legacy)](/support-and-community/plans-and-billing/overages-legacy/) until their first renewal after December 1, 2025). +If you're curious, you can read the [OpenAI article on tokens](https://help.openai.com/en/articles/4936856-understanding-tokens), or refer to the pricing page for plan-level credit allocations. If you reach your monthly credit limits on the Free plan, premium models pause until your quota resets at the start of your next billing cycle. On paid plans, you can continue using premium models via [add-on credits](/support-and-community/plans-and-billing/add-on-credits/) and auto-reload — see [What if I need more AI usage than my plan includes?](#what-if-i-need-more-ai-usage-than-my-plan-includes) for the full list of options. ### How often do my credits reset? -Allotted credits refill every 30 days from your signup date. When you upgrade to a [paid plan](https://www.warp.dev/pricing), you will be given more credits immediately. You can follow along with your refill period by referencing **Settings** > **Billing and usage**. Alternatively, purchase [Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/), or enable auto reload with a monthly spend limit, to continue using premium models beyond your included quota. Users still on legacy Pro, Turbo, or Lightspeed plans continue to use [Overages (Legacy)](/support-and-community/plans-and-billing/overages-legacy/) until their first renewal after December 1, 2025. +Allotted credits refill every 30 days from your signup date. When you upgrade to a [paid plan](https://www.warp.dev/pricing), you will be given more credits immediately. You can follow along with your refill period by referencing **Settings** > **Billing and usage**. Alternatively, purchase [add-on credits](/support-and-community/plans-and-billing/add-on-credits/), or enable auto-reload with a monthly spend limit, to continue using premium models beyond your included quota. :::note Unused credits do not rollover to the next cycle and can't be transferred to other accounts. ::: +### How do credits work for multi-seat teams? + +On the new multi-seat paid plans, credits attribute differently than they did on Warp's older pooled-credit teams: + +* **Plan-included monthly credits** — Each seat receives its own monthly credit allowance that resets every 30 days based on the team's renewal date. See [warp.dev/pricing](https://www.warp.dev/pricing) for the current per-seat allowance on your plan. +* **Add-on credits** — As of May 21, 2026, [add-on credits](/support-and-community/plans-and-billing/add-on-credits/) are scoped to the individual user who purchased or was allocated them, not pooled across the team. A single heavy user can no longer drain the whole team's purchased credits. +* **Grandfathered pooled credits** — Teams that purchased add-on credits before May 21, 2026 keep their existing pooled balance until it's exhausted. Pooled credits are spent down first across the team; all new add-on credit purchases after May 21, 2026 are user-scoped. +* **Team-wide spend cap** — Admins set a single team-wide monthly spend cap that governs auto-reload across the team. See [How does auto-reload work for teams?](#how-does-auto-reload-work-for-teams) below. + +Enterprise plans support team-scoped credit pools and per-user spend limits separately — see [enterprise billing](/enterprise/support-and-resources/billing/). + +### How do platform credits factor in? + +Warp meters credits across three buckets: **AI credits** (the model call), **compute credits** (the sandbox a cloud agent runs in), and **platform credits** (run lifecycle, integrations, dashboard, APIs, and observability). All three draw from the same pool — your monthly Warp credits first, then [add-on credits](/support-and-community/plans-and-billing/add-on-credits/) once those are exhausted. + +Platform credits apply in two situations: + +* **Every cloud agent run, on every plan.** Warp's platform infrastructure coordinates every cloud run regardless of which agent or inference source it uses. On self-serve paid plans (Build, Max, Business), platform-credits billing is in a preview period until July 1, 2026 — see [When do platform credits start being charged on self-serve plans?](#when-do-platform-credits-start-being-charged-on-self-serve-plans) for details. +* **Local agent runs on Business and Enterprise that use customer-supplied inference** — BYOK, a custom inference endpoint, or BYOLLM. Warp isn't paying for the model call, but Warp's platform infrastructure is still running the agent. Billing for these runs is also in preview until July 1, 2026 on self-serve paid plans. + +Local agent runs on Free, Build, or Max — and local runs on Business or Enterprise that use Warp-managed inference — do not consume platform credits. See [platform credits](/support-and-community/plans-and-billing/platform-credits/) for the full breakdown. + +### What if I need more AI usage than my plan includes? + +If you regularly run through your plan's monthly credit allowance, you have a few options: + +* **Upgrade to Max** — Designed for developers with heavier AI usage. Max includes a higher monthly credit allowance than Build, plus a better effective rate for credits than buying [add-on credits](/support-and-community/plans-and-billing/add-on-credits/) on Build. See [warp.dev/pricing](https://www.warp.dev/pricing) for current allowances. +* **Purchase add-on credits** — Top up your account on demand. Larger denominations have a better effective rate. Add-on credits roll over month-to-month and remain valid for 12 months as long as you have an active subscription — if you move to the Free plan, you'll lose access to any remaining add-on credits. See [add-on credits](/support-and-community/plans-and-billing/add-on-credits/) for current denominations. +* **Enable auto-reload** — Pick a denomination and a monthly spend cap, and Warp will automatically purchase add-on credits when your balance drops below 100 credits, up to your cap. +* **Bring Your Own API Key (BYOK)** — Point Warp at your own OpenAI, Anthropic, or Google API key. Requests routed through BYOK don't consume Warp credits — you're billed directly by the model provider. See [Bring Your Own API Key](/agent-platform/inference/bring-your-own-api-key/). On Business and Enterprise, platform credits may apply for local agent runs (billing starts July 1, 2026 on self-serve plans — see [When do platform credits start being charged on self-serve plans?](#when-do-platform-credits-start-being-charged-on-self-serve-plans)). +* **Use a custom inference endpoint** — Route requests through any OpenAI-compatible endpoint (OpenRouter, LiteLLM, z.ai, an internal gateway, etc.) without spending Warp credits. See [Custom inference endpoint](/agent-platform/inference/custom-inference-endpoint/). On Business and Enterprise, platform credits may apply for local agent runs (billing starts July 1, 2026 on self-serve plans — see [When do platform credits start being charged on self-serve plans?](#when-do-platform-credits-start-being-charged-on-self-serve-plans)). + +*BYOK and custom inference endpoint availability is subject to organization size — see [Can I bring my own API key?](#can-i-bring-my-own-api-key) for details.