fix: add DeepSeek v4 Pro/Flash pricing and fix snapshot survival through runtime cache#366
Open
NihalJain wants to merge 1 commit into
Open
fix: add DeepSeek v4 Pro/Flash pricing and fix snapshot survival through runtime cache#366NihalJain wants to merge 1 commit into
NihalJain wants to merge 1 commit into
Conversation
…ugh runtime cache (getagentseal#365) Pricing sourced from api-docs.deepseek.com/quick_start/pricing: deepseek-v4-flash: $0.14/M input · $0.28/M output · $0.0028/M cache-read · free cache-write deepseek-v4-pro: $1.74/M input · $3.48/M output · $0.0145/M cache-read · free cache-write Note: LiteLLM PR #27056 had incorrect cache-read prices (1.4e-8 for flash, 1.74e-7 for pro); corrected here to match the official docs (2.8e-9 and 1.45e-8 respectively). Changes: - bundle-litellm.mjs: add both models to MANUAL_ENTRIES so they survive future re-bundles until LiteLLM PR #27056 is merged - models.ts: add display names; fix loadPricing() to merge bundled snapshot entries back after loading the 24-hour runtime cache file, so MANUAL_ENTRIES are never silently dropped - providers/claude.ts: add shortNames for the Claude provider display - tests/models.test.ts: regression tests for pricing values, provider-prefixed lookups, calculateCost with observed production token counts, and display names
NihalJain
changed the title
Contributor
Author
|
Hi @iamtoruk please have a look |
This was referenced May 20, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fixes #365!
Pricing sourced from api-docs.deepseek.com/quick_start/pricing:
deepseek-v4-flash: $0.14/M input · $0.28/M output · $0.0028/M cache-read · free cache-write
deepseek-v4-pro: $1.74/M input · $3.48/M output · $0.0145/M cache-read · free cache-write
Note: LiteLLM PR #27056 had incorrect cache-read prices (1.4e-8 for flash, 1.74e-7 for pro); corrected here to match the official docs (2.8e-9 and 1.45e-8 respectively).
Changes:
Testing
npm testpassesnpm run buildsucceedsnode dist/cli.js todayshows correct costs and session counts for this providernode dist/cli.js today --provider claudeshows correct model names and pricing