Repository navigation
chore: fixing the anthrpic models pricing - #1009
Merged
Merged
Conversation
Contributor
There was a problem hiding this comment.
🟡 Changes recommended
Vertex AI’s Opus 5.5 batch prices are overstated by 25% relative to the retained half-price rates, requiring corrections across the batch configurations and unprefixed alias.
1 open issue
What changed in this PR
This PR updates Anthropic model pricing across the provider catalogs and expands Bedrock model configuration coverage.
Changes:
- Adjusts Vertex AI batch rates and Anthropic/Vertex AI cache pricing.
- Adds Bedrock Sonnet 5.5 pricing entries and Haiku 5.5 context-tier pricing.
- Adds Bedrock Sonnet 5.5 parameter and capability configurations.
| File | Description |
|---|---|
pricing/vertex-ai.json |
Updates Opus 5.5 batch rates and Sonnet 5.5 cache-read rates. |
pricing/bedrock.json |
Adds Sonnet 5.5 pricing aliases and Haiku 5.5 context tiers. |
pricing/anthropic.json |
Adds batch cache pricing and adjusts cache-read rates. |
general/bedrock.json |
Adds base, US, and EU Sonnet 5.5 configurations. |
Review effort: Balanced
…pricing - Vertex AI: restore Opus 5.5 batch request/response token prices to the correct 50% discount (0.0002/0.001 default, 0.00022/0.0011 US/EU) instead of the overstated 1.25x values, for both the anthropic.claude-opus-5-5 entry and the unprefixed claude-opus-5-5 alias, across standard and batch context tiers. - Bedrock: fix Sonnet 5.5 cache_read_input_token pricing to use the 0.05x multiplier (0.1/MTok global, 0.11/MTok US/EU) per Anthropic's Oct 7 2026 price cut, instead of the stale 0.1x multiplier, across us/eu.anthropic.claude-sonnet-5-5 and the *-v1 variants (including global). Verified against Anthropic's official pricing page and rate card PDF, and Google Cloud's Vertex AI partner model pricing page. Addresses PR review comments from Copilot, sivadurga-d, and prabhash-varma on PR #1009. Co-authored-by: Cursor <cursoragent@cursor.com>
Contributor
There was a problem hiding this comment.
🟡 Changes recommended
The unversioned Claude Sonnet 5.5 entries still use a cache-read rate of 0.00002 instead of 0.00001, causing cost attribution to remain twice the corrected rate.
1 open issue
1 resolved since last review
Review effort: Balanced
prabhash-varma
approved these changes
Oct 29, 2026
6 of 8 tasks
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
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.
Description
Please include a summary of the changes and the related issue. Please also include relevant motivation and context.
Source Verification
https://aws.amazon.com/bedrock/pricing/
https://cloud.google.com/model-garden/partner-models/pricing?hl=en
https://platform.claude.com/docs/en/about-claude/pricing
Important
Please include a link to the official pricing page from the provider. Simple "I heard it from somewhere" or screenshot sources are not accepted.
Checklist
jqor an online validatorRelated Issue
Fixes # (issue)
Anthropic sonnet cache read pricing reduciton and few other batch pricing fixes.