* + +For organization-scale needs (cloud-provider managed inference, granular admin controls, or higher seat counts), Enterprise plans include [Bring Your Own LLM (BYOLLM)](/enterprise/enterprise-features/bring-your-own-llm/). + +### How does auto-reload work for teams? + +Auto-reload prevents team members from getting blocked by credit exhaustion. It works the same way for individual and multi-seat paid plans, with one extra knob for teams. + +When auto-reload is **on**: + +* The admin chooses an add-on credit **denomination**. Larger denominations have a better effective per-credit rate. +* Whenever any individual user's balance (their plan credits plus their user-scoped add-on credits balance) drops below **100 credits**, Warp automatically purchases another bundle of the configured denomination on the team's behalf. +* All auto-reload purchases count against a single **team-wide monthly spend cap** that the admin sets. Once the team hits the cap in a given month, auto-reload pauses until the next billing cycle or until the admin raises the cap. +* While auto-reload is on, **individual team members cannot purchase add-on credits manually** — the team-wide auto-reload configuration governs all purchases. + +Teams with a pre-May 21, 2026 grandfathered pooled add-on credit balance: that pooled balance drains first across the team before user-scoped add-on credits and is not counted toward any individual user's 100-credit auto-reload threshold. + +When auto-reload is **off**, eligible team members can purchase add-on credits for themselves, as long as the team stays below the team-wide monthly spend cap. Users keep working as long as they have plan credits, previously purchased add-on credits, or have routed Warp at their own API key or [custom inference endpoint](/agent-platform/inference/custom-inference-endpoint/). Once those run out, premium-model usage is blocked until credits are topped up or the next billing cycle begins. + +Auto-reload can be enabled, paused, or reconfigured at any time in **Settings** > **Billing and usage**. + +### How are cloud agent runs on team plans billed when no individual user triggered them? + +Some cloud agent runs aren't initiated by a specific team member — for example, scheduled runs or runs triggered through a team API key. On self-serve plans (Build, Max, Business), these runs are billed to the **team owner**. + +:::caution +Team owners: scheduled runs and runs triggered through a team API key draw from your personal credit pool. If auto-reload is enabled on your account, automated jobs can consume your add-on credits and count toward your spend cap. Review your auto-reload settings and team-wide spend cap in **Settings** > **Billing and usage** before relying on scheduled or API-key-triggered cloud agents. +::: + +The waterfall on the owner's account is: + +1. First, the owner's plan-included monthly credits are consumed. +2. Once those are exhausted, the owner's add-on credits are consumed. + +When auto-reload is **off**, the request is blocked once both buckets are depleted. When auto-reload is **on**, cloud agent usage can trigger auto-reload on the owner's pool subject to the team-wide spend cap; further cloud agent runs then draw from that reloaded balance until the cap is reached. + +"Blocked" means the run fails immediately with an insufficient-credits error rather than queuing or retrying. For unattended runs (scheduled jobs, team-API-key triggers), this manifests as a failed run in the Oz dashboard with an [insufficient credits](/reference/api-and-sdk/troubleshooting/errors/insufficient-credits/) error code; the run won't be retried automatically. Owners should monitor the dashboard and configure spend caps with headroom for critical scheduled workloads. + +:::note +Enterprise plans support team-scoped credit pools, so this traffic draws from the team pool rather than an individual admin. See [enterprise billing](/enterprise/support-and-resources/billing/) for overage and contract terms. +::: + ### Can I use a Free plan if I'm a developer at a large company or organization? Yes. Developers at any company size are welcome to use Warp’s Free plan. @@ -171,13 +229,65 @@ Warp Drive data is securely stored on Google Cloud Platform servers located in t For more details, please [visit the Security Overview](https://www.warp.dev/legal/security) or contact [security@warp.dev](mailto:security@warp.dev). -### What happened to the Lite model? +### Does Warp have a SOC 2 Type 2 attestation? + +Yes. Warp has obtained a SOC 2 Type 2 attestation from an accredited third party. See the [Trust Center](/enterprise/security-and-compliance/trust-center/) to request the report. + +### Does Warp have Zero Data Retention policies with LLM providers? -Over time, the Lite model—originally designed as a fallback when premium models ran out—began to deliver inconsistent results, especially for users running complex, multi-step prompts. +Warp integrates with multiple LLM providers — including Anthropic, OpenAI, Google, and Fireworks AI — to power its AI features. Warp has executed Zero Data Retention (ZDR) agreements with these providers. Across all plans, these agreements mean: -For credit-efficient usage, we encourage you to try our new **Auto (cost-efficiency) model**, which automatically selects the optimal model based on task complexity to help extend your credits. To continue AI usage please either add [Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/) or consider [using your own API key](/support-and-community/plans-and-billing/bring-your-own-api-key/). +* LLM providers commit not to train their models on any customer-generated data processed through Warp's services. +* LLM providers commit to delete inputs and outputs after generating the relevant output, within a fixed time period. -If you have any