Issue Station
Sign In
Tools hereToolbox

litellm - ✅(Solved) Fix Fix "us.anthropic.claude-opus-4-6-v1" entry in "model_prices_and_context_window.json" [1 pull requests, 1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
BerriAI/litellm#23506•Fetched 2026-04-08 00:43:56
View on GitHub
Comments
0
Participants
1
Timeline
4
Reactions
0
Author
Yu-yunjongYu-yunjong
Participants
Yu-yunjongYu-yunjong
Timeline (top)
cross-referenced ×1labeled ×1referenced ×1subscribed ×1

Root Cause

Because of this, listing the Max Input for Opus 4.6 as 1,000,000 tokens may give the impression that the default input limit is 1M, which is not how the official documentation describes the model.

Fix Action

Fixed

PR fix notes

PR #24593: fix: correct max_input_tokens for Claude Opus 4.6 from 1M to 200K bas…

Description (problem / solution / changelog)

…e limit (#23506)

Relevant issues

<!-- e.g. "Fixes #000" -->

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

  • I have Added testing in the tests/test_litellm/ directory, Adding at least 1 test is a hard requirement - see details
  • My PR passes all unit tests on make test-unit
  • My PR's scope is as isolated as possible, it only solves 1 specific problem
  • I have requested a Greptile review by commenting @greptileai and received a Confidence Score of at least 4/5 before requesting a maintainer review

Delays in PR merge?

If you're seeing a delay in your PR being merged, ping the LiteLLM Team on Slack (#pr-review).

CI (LiteLLM team)

CI status guideline:

  • 50-55 passing tests: main is stable with minor issues.
  • 45-49 passing tests: acceptable but needs attention
  • <= 40 passing tests: unstable; be careful with your merges and assess the risk.

  • Branch creation CI run
    Link:

  • CI run for the last commit
    Link:

  • Merge / cherry-pick CI run
    Links:

Type

<!-- Select the type of Pull Request --> <!-- Keep only the necessary ones -->

🆕 New Feature 🐛 Bug Fix 🧹 Refactoring 📖 Documentation 🚄 Infrastructure ✅ Test

Changes

Changed files

  • litellm/model_prices_and_context_window_backup.json (modified, +14/-27)
  • model_prices_and_context_window.json (modified, +14/-27)
RAW_BUFFERClick to expand / collapse

https://github.com/BerriAI/litellm/blob/92d39c308cd6426943ad7a0a83569cc9647815fb/model_prices_and_context_window.json#L1032-L1050

We also need to update model_prices_and_context_window_backup.json.

Hi, I believe there is an incorrect Max Input value for Claude Opus 4.6 in the LiteLLM model info page.

Currently the model info appears as:

Model Info

  • Provider: anthropic
  • Mode: Chat
  • Max Input: 1,000,000 tokens
  • Max Output: 128,000 tokens

Model Info

  • Provider: bedrock_converse
  • Mode: Chat
  • Max Input: 1,000,000 tokens
  • Max Output: 128,000 tokens

However, according to the official Anthropic documentation:

Claude Sonnet 4.6 → Max Input 200,000 tokens (base)

Claude Opus 4.6 → Max Input 200,000 tokens (base)

Both models can support 1M token input, but this is documented as an extended / beta context capability, not the default base limit.

Because of this, listing the Max Input for Opus 4.6 as 1,000,000 tokens may give the impression that the default input limit is 1M, which is not how the official documentation describes the model.

Suggested correction

Claude Opus 4.6

  • Max Input: 200,000 tokens
  • Max Output: 128,000 tokens

Optionally, extended capability could be indicated separately, e.g.:

  • Max Input: 200,000 tokens (base)
  • Extended context: 1,000,000 tokens

References

Anthropic Models Overview https://platform.claude.com/docs/en/about-claude/models/overview

Amazon Bedrock Claude documentation https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages-request-response.html

Thanks.

extent analysis

Fix Plan

To correct the Max Input value for Claude Opus 4.6, follow these steps:

  • Update the model_prices_and_context_window.json file:
    • Locate the section for Claude Opus 4.6
    • Change the Max Input value to 200,000 tokens
  • Optionally, add an Extended context field to indicate the 1,000,000 token capability:
    • Add a new field: "Extended context": "1,000,000 tokens"

Example code snippet:

{
  "Model Info": {
    "Provider": "anthropic",
    "Mode": "Chat",
    "Max Input": "200,000 tokens",
    "Max Output": "128,000 tokens",
    "Extended context": "1,000,000 tokens"
  }
}
  • Update the model_prices_and_context_window_backup.json file with the same changes.

Verification

After making these changes, verify that the Max Input value for Claude Opus 4.6 is correctly displayed as 200,000 tokens, and the Extended context capability is optionally shown as 1,000,000 tokens.

Extra Tips

  • Ensure that the changes are properly committed and pushed to the repository.
  • Review the official Anthropic documentation for any future updates to model limitations.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#ssr#installation#tensor shape#autograd error#optimization#mixed precision#training loop#device allocation#model download

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING