Model

Qwen3.7 Max

Name: Qwen3.7 Max
Brand: alibaba

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

34 providers · 36 listingsreleased May 21, 2026closed weights

$0.825

lowest input /M · Merge Gateway

$2.48

lowest output /M · Merge Gateway

1.06M

context window

500K

max output

Compare providers (sorted by listed input price)

32 of 34 providers publish a price for Qwen3.7 Max. The cheapest full-context option is Merge Gateway at $0.825/$2.48 per M — 67% below Alibaba's own price. Listed prices span 3.9× for identical weights.

			Cache read /M	Cache write /M		Capabilities
Merge Gateway qwen/qwen3.7-max	$0.825	$2.48	$0.165	—	1M	reasoningtoolsstructuredno vision	May 21, 2026
LLM Gatewayvariant novita/qwen3.7-max	$1.25	$3.75	$0.25	—	1M	reasoningtoolsno structuredno vision	May 21, 2026
OrcaRouter qwen/qwen3.7-max	$1.25	$3.75	$0.25	$1.56	1M	reasoningtoolsno structuredno vision	May 21, 2026
NovitaAI qwen/qwen3.7-max	$1.25	$3.75	$0.25	$1.56	1M	reasoningtoolsstructuredno vision	May 27, 2026
Pioneer qwen3.7-max	$1.25	$3.75	$0.25	$1.56	991K	reasoningtoolsno structuredno vision	May 21, 2026
DevPass (LLM Gateway) qwen3.7-max	$1.25	$3.75	$0.25	$3.13	1M	reasoningtoolsno structuredno vision	May 21, 2026
Cloudflare AI Gateway alibaba/qwen3.7-max	$1.25	$3.75	$0.25	—	1M	reasoningtoolsno structuredno vision	May 21, 2026
Kilo Gateway qwen/qwen3.7-max	$1.25	$3.75	$0.125	$1.56	1M	reasoningtoolsstructuredno vision	May 21, 2026
Together AI Qwen/Qwen3.7-Max	$1.25	$3.75	$0.125	—	1M	no reasoningtoolsno structuredno vision	Jul 2, 2026
OpenRouter qwen/qwen3.7-max	$1.48	$4.42	$0.295	$1.84	1M	reasoningtoolsstructuredno vision	May 21, 2026
AIHubMix qwen3.7-max	$1.69	$5.07	$0.169	$2.11	991K	reasoningtoolsstructuredno vision	May 21, 2026
Ofoxvariant qwen/qwen3.7-max	$1.71	$5.14	$0.17	$2.14	1.06M	reasoningtoolsno structuredno vision	May 21, 2026
302.AI qwen3.7-max	$1.80	$5.30	—	—	1M	reasoningtoolsno structuredno vision	May 21, 2026
CrossModel qwen/qwen3.7-max	$1.88	$5.63	$0.375	$2.35	1M	reasoningtoolsstructuredno vision	May 21, 2026
NanoGPT qwen3.7-max	$2.50	$7.50	$0.5	$3.13	1M	reasoningtoolsno structuredno vision	May 21, 2026
Impossibl qwen/qwen3.7-max	$2.50	$7.50	$0.5	—	1M	reasoningtoolsno structuredno vision	May 21, 2026
LLM Gatewayvariant alibaba/qwen3.7-max	$2.50	$7.50	$0.5	$3.13	1M	reasoningtoolsno structuredno vision	May 21, 2026
Alibaba Coding Plan (China) qwen3.7-max	$2.50	$7.50	$0.5	$3.13	1M	reasoningtoolsno structuredno vision	May 21, 2026
Alibaba (China) qwen3.7-max	$2.50	$7.50	$0.5	$3.13	1M	reasoningtoolsno structuredno vision	May 21, 2026
Charm Hyper qwen3.7-max	$2.50	$7.50	$0.5	—	1M	reasoningtoolsno structuredno vision	Jul 22, 2026

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M: $0.825unchanged
Best output /M: $2.48unchanged
Provider coverage: 36; 32 at the start · 24 snapshots

Published best prices are unchanged.

24 daily snapshots collected from Aug 21, 2026 through Sep 14, 2026. A price chart will appear after the first real move.

Price badge

![Qwen3.7 Max price](https://www.vaanalytics.in/badge/alibaba/qwen3.7-max.svg)

https://www.vaanalytics.in/badge/alibaba/qwen3.7-max.svg

Live SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.

Recent changes

Changelog →

repricedvia ofox · Sep 13, 2026
- input: $2.50 → $1.71
- output: $7.50 → $5.14
- cache_read: $0.5 → $0.17
- cache_write: $3.13 → $2.14
new modelvia ofox · Sep 11, 2026
new modelvia 302ai · Sep 9, 2026
capabilityvia merge-gateway · Sep 5, 2026
- structured_output: false → true
repricedvia crossmodel · Aug 31, 2026
- input: $1.50 → $1.88
- output: $4.50 → $5.63
- cache_read: $0.3 → $0.375
- cache_write: $1.88 → $2.35
new modelvia orcarouter · Aug 28, 2026

Benchmarks

SWE-Bench Verified ↗(resolved)report ↗Unclassified source80.4
SWE-Bench Pro ↗(resolve rate)report ↗Unclassified source60.6
SWE-Bench Multilingual ↗(resolve rate)report ↗Unclassified source78.3
Terminal-Bench ↗(success rate)report ↗Unclassified source69.7
GPQA Diamond ↗(accuracy)report ↗Unclassified source92.4
Humanity's Last Exam ↗(accuracy)report ↗Unclassified source41.4
SciCode report ↗Unclassified source53.5
MCP Atlas(success rate)report ↗Unclassified source76.4
NL2Repo report ↗Unclassified source47.2

Scores a lab published about its own model are claims, not measurements. Rankings elsewhere on this site use independently measured scores only.

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.