[Feat] add claude-opus-4-6 to model cost map

[ishaan-jaff]

[Feat] add claude-opus-4-6 to model cost map

Pre-Submission checklist

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

• I have Added testing in the tests/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

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

🆕 New Feature
✅ Test

Changes

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
litellm	Ready	Preview, Comment	Feb 5, 2026 6:40pm

[greptile-apps]

Greptile Overview

Greptile Summary

Added support for claude-opus-4-6 model with four variants (claude-opus-4-6, claude-opus-4-6-20260205, anthropic.claude-opus-4-6-20260205-v1:0, and azure_ai/claude-opus-4-6).

Key changes:

• Set max_output_tokens to 128,000 (double the 64,000 limit of opus 4.5)
• Maintained same pricing as opus 4.5: $5/MTok input, $25/MTok output
• Enabled all feature flags: reasoning, computer use, vision, prompt caching, etc.
• Both JSON files (main and backup) updated identically

Note: The PR checklist indicates tests have not been added yet, which is marked as a hard requirement in the contributing guidelines.

Confidence Score: 4/5

• Safe to merge with low risk - simple data addition following established patterns
• Configuration changes are straightforward and follow the exact pattern of existing opus models. JSON structure is valid and both files are synchronized. Minor deduction for missing tests mentioned in PR requirements.
• No files require special attention - both JSON files have identical, valid changes

Important Files Changed

Filename	Overview
model_prices_and_context_window.json	Added four claude-opus-4-6 model variants with 128k max output tokens (double opus 4.5's 64k limit)
litellm/model_prices_and_context_window_backup.json	Identical changes to main JSON file - added four claude-opus-4-6 model variants

Sequence Diagram

sequenceDiagram
    participant User
    participant LiteLLM
    participant CostMap as model_prices_and_context_window.json
    participant Provider as Anthropic API
    
    User->>LiteLLM: completion(model="claude-opus-4-6")
    LiteLLM->>CostMap: lookup "claude-opus-4-6"
    CostMap-->>LiteLLM: return pricing & config<br/>(max_output: 128k, input: $5/MTok)
    LiteLLM->>LiteLLM: validate max_tokens <= 128000
    LiteLLM->>Provider: forward request to Anthropic
    Provider-->>LiteLLM: response with token usage
    LiteLLM->>CostMap: calculate cost using<br/>input_cost_per_token & output_cost_per_token
    LiteLLM-->>User: response + calculated cost

Loading

[greptile-apps]

_{2 files reviewed, no comments}

_{Edit Code Review Agent Settings | Greptile}

[PeterDaveHello]

#20508 could be more complete than this one?