Velokey

Qwen3.7 Max

阿里巴巴Chatin 2 · out 6 Credits / 1M tokens≈$2 / $6Available
Get API keyAPI docs

Qwen3.7-Max is Alibaba's flagship agent model for long-horizon coding, MCP orchestration, and hours-long autonomy, with a 1M-token context. Access it through Velokey's unified endpoint with below-list pricing.

1M-token contextFlagship coding agentHours-long autonomyMCP tool orchestration

Use cases

End-to-end coding agent · Whole-codebase engineering

Input

Text

Output

Text

Billing

Per token

Model Type:
0.7
02
2048
2568192
qwen3.7-max

Start a conversation

Type a message below to begin

Sign up to get $0.5 in free credits — about 20 free images

Pricing details

Transparent usage-based pricing with no hidden fees.

Detailed Pricing

Usage-based pricing breakdown

SpecPriceOfficialSavings
Input/1M tokens2 Credits≈$22.5 Credits-20%
Output/1M tokens6 Credits≈$67.5 Credits-20%
Cache Read/1M tokens0.2 Credits≈$0.20.25 Credits-20%
Cache Write/1M tokens2.5 Credits≈$2.53.13 Credits-20%

Billing Rules

  • Output price varies by model, resolution, quality, duration, or token usage.
  • Uploaded reference files may be charged separately when supported.
  • Add-on capabilities such as web search or image search may be billed per request.
  • Token-based models are billed by input and output tokens.
  • If the primary route is unavailable, Velokey may automatically switch to a stable fallback route when possible.
  • Usage is pay-as-you-go with transparent credit deduction.

* Final cost depends on the generated result.

Related models

Explore other models in the same family.

Affordable Qwen3.7-Max API

Access Alibaba's Qwen3.7-Max on Velokey — a flagship coding agent, a 1M-token context, hours-long long-horizon autonomy, and MCP tool orchestration, with a unified endpoint and below-list