questions or feedback, please connect with us in our [community Slack](/support-and-community/#sending-warp-feedback). +Warp enforces these commitments through both technical measures and contractual safeguards with the LLM providers. + +### How can I enable Zero Data Retention in Warp? + +Zero Data Retention (ZDR) can be enabled in two ways: + +* **Individual level** — Any user can enable full ZDR for their own account by disabling **Help Improve Warp** in **Settings** > **Privacy**. +* **Organization-wide** — On Business and Enterprise plans, admins can enforce ZDR for all members from the [Admin Panel](/enterprise/team-management/admin-panel/), so team-wide compliance doesn't rely on individual settings. + +To discuss organization-wide ZDR for your team, [contact our sales team](https://www.warp.dev/contact-sales). + +Regardless of plan, Warp never allows OpenAI, Anthropic, Google, or other model providers to store, retain, or train their models on your data — see [Does Warp have Zero Data Retention policies with LLM providers?](#does-warp-have-zero-data-retention-policies-with-llm-providers) for details. + +### Can I bring my own API key? + +Yes. On Free, Build, Max, Business, and Enterprise plans, you can configure your own OpenAI, Anthropic, or Google API key in **Settings** > **AI** > **Manage models**. Requests routed through your own key don't consume Warp credits — you're billed directly by the model provider. + +See [Bring Your Own API Key](/agent-platform/inference/bring-your-own-api-key/) for setup steps, the list of supported providers and models, and the differences between BYOK, custom inference endpoints, and BYOLLM. + +BYOK and custom inference endpoint support are available for individual users and organizations with 10 or fewer employees, subject to Warp's Terms of Service. Companies or organizations with more than 10 employees need a Warp Business or Enterprise plan to use these features. + +On Business and Enterprise, local agent runs that use BYOK still consume platform credits for Warp's platform infrastructure. See [platform credits](/support-and-community/plans-and-billing/platform-credits/). + +### Does Warp support custom inference endpoints? + +Yes. In addition to BYOK, Warp can route requests to any OpenAI-compatible inference endpoint — including OpenRouter, LiteLLM, z.ai, and internal gateways your team already runs. Custom inference endpoint requests also don't consume Warp credits. + +Custom inference endpoints are available on Free, Build, Max, Business, and Enterprise. See [Custom inference endpoint](/agent-platform/inference/custom-inference-endpoint/) for configuration steps, billing behavior, and how custom inference endpoints differ from BYOK and from Enterprise's [Bring Your Own LLM (BYOLLM)](/enterprise/enterprise-features/bring-your-own-llm/) managed inference. + +BYOK and custom inference endpoint support are available for individual users and organizations with 10 or fewer employees, subject to Warp's Terms of Service. Companies or organizations with more than 10 employees need a Warp Business or Enterprise plan to use these features. + +On Business and Enterprise, local agent runs that use a custom inference endpoint still consume platform credits for Warp's platform infrastructure. See [platform credits](/support-and-community/plans-and-billing/platform-credits/). + +### Does Warp support other model routers or "Bring Your Own LLM"? + +On the Enterprise plan, Warp's [Bring Your Own LLM (BYOLLM)](/enterprise/enterprise-features/bring-your-own-llm/) lets you route inference through major cloud-provider Model-as-a-Service offerings. BYOLLM currently supports AWS Bedrock, with Azure Foundry and Google Vertex coming soon. Warp still manages model support, routing, and orchestration, but inference runs in your cloud environment so you can maintain data locality, security controls, and existing cloud spend commitments. + +Custom or in-house model routers outside this list aren't supported by default today. If you have specific requirements, [contact our sales team](https://www.warp.dev/contact-sales). + +For lighter-weight routing through any OpenAI-compatible endpoint (OpenRouter, LiteLLM, z.ai, internal gateways), see [Does Warp support custom inference endpoints?](#does-warp-support-custom-inference-endpoints) above. + +### What features are available during multi-harness orchestration beta? + +Multi-harness orchestration is currently in beta and available to all users. You can use the [Warp Agent](/agent-platform/cloud-agents/harnesses/warp-agent/) alongside [Claude Code](/agent-platform/cloud-agents/harnesses/claude-code/) and [Codex](/agent-platform/cloud-agents/harnesses/codex/) in Oz cloud environments, and mix and match harnesses across workflows. + +[Agent Memory](/agent-platform/agent-memory/) is currently in Research Preview. It lets preferences, project knowledge, and learnings from past sessions carry across harnesses and future agent runs. [Contact our sales team](https://www.warp.dev/contact-sales) to request access. + +As these features move out of beta or Research Preview, availability, limits, and pricing may change. ### What payment options are available for Warp's self-service plans? @@ -231,122 +341,79 @@ The team at Warp is standing by and ready to help. For subscribers technical iss --- -### Warp's pricing change FAQs (Oct 30, 2025) +### May 2026 pricing changes -For more details, see this blog post on [Warp's plan changes](https://www.warp.dev/blog/warp-new-pricing-flexibility-byok). +The May 21, 2026 update introduces new seat limits, changes how add-on credits are attributed, opens BYOK to every plan, adds custom inference endpoints, and starts metering platform credits for cloud agent runs. The questions below cover what's changing and what to do if any of it affects you. -#### How do I change from my current plan to the new Build or Business plan? +#### Are there new seat limits per plan? -You can switch to the new Warp Build or Business plan anytime from **Settings** > **Billing and usage** > **Manage billing** > **Update subscription** in the Warp app or at [app.warp.dev/upgrade](https://app.warp.dev/upgrade). Select Change plan, then choose the plan that fits your needs. +Yes. As of May 21, 2026, each plan has an explicit seat limit. See [warp.dev/pricing](https://www.warp.dev/pricing) for the current per-plan caps. -If you take no action, your Pro, Turbo, Lightspeed, or legacy Business plan will automatically move to the new structure on your first