feat: add dashscope/qwen3-max model with tiered pricing

[looksgood]

Add support for Alibaba Cloud's Qwen3-Max model with:

• 258K input tokens, 65K output tokens
• Tiered pricing based on context window usage (0-32K, 32K-128K, 128K-252K)
• Function calling and tool choice support
• Reasoning capabilities enabled

Relevant issues

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
🐛 Bug Fix
🧹 Refactoring
📖 Documentation
🚄 Infrastructure
✅ 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 11, 2026 2:37am

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[greptile-apps]

Greptile Overview

Greptile Summary

Adds the dashscope/qwen3-max model entry to both pricing JSON files with tiered pricing (3 tiers: 0-32K, 32K-128K, 128K-252K), 258K input / 65K output token limits, and support for function calling, tool choice, and reasoning. The configuration is identical to the existing dashscope/qwen3-max-preview entry, suggesting this promotes the preview model to a stable release alias.

• No tests included — the PR checklist and AGENTS.md require at least one test in tests/litellm/
• Both JSON files are kept in sync

Confidence Score: 4/5

• This PR is safe to merge — it only adds a new model entry to JSON config files with no code logic changes.
• Config-only change that adds a new model entry following the exact same pattern as the existing dashscope/qwen3-max-preview. Both files are in sync. No code logic is affected. Minor deduction for missing tests per repository policy.
• No files require special attention.

Important Files Changed

Filename	Overview
model_prices_and_context_window.json	Adds dashscope/qwen3-max model entry with tiered pricing, identical configuration to existing dashscope/qwen3-max-preview. Structure follows established patterns correctly.
litellm/model_prices_and_context_window_backup.json	Backup file mirrors the same dashscope/qwen3-max entry added in the primary JSON file. Both files are in sync.

[greptile-apps]

_{2 files reviewed, no comments}

_{Edit Code Review Agent Settings | Greptile}

[ishaan-jaff]

lgtm