Qwen3.7 Max

qwen/qwen3.7-max-20260520

Qwen: Qwen3.7 Max, from provider Qwen, processes text input and generates text output. It supports tools, reasoning, and a context length of 1,000,000 tokens. The model is not open weights, costs $1.475 per million input tokens and $4.425 per million output tokens, and was released on August 26 2025.

  • tool use
  • structured outputs
  • reasoning

At a glance

providerqwen
releasedAug 26, 2025
context1M
input / M$1.48

Specifications

What the API gives you

Context window
1M tokens
Max output
66K tokens
Input price
$1.48 / 1M tokens
Output price
$4.42 / 1M tokens
Cache read
$0.29 / 1M tokens
Modalities
text → text
Knowledge cutoff
Released
Aug 26, 2025

Recommendation coverage

Where this model appears

  1. #6Best LLM for Roleplay & Character
  2. #7Best LLM for Competition Math
  3. #7Best LLM for Literary Translation

Measured evidence

Public benchmark record

LMArena Agent
-0.82026-07-13
LMArena Agent
0.32026-07-20
LMArena Text
1476 Elo2026-07-16
LMArena Text
1485 Elo2026-07-20
LMArena WebDev
1516 Elo2026-07-16
LMArena WebDev
1516 Elo2026-07-20

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.