renewal after **December 1, 2025**. You’ll receive an email before your renewal with details to make the transition easier. +The seat limit governs paid-plan features and credit allocation. It's separate from the unlimited Warp Drive collaborators every plan supports. You can keep inviting unlimited users to share Notebooks, Workflows, and other Warp Drive resources without hitting the seat cap. The cap only applies when a user takes a paid seat on your team. -#### What happens when I change from my legacy plan to the new Build or Business plans? +#### What if my team is already above the new seat limit? -If you move from Warp’s legacy Pro, Turbo, Lightspeed, or old Business plans to the new Build or Business plans: - -* You’ll receive a prorated credit balance on Stripe for your current plan, based on how far you are into your billing cycle. This balance can be applied toward monthly Build fees or any Add-on Credits you purchase. - * You can view your credit balance by going to **Settings** > **Billing and usage** > **Manage Account**. You can also view your credit balance on the Stripe invoice that was sent when your plan changed to Build or Business. -* Your credit balance will reset to **0/1,500** when you switch to the Build or Business plan. - -If you switched immediately after the rollout, before a subsequent update was applied, we’ll retroactively reset your credit balance to 0/1,500. - -* You should see this reflected in **Settings** > **Billing and usage**. If you experience any issues, please contact us at **build-priority@warp.dev**. - -:::note -We recommend you use all the credits on your legacy plan before you switch over to the new plans. This way you can make best use of them before they are reset to the new plan limits. -::: - -:::caution -Add-on credit auto reload will be enabled by default for some legacy plan users when they transition to the Build plan. Please see more in our [Pricing FAQs](/support-and-community/plans-and-billing/pricing-faqs/#what-happens-to-my-current-plan-pro-turbo-lightspeed). -::: - -#### What should I keep in mind about this change? - -* **BYOK and Add-on credits**: These are only available on the new Build and Business plans. Switching early gives you immediate access. -* **Pricing differences**: Depending on your usage, your monthly cost may increase or decrease. You’ll now pay based on what you actually use. -* **Renewal timing**: You’ll stay on your current plan until your renewal date after December 1. No interruptions to service will occur. -* **Transparency**: You can view your credit balance, monthly spend limit, and Add-on settings anytime in **Settings** > **Billing and usage**. - -For full details, see [warp.dev/pricing](https://www.warp.dev/pricing) or reach out to billing@warp.dev if you have questions about your transition. - -#### For existing paid users: when will the new pricing take effect for my account? - -For **new customers**, the new pricing and packaging take effect immediately on Oct 30, 2025. - -For **existing monthly subscribers**, changes will apply on your first renewal after **December 1, 2025**; most likely during the month of December 2025. For **annual subscribers**, the new plan and pricing will take effect on your next renewal after December 1, 2025. - -If you have any questions, please reach out to us at **billing@warp.dev**. - -#### **What happens to my current plan (Pro, Turbo, Lightspeed, Business)?** - -You will retain your current plan and credits until the first renewal after December 1, 2025. At renewal, all current Pro, Turbo, Lightspeed, and Business plans will transition to the new Warp Build and Business plans. - -The Build and new Business plans include 1,500 monthly credits, the ability to purchase [Add-on Credits](/support-and-community/plans-and-billing/add-on-credits/) that roll over for 12 months, and the ability to bring your own API key. Learn more at [warp.dev/pricing](https://www.warp.dev/pricing). - -In addition, [Add-on credit auto reload](/support-and-community/plans-and-billing/add-on-credits/#id-2.-enable-auto-reload) will be automatically enabled for some legacy plan users in the following ways (but can be opted out of or modified at any time). Our goal is to maintain the same maximum monthly spend in line with your legacy plan subscription plus any Overages: - -* **Pro:** Will transition to the Build plan. Auto-reload _**will not**_** be enabled by default**. -* **Turbo:** Will transition to the Build plan. Auto-reload _**will**_** be enabled by default**. It will default to $30 auto-reload monthly spending limit for monthly subscribers and $22 for yearly subscribers. A handful of Turbo subscribers received a bulk discount for teams of 3 or more—please check your email for details on the default spending limits for your account. -* **Lightspeed:** Will transition to the Build plan. Auto-reload _**will**_** be enabled by default**. It will default to $205 auto-reload monthly spending limit for monthly subscribers and $182 for yearly subscribers. -* **Business:** Will transition to the new Business plan. Auto-reload _**will**_** be enabled by default**. It will default to $10 auto-reload monthly spending limit for both monthly and yearly subscribers. - -In any of the above cases, if Overages were enabled, we will set the monthly auto-reload spending limit equal to your Overage spending limit plus any of the amounts listed above.\ -\ -If your total auto-reload monthly spend limit is $80 or above, we will set the Add-on credit denomination to $20 / 1000 credits by default. If your total auto reload monthly spending limit is below $80, we will set the Add-on credit denomination to $10 / 400 credits by default. +Your team's current access doesn't change. Existing members keep their seats and can continue using Warp the same way they do today. -#### Can I continue to use Warp as my primary terminal? +The cap only governs **adding new members**. While your team is at or above the cap, you can't add a new member or backfill a seat after a member leaves. To grow past the cap, switch to the next plan up (or to Enterprise) anytime under **Settings** > **Billing and usage**. -Yes, the terminal features of Warp will continue to be free to use for developers. Learn more at [Plans And Pricing](/support-and-community/plans-and-billing/plans-pricing-refunds/). +#### How are add-on credits being attributed differently? -#### How are Add-on credits different from overages? +Before May 21, 2026, add-on credits on multi-seat teams