Qwen3.7 Max

Provider: Alibaba (Qwen) CN Official API price

Input price
$1.48
/ 1M tokens
Output price
$4.42
/ 1M tokens
Cache price
$0.29
/ 1M tokens (read)
Context
1M tokens
Max output 131K tokens

Overview

Alibaba's flagship Qwen3.7 Max is a reasoning model built for agent-centric workflows, coding, and productivity tasks. It has no free tier.

Strengths

  • 1,000,000 token context window
  • 131,072 token maximum output length
  • Native function calling and JSON mode support
  • Cached input priced at $0.295 per million tokens

Best use cases

  • Complex multi-step autonomous agent operations
  • Large-scale software codebase analysis and refactoring
  • Processing million-token documents with thinking capabilities

Pricing position

Priced at $1.475 input and $4.425 output per million tokens, aligning closely with GLM 5.3 while undercutting GPT-5 output costs.

Caveats

Significantly more expensive than Qwen3.7 Flash; evaluate simpler variants if reasoning and high output limits are unneeded.

Notes drafted by an LLM from the figures on this page (2026-11-12) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
131K tokens
Listed on OpenRouter
2026-05-21
Tracked since
2026-05-21
Last updated
2026-11-10

Features

Function callingJSON outputReasoning

Price history

  • 2026-05-21 Added

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.37
1M (small app) 1 0.5 $3.69
10M (mid scale) 10 5 $36.88
100M (large) 100 50 $368.75

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API (qwen/qwen3.7-max)