Qwen3.7 Max Thinking
NanoGPT
Qwen3.7 Max Thinking by NanoGPT costs $2.50 per 1M input tokens and $7.50 per 1M output tokens, with a 1M-token context window.
Pricing
Input (per 1M tokens)
$2.50
Output (per 1M tokens)
$7.50
Cached input (per 1M)
$0.25
Specifications
- Provider
- NanoGPT
- Context window
- 1M tokens
- Parameters
- —
- Released
- May 2026
- Open weights
- No
- Frontier model
- No
Benchmarks
- LiveBench
- 75.2
Compare Qwen3.7 Max Thinking with…
Qwen3.7 Max Thinking vs Qwen3-Coder 480B-A35B Instruct$7.50/1MQwen3.7 Max Thinking vs Mistral Medium 3.5$7.50/1MQwen3.7 Max Thinking vs Mistral Medium (latest)$7.50/1MQwen3.7 Max Thinking vs GLM-4 Plus$7.50/1MQwen3.7 Max Thinking vs Qwen3.6 Max Preview$7.80/1MQwen3.7 Max Thinking vs Kimi K2 Thinking Turbo$8.00/1M
FAQ
How much does Qwen3.7 Max Thinking cost?
Qwen3.7 Max Thinking is priced at $2.50 per 1M input tokens and $7.50 per 1M output tokens. Output tokens cost more than input.
What is Qwen3.7 Max Thinking's context window?
Qwen3.7 Max Thinking supports a context window of 1M tokens — the maximum prompt plus response length it can handle in a single request.
Is Qwen3.7 Max Thinking open weight?
No — Qwen3.7 Max Thinking is a closed/proprietary model accessed via API.
Data as of 2026-06-28. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.