were **pooled**. Every team member drew from a single shared balance. As of May 21, 2026, **add-on credits are user-scoped**. Each user has their own balance, and a single heavy user can no longer drain the whole team's purchased credits. -Add-on credits replace overages with a simpler, prepaid system. They’re up to \~40% cheaper than the old overage rates, roll over month-to-month, and remain valid for 12 months. They also come with Warp’s full SOC 2 / Zero Data Retention protection. +Two practical changes for teams: -#### Do credits rollover? +* **Anyone on the team can now purchase add-on credits** for their own usage, subject to the team-wide spend cap admins set under **Settings** > **Billing and usage**. Previously, admins typically managed the shared pool on behalf of the team. +* **Grandfathered pooled credits**: Existing pooled add-on credit balances purchased before May 21, 2026 are honored. They drain first across the team before any user-scoped add-on credits are consumed. No new credits are added to the pooled balance. Once it's exhausted, all future add-on credit purchases are user-scoped. -For existing users on legacy plans, Warp credits on Pro, Turbo, and Lightspeed do not rollover. +For details, see [add-on credits](/support-and-community/plans-and-billing/add-on-credits/). -For the Build plan, credits will not rollover but Add-on credits will rollover and be valid for 12 months from the date of purchase. +#### What happens to my add-on credits if I leave the team? -#### Can I purchase Add-on Credits on legacy plans (Pro, Turbo, Lightspeed)? +Add-on credits are tied to the team that paid for them, so team-membership changes affect access: -No. Add-on Credits (including auto-reload) are only available on the Build, Business, and Enterprise plans. If you attempt to purchase Add-on Credits on a legacy plan, the purchase will not go through. To access Add-on Credits, switch to the Build plan at any time from **Settings** > **Billing and usage** or at [app.warp.dev/upgrade](https://app.warp.dev/upgrade). If you need additional usage while on a legacy plan, you can use [Overages (Legacy)](/support-and-community/plans-and-billing/overages-legacy/) instead. +* **You leave a team**: You lose access to any add-on credits tied to that team. If you rejoin the same team later, you regain access to any unused, non-expired credits. The admin pays a prorated rate for your seat on rejoin. +* **An admin removes you from a team**: You lose access to any add-on credits tied to that team. If you rejoin later, you regain access to any unused, non-expired credits. +* **An admin deletes the team**: Any remaining add-on credits tied to the team are no longer usable by anyone. -#### Can I bring my own key on legacy plans (Pro, Turbo, Lightspeed)? +Unused add-on credits remain valid for 12 months from purchase, as long as you have an active subscription. See [When team membership changes](/support-and-community/plans-and-billing/add-on-credits/#when-team-membership-changes) on the add-on credits page for full details. -No, Bring-your-own API key for OpenAI, Anthropic, and Gemini is only available to users on the Warp Build plan. You can choose to switch your existing plan to Warp Build at any time before your applicable renewal date to access BYOK. +#### Can I bring my own API key on the Free plan now? -#### How does the monthly spend limit on Add-on Credits work? +Yes. As of May 21, 2026, **Bring Your Own API Key (BYOK)** is available on all plans, including Free. Previously, BYOK required a Build, Business, or Enterprise subscription. You can configure your OpenAI, Anthropic, or Google key under **Settings** > **AI** > **Manage models**. -You set a monthly spend limit that applies to your AI usage for each calendar month. This limit acts as the maximum amount you can spend on credits during that period. +See [Bring Your Own API Key](/agent-platform/inference/bring-your-own-api-key/) for the full list of supported providers and setup steps. -If a purchase would exceed your limit, it won’t go through—you’ll need to either increase your limit or choose a smaller purchase amount. +#### What is the new custom inference endpoint feature? -**For auto reload settings:** +**Custom inference endpoints** let you route Warp's AI traffic through any OpenAI-compatible inference endpoint, including OpenRouter, LiteLLM, z.ai, and internal gateways your team already runs. Support is available on Free, Build, Max, Business, and Enterprise. -* New users who enable auto reload will start with a $200 spend limit. -* Existing paid plan users who enable auto reload will have their limit match their existing Overages spend limit (if previously configured, otherwise $200). +Here's how custom inference endpoints differ from BYOK and BYOLLM: -#### I’m an individual developer and need more than 1,500 credits per month. What’s the right plan for me? +* **BYOK** sends requests directly to OpenAI, Anthropic, or Google using your own provider API key. +* **Custom inference endpoint** sends requests to any OpenAI-compatible URL you control or that your team runs. +* **BYOLLM** is an Enterprise-only managed inference feature. Warp routes traffic through your cloud provider (AWS Bedrock today, with Azure Foundry and Google Vertex coming soon) and handles the routing, orchestration, governance, and observability. -If you regularly use more than 1,500 credits per month, the Build plan is designed for you. It includes 1,500 monthly credits and gives you the flexibility to scale further with Add-on Credits, which you can purchase at discounted rates directly under **Settings** > **Billing and usage**. +For setup and details, see [Custom inference endpoint](/agent-platform/inference/custom-inference-endpoint/). -Add-on Credits roll over month to month, remain valid for 12 months, and offer up to \~40% savings for larger denominations. You can also enable auto reload to automatically top up your credits when your balance runs low. +#### When do platform credits start being charged on self-serve plans? -If you’re part of a team that needs shared credit management, SSO, or enforced Zero Data Retention (ZDR), the Business plan provides all the same AI capabilities plus advanced security and administrative features. +[Platform credits](/support-and-community/plans-and-billing/platform-credits/) apply to every cloud agent run, plus local agent runs on Business that use BYOK or a custom inference endpoint. **For self-serve plans (Free, Build, Max, Business), platform-credits billing doesn't start until July 1, 2026.