OpenAI & Anthropic Compatible API Gateway for AWS Bedrock and AI Services
Run your favorite OpenAI and Anthropic-compatible applications on AWS Bedrock. Access 80+ models including Claude, Kimi K2, MiniMax, Qwen with enterprise privacy, compliance controls, and pay-per-use AWS pricing.
14-day free trial on AWS Marketplace · $0.10/container-hour
Free for local development · Try Locally with Docker
Run stdapi.ai locally with the free community image. Requires AWS credentials configured (run aws sso login first).
docker run --rm -p 8000:8000 \
-v ~/.aws:/home/nonroot/.aws:ro \
-e AWS_BEDROCK_REGIONS=us-east-1,us-west-2 \
-e ENABLE_DOCS=true \
ghcr.io/stdapi-ai/stdapi.ai-community:latestPodman on Fedora/RHEL (SELinux): Add
--userns=keep-idand use:ro,zinstead of:ro
Open http://localhost:8000/docs in your browser — Swagger UI lets you explore all endpoints and send live requests without writing any code.
Or test from the terminal with curl:
List available models:
# All discovered models with capabilities, modalities, and supported routes
curl http://localhost:8000/search_models
# Filter — e.g. vision-capable chat models only
curl "http://localhost:8000/search_models?route=/v1/chat/completions&input_modalities=IMAGE"
# OpenAI-compatible model list
curl http://localhost:8000/v1/modelsOpenAI-compatible chat:
curl http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "amazon.nova-micro-v1:0",
"messages": [{"role": "user", "content": "Hello from AWS Bedrock!"}]
}'Anthropic-compatible chat:
curl http://localhost:8000/anthropic/v1/messages \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{
"model": "amazon.nova-micro-v1:0",
"max_tokens": 1000,
"messages": [{"role": "user", "content": "Hello from AWS Bedrock!"}]
}'Using the official SDKs? Point base_url at http://localhost:8000/v1 (OpenAI SDK) or http://localhost:8000/anthropic (Anthropic SDK) — no other code changes.
Deploy to AWS in minutes with Terraform. The AWS Marketplace subscription includes a 14-day free trial.
module "stdapi_ai" {
source = "stdapi-ai/stdapi-ai/aws"
version = "~> 1.0"
}That's it. You get a production-grade ECS Fargate deployment with HTTPS, WAF, auto-scaling, and monitoring.
Full deployment guide → · Advanced deployment →
Prefer a hands-off setup? A managed deployment service is available.
- 🔌 Drop-in replacement — Change only the base URL. Works with LangChain, Continue.dev, Open WebUI, n8n, Claude Code, Aider, and 1000+ tools.
- 🔒 Data stays in your AWS account — All inference runs in your account. Data never shared with model providers or used for training. Configure allowed regions for GDPR, HIPAA, FedRAMP.
- 🌍 Multiply quota across regions — Each AWS region has independent quota. 3 regions = 3× tokens per minute. Automatic routing and failover—no client changes.
- 💰 Pay only what you use — AWS Bedrock rates, no markup, no subscriptions or monthly minimums.
- ⚡ Advanced Bedrock features — Reasoning modes (Claude, Nova), prompt caching, guardrails, service tiers, inference profiles, prompt routers—all through standard OpenAI and Anthropic API parameters.
- 🧠 80+ models — Claude, Kimi K2, MiniMax, Qwen, GLM, Nova, Llama, Stability AI, and more. Switch instantly—no vendor lock-in.
- 🎨 Complete multi-modal API — Chat, embeddings, image generation/editing/variations, audio speech/transcription/translation. Amazon Polly, Transcribe, Translate unified under OpenAI-compatible endpoints.
- 📊 Full observability — OpenTelemetry integration, request/response logging, Swagger and ReDoc API documentation.
- 🤖 Integrated MCP server — Every API endpoint exposed as a Model Context Protocol tool. AI agents connect directly—no HTTP client code required. Streamable HTTP and SSE transports with configurable tool selection.
- 🔄 Automatic deprecated model fallback — When AWS retires a model, requests are transparently redirected to its replacement. Applications survive model deprecations without code changes.
| Category | What You Can Build | Tools | Guide |
|---|---|---|---|
| 💬 Chat Interfaces | Private ChatGPT alternative, team chat, knowledge base with RAG | Open WebUI, LibreChat | Guide → |
| 💻 Coding Assistants | AI pair programming, code completion, codebase chat | Continue.dev, Cline, Cursor, Claude Code, Aider | Guide → |
| 🔄 Workflow Automation | AI-powered ticket routing, content creation, data processing | n8n, Make, Zapier | Guide → |
| 🤖 Chatbots | Slack/Discord/Teams bots, documentation assistants | Slack Bot, Botpress | |
| 🧠 Autonomous Agents | Personal AI assistants, research agents, multi-agent systems, code agents | OpenClaw, LangGraph, CrewAI, AutoGPT |
All use cases and integration guides →
The commercial license via AWS Marketplace is for production, internal tools, and proprietary applications:
- ✅ 14-day free trial — test in your environment risk-free
- ✅ Commercial license — no AGPL obligations, keep your code private
- ✅ Hardened containers — security-optimized with regular updates
- ✅ Terraform module — production-ready infrastructure in minutes
- ✅ Streamlined AWS billing — consolidated with your existing AWS costs
For contributors working on stdapi.ai itself:
- Python 3.14+
- uv package manager
- AWS credentials configured
git clone https://github.com/stdapi-ai/stdapi.ai.git
cd stdapi.ai
uv sync --frozen --extra uvicorn
aws sso login --profile your-profile-name
export AWS_BEDROCK_REGIONS=us-east-1
export ENABLE_DOCS=true
uv run uvicorn stdapi.main:app --host 0.0.0.0 --port 8000- Follow existing code style and conventions
- Add tests for new features
- Update documentation for user-facing changes
- Ensure all tests pass before submitting PR
Dual-licensed:
- AGPL-3.0-or-later — Free for open-source projects that share alike
- Commercial License — AWS Marketplace, for proprietary applications (14-day free trial)
We welcome contributions! Whether it's bug reports, new features, documentation improvements, or ideas — please feel free to open issues or submit pull requests.
- Issues: GitHub Issue Tracker
- Documentation: stdapi.ai
- Sponsor: GitHub Sponsors — Priority support, feature prioritization, and influence on the roadmap. View tiers →
Ready to run 80+ AI models securely on AWS?
Start 14-Day Free Trial on AWS Marketplace · Deployment guide · Terraform examples · Try Locally with Docker