Skip to main content

Qwen3.7 Max 2026-05-20

Qwen3.7 Max 2026-05-20.

Input / output price
$2.50 / $7.50 per 1M
Released
May 20, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "qwen/qwen3.7-max-2026-05-20".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Qwenqwen/qwen3.7-max-2026-05-20
$2.50/M$7.50/M

Pricing

USD per 1M tokens on Qwen, after gateway discounts.

Input
$2.50 per 1M
Output
$7.50 per 1M
Cache read
$0.50 per 1M
Cache write
$3.125 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$2.50/MQwen

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

47tokens/sacross providers

Faster than 63% of the other 599 models on the gateway

Response latency

Lower is better

4.0sacross providers

Faster than 36% of the other 780 models on the gateway

Benchmarks

The Respan Index plus 19 published scores from 4 sources, each linked to where it was published.

43.1/ 100

Respan Index#63 of 176

176 ranked models. The shaded band is this model's 95% interval, 36.4 to 52.7. GLM-5.2 and Muse Spark Open fall inside it, so the gap is within the margin of error.
Qwen3.7 Max 2026-05-20 by category: Coding 16.7, Agents 52.7, Reasoning 48.6, Knowledge & language 55.0, Human preference 54.0
  1. 63Qwen3.7-Max43.1
  2. 62GLM-5.243.4
  3. 64Muse Spark Open42.8

Published scores

BenchmarkScore
SWE-bench VerifiedEpoch AI77.3%
LiveBench CodingLiveBench74.2%

Compare Qwen3.7 Max 2026-05-20: Qwen3.7-Max vs Qwen3-Max, Qwen3.7-Max vs Qwen3.8-Max, Qwen3.7-Max vs Qwen3.8-Flash-Next, Qwen3.7-Max vs Qwen3.8 27B, Qwen3.7-Max vs Qwen3.6-Max-Preview, Qwen3.7-Max vs Qwen3.7-Plus

Apps

Use Qwen3.7 Max 2026-05-20 in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Qwen3.7 Max 2026-05-20 FAQ

Short answers, built from the data on this page.

Qwen3.7 Max 2026-05-20 is a model from Qwen, released on May 20, 2026. Qwen3.7 Max 2026-05-20.

On the Respan gateway, Qwen3.7 Max 2026-05-20 costs $2.50 per 1M input tokens and $7.50 per 1M output tokens on Qwen, after gateway discounts.

Qwen3.7 Max 2026-05-20 is served by Qwen.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "qwen/qwen3.7-max-2026-05-20". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Qwen3.7 Max 2026-05-20 scores 43.1 out of 100 on the Respan Index v1.1, ranking #63 of 176 models. By category: Coding 16.7, Agents 52.7, Reasoning 48.6, Knowledge & language 55.0, and Human preference 54.0. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Qwen3.7 Max 2026-05-20 has 19 published benchmark scores, including SWE-bench Verified 77.3%, LiveBench Agentic Coding 43.6%, and GPQA Diamond 90.9%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.