** -#### Should I subscribe to the Build plan or the Business plan? +Between May 21 and June 30, 2026, all self-serve plans are in a **preview period**. Platform credits are not consumed during this window, so they won't draw from your monthly Warp credits, your add-on credit balance, or your spend cap. -If you’re an individual developer or part of a small team, the Build plan is the best fit. It includes 1,500 monthly credits, discounted Add-on Credits for additional usage, and the ability to bring your own API key (BYOK) for OpenAI, Anthropic, or Google models. You’ll also get unlimited Warp Drive objects, collaboration tools, and the highest codebase indexing limits. +On **Enterprise**, platform credit usage is governed by your contract. See [enterprise billing](/enterprise/support-and-resources/billing/) for details. -If you’re part of a larger team (up to 50 members) that needs advanced administrative and security controls, choose the Business plan. It includes everything in Build, plus SSO, enforced Zero Data Retention (ZDR), shared Add-on Credits that can be used by all team members, and centralized billing – ideal for organizations that need stronger security, compliance, and team-wide management. +On **July 1, 2026**, Warp begins consuming platform credits for: -#### How do credits work for multi-seat teams? +* Every cloud agent run on Free, Build, Max, or Business. +* Local agent runs on Business that use BYOK or a custom inference endpoint. -For teams on the Build or Business plans, credits are managed at two levels: +#### I'm a team admin. What do I need to do? -* **Included monthly credits**: Each seat on a paid plan receives 1,500 individual credits per month. These credits are tied to the user and reset every 30 days based on their subscription or renewal date. -* **Add-on Credits**: Once individual credits are used up, team members draw from a shared Add-on Credit balance that can be topped up and managed by team admins. +A short checklist to triage the May 2026 changes for your team: -This shared model gives teams the flexibility to handle variable AI usage – heavy users can consume more when needed, while the entire team benefits from shared value and volume-based discounts. +* **Check your seat count.** Go to **Settings** > **Teams** to see whether your team is at or above your plan's new seat limit. If you are, see [What if my team is already above the new seat limit?](#what-if-my-team-is-already-above-the-new-seat-limit). +* **Set your team's add-on credit spend cap.** Under **Settings** > **Billing and usage**, configure the monthly cap that applies to add-on credit purchases across your team. Team members can now buy their own add-on credits, but every purchase counts against this cap. +* **Let your team know add-on credits are user-scoped now.** Each member can purchase add-on credits for their own usage without affecting anyone else's balance. +* **Plan for platform credits on July 1, 2026.** If your team is on Business and uses BYOK or a custom inference endpoint locally, those local runs will start consuming platform credits when the preview period ends. See [When do platform credits start being charged on self-serve plans?](#when-do-platform-credits-start-being-charged-on-self-serve-plans). diff --git a/src/content/docs/terminal/input/classic-input.mdx b/src/content/docs/terminal/input/classic-input.mdx index bdc1bd6e..9d36dad1 100644 --- a/src/content/docs/terminal/input/classic-input.mdx +++ b/src/content/docs/terminal/input/classic-input.mdx @@ -130,4 +130,4 @@ Once a requested command is executed, you can click to expand the output and vie If a requested command fails, Oz detects it. Agent Mode is self-correcting. It will request another command until it completes the task for you. -Warp lets you choose from a curated list of LLMs for use in Agent Mode. By default, Warp uses **Auto (Responsive)**, which routes to the highest-quality, fastest available model. You can switch to other supported models — see [Model choice](/agent-platform/capabilities/model-choice/) for the full list. +Warp lets you choose from a curated list of LLMs for use in Agent Mode. By default, Warp uses **Auto (Responsive)**, which routes to the highest-quality, fastest available model. You can switch to other supported models — see [Model choice](/agent-platform/inference/model-choice/) for the full list. diff --git a/src/content/docs/terminal/input/universal-input.mdx b/src/content/docs/terminal/input/universal-input.mdx index 591ba9d2..e715d770 100644 --- a/src/content/docs/terminal/input/universal-input.mdx +++ b/src/content/docs/terminal/input/universal-input.mdx @@ -325,4 +325,4 @@ From the Profile Picker, you can view all available profiles, switch between the The Model Picker is tied to your current Agent Profile. Each profile has a default model, but you can override it at any time using the picker. Warp curates a selection of top large language models (LLMs) for you to choose from, balancing speed, quality, and reasoning ability depending on your needs. -For a full list of supported models and guidance on when to use them, see [Model Choice](/agent-platform/capabilities/model-choice/). +For a full list of supported models and guidance on when to use them, see [Model Choice](/agent-platform/inference/model-choice/). diff --git a/src/sidebar.ts b/src/sidebar.ts index fc60bc8e..ed8b12fd 100644 --- a/src/sidebar.ts +++ b/src/sidebar.ts @@ -260,7 +260,6 @@ export const sidebarTopics: StarlightSidebarTopicsUserConfig = [ 'agent-platform/capabilities/skills', 'agent-platform/capabilities/planning', { slug: 'agent-platform/capabilities/task-lists', label: 'Task lists' }, - 'agent-platform/capabilities/model-choice', 'agent-platform/capabilities/rules', { slug: 'agent-platform/capabilities/agent-notifications', label: 'Agent notifications' }, { slug: 'agent-platform/capabilities/full-terminal-use', label: 'Full terminal use' }, @@ -296,6 +295,15 @@ export const sidebarTopics: StarlightSidebarTopicsUserConfig = [ 'agent-platform/capabilities/mcp', ], }, + { + label: 'Inference & providers', + collapsed: true, + items: [ + { slug: 'agent-platform/inference/model-choice', label: 'Model choice' }, + 'agent-platform/inference/bring-your-own-api-key', + { slug: 'agent-platform/inference/custom-inference-endpoint', label: 'Custom inference endpoint' }, + ], + }, { slug: 'agent-platform/local-agents/interactive-code-review', label: 'Interactive code review' }, { slug: 'agent-platform/local-agents/active-ai', label: 'Active AI recommendations' }, 'agent-platform/local-agents/generate', @@ -540,8 +548,6 @@ export const sidebarTopics: StarlightSidebarTopicsUserConfig = [ 'support-and-community/plans-and-billing/credits', 'support-and-community/plans-and-billing/add-on-credits', { slug: 'support-and-community/plans-and-billing/platform-credits', label: 'Platform credits' }, - 'support-and-community/plans-and-billing/bring-your-own-api-key', - 'support-and-community/plans-and-billing/overages-legacy', 'support-and-community/plans-and-billing/pricing-faqs', ], }, diff --git a/vercel.json b/vercel.json index f2b32ed3..276877f2 100644 --- a/vercel.json +++ b/vercel.json @@ -115,7 +115,7 @@ }, { "source": "/agent-platform/agent-concepts/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -240,7 +240,7 @@ }, { "source": "/agent-platform/agent-mode/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -315,7 +315,7 @@ }, { "source": "/agent-platform/agent-platform/ai-model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -380,7 +380,7 @@ }, { "source": "/agent-platform/agent-platform/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -490,22 +490,22 @@ }, { "source": "/agent-platform/agent-platform/using-agents/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { "source": "/agent-platform/agent-platform/using-agents/model-choice#available-models", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { "source": "/agent-platform/agent-platform/using-agents/model-choice#configuring-models-per-agent-profile", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { "source": "/agent-platform/agent-platform/using-agents/model-choice#how-to-change-models", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -605,7 +605,7 @@ }, { "source": "/agent-platform/agents/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -675,7 +675,7 @@ }, { "source": "/agent-platform/agents/using-agents/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -725,7 +725,7 @@ }, { "source": "/agent-platform/ai-features/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -915,7 +915,7 @@ }, { "source": "/agent-platform/features/ai-command-search/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -925,7 +925,7 @@ }, { "source": "/agent-platform/features/ai-command/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -960,7 +960,7 @@ }, { "source": "/agent-platform/features/ai/ai-models-and-providers", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -1010,7 +1010,7 @@ }, { "source": "/agent-platform/features/ai/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -1040,7 +1040,7 @@ }, { "source": "/agent-platform/features/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -1050,7 +1050,7 @@ }, { "source": "/agent-platform/features/terminal-ai/ai-models", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -1420,7 +1420,7 @@ }, { "source": "/agent-platform/warp-agents/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -2740,7 +2740,7 @@ }, { "source": "/support-and-community/help/ai-features/bring-your-own-llm", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { @@ -2843,6 +2843,11 @@ "destination": "/support-and-community/troubleshooting-and-support/known-issues/", "statusCode": 308 }, + { + "source": "/support-and-community/plans-and-billing/overages-legacy", + "destination": "/support-and-community/plans-and-billing/add-on-credits/", + "statusCode": 308 + }, { "source": "/support-and-community/plans-pricing-and-billing", "destination": "/support-and-community/plans-and-billing/plans-pricing-refunds/", @@ -2860,12 +2865,12 @@ }, { "source": "/support-and-community/plans-pricing-and-billing/bring-your-own-api-key", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { "source": "/support-and-community/plans-pricing-and-billing/overages-legacy", - "destination": "/support-and-community/plans-and-billing/overages-legacy/", + "destination": "/support-and-community/plans-and-billing/add-on-credits/", "statusCode": 308 }, { @@ -2970,7 +2975,7 @@ }, { "source": "/support-and-community/support-and-billing/plans-and-billing/bring-your-own-api-key", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { @@ -3005,17 +3010,17 @@ }, { "source": "/support-and-community/support-and-billing/plans-and-pricing/bring-your-own-api-key", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { "source": "/support-and-community/support-and-billing/plans-and-pricing/bring-your-own-api-key#enabling-byok", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { "source": "/support-and-community/support-and-billing/plans-and-pricing/bring-your-own-api-key#how-does-byok-work", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { @@ -3040,12 +3045,12 @@ }, { "source": "/support-and-community/support-and-billing/plans-and-pricing/usage-overages", - "destination": "/support-and-community/plans-and-billing/overages-legacy/", + "destination": "/support-and-community/plans-and-billing/add-on-credits/", "statusCode": 308 }, { "source": "/support-and-community/support-and-billing/plans-and-prilling/bring-your-own-api-key", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { @@ -3135,12 +3140,12 @@ }, { "source": "/support-and-community/support-and-community/plans-pricing-and-billing/bring-your-own-api-key", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { "source": "/support-and-community/support-and-community/plans-pricing-and-billing/overages-legacy", - "destination": "/support-and-community/plans-and-billing/overages-legacy/", + "destination": "/support-and-community/plans-and-billing/add-on-credits/", "statusCode": 308 }, { @@ -4030,7 +4035,7 @@ }, { "source": "/agent-platform/warp-agents/capabilities-overview/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -4395,7 +4400,7 @@ }, { "source": "/support-and-billing/plans-and-pricing/bring-your-own-api-key", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { @@ -4475,7 +4480,7 @@ }, { "source": "/agent-platform/agent-concepts/model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -4600,7 +4605,7 @@ }, { "source": "/agent-platform/agent-mode/model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -4660,7 +4665,7 @@ }, { "source": "/agent-platform/agent-platform/ai-model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -4720,7 +4725,7 @@ }, { "source": "/agent-platform/agent-platform/model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -4795,7 +4800,7 @@ }, { "source": "/agent-platform/agent-platform/using-agents/model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -4895,7 +4900,7 @@ }, { "source": "/agent-platform/agents/model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -4965,7 +4970,7 @@ }, { "source": "/agent-platform/agents/using-agents/model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -5015,7 +5020,7 @@ }, { "source": "/agent-platform/ai-features/model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -5175,7 +5180,7 @@ }, { "source": "/agent-platform/features/ai-command-search/model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -5185,7 +5190,7 @@ }, { "source": "/agent-platform/features/ai-command/model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -5220,7 +5225,7 @@ }, { "source": "/agent-platform/features/ai/ai-models-and-providers/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -5270,7 +5275,7 @@ }, { "source": "/agent-platform/features/ai/model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -5300,7 +5305,7 @@ }, { "source": "/agent-platform/features/model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -5310,7 +5315,7 @@ }, { "source": "/agent-platform/features/terminal-ai/ai-models/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -6725,7 +6730,7 @@ }, { "source": "/support-and-community/help/ai-features/bring-your-own-llm/", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { @@ -6783,6 +6788,11 @@ "destination": "/support-and-community/troubleshooting-and-support/known-issues/", "statusCode": 308 }, + { + "source": "/support-and-community/plans-and-billing/overages-legacy/", + "destination": "/support-and-community/plans-and-billing/add-on-credits/", + "statusCode": 308 + }, { "source": "/support-and-community/plans-pricing-and-billing/", "destination": "/support-and-community/plans-and-billing/plans-pricing-refunds/", @@ -6800,12 +6810,12 @@ }, { "source": "/support-and-community/plans-pricing-and-billing/bring-your-own-api-key/", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { "source": "/support-and-community/plans-pricing-and-billing/overages-legacy/", - "destination": "/support-and-community/plans-and-billing/overages-legacy/", + "destination": "/support-and-community/plans-and-billing/add-on-credits/", "statusCode": 308 }, { @@ -6870,7 +6880,7 @@ }, { "source": "/support-and-community/support-and-billing/plans-and-billing/bring-your-own-api-key/", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { @@ -6895,7 +6905,7 @@ }, { "source": "/support-and-community/support-and-billing/plans-and-pricing/bring-your-own-api-key/", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { @@ -6910,12 +6920,12 @@ }, { "source": "/support-and-community/support-and-billing/plans-and-pricing/usage-overages/", - "destination": "/support-and-community/plans-and-billing/overages-legacy/", + "destination": "/support-and-community/plans-and-billing/add-on-credits/", "statusCode": 308 }, { "source": "/support-and-community/support-and-billing/plans-and-prilling/bring-your-own-api-key/", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { @@ -6975,12 +6985,12 @@ }, { "source": "/support-and-community/support-and-community/plans-pricing-and-billing/bring-your-own-api-key/", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { "source": "/support-and-community/support-and-community/plans-pricing-and-billing/overages-legacy/", - "destination": "/support-and-community/plans-and-billing/overages-legacy/", + "destination": "/support-and-community/plans-and-billing/add-on-credits/", "statusCode": 308 }, { @@ -7175,7 +7185,7 @@ }, { "source": "/agent-platform/warp-agents/model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -7670,7 +7680,7 @@ }, { "source": "/agent-platform/warp-agents/capabilities-overview/model-choice/", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -8030,7 +8040,7 @@ }, { "source": "/support-and-billing/plans-and-pricing/bring-your-own-api-key/", - "destination": "/support-and-community/plans-and-billing/bring-your-own-api-key/", + "destination": "/agent-platform/inference/bring-your-own-api-key/", "statusCode": 308 }, { @@ -8150,7 +8160,7 @@ }, { "source": "/agents/using-agents/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -8185,7 +8195,7 @@ }, { "source": "/agent-platform/agent/using-agents/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -8245,7 +8255,7 @@ }, { "source": "/agent-platform/warps-agent/capabilities-overview/model-choice", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -8585,12 +8595,12 @@ }, { "source": "/agents/using-agents/model-choice#available-models", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { "source": "/agents/using-agents/model-choice#how-to-change-models", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -8670,22 +8680,22 @@ }, { "source": "/agent-platform/agent/using-agents/model-choice#auto-models", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { "source": "/agent-platform/agent/using-agents/model-choice#available-models", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { "source": "/agent-platform/agent/using-agents/model-choice#how-to-change-models", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { "source": "/agent-platform/agent/using-agents/model-choice#model-fallback", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -8840,17 +8850,17 @@ }, { "source": "/agent-platform/warps-agent/capabilities-overview/model-choice#auto-models", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { "source": "/agent-platform/warps-agent/capabilities-overview/model-choice#how-to-change-models", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { "source": "/agent-platform/warps-agent/capabilities-overview/model-choice#model-fallback", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -9070,7 +9080,7 @@ }, { "source": "/agents/using-agents/model-choice#auto-models", - "destination": "/agent-platform/capabilities/model-choice/", + "destination": "/agent-platform/inference/model-choice/", "statusCode": 308 }, { @@ -9577,6 +9587,21 @@ "source": "/agent-platform/capabilities/agent-memory", "destination": "/agent-platform/agent-memory/", "statusCode": 308 + }, + { + "source": "/agent-platform/capabilities/model-choice", + "destination": "/agent-platform/inference/model-choice/", + "statusCode": 308 + }, + { + "source": "/support-and-community/plans-and-billing/bring-your-own-api-key", + "destination": "/agent-platform/inference/bring-your-own-api-key/", + "statusCode": 308 + }, + { + "source": "/support-and-community/plans-and-billing/custom-inference-endpoint", + "destination": "/agent-platform/inference/custom-inference-endpoint/", + "statusCode": 308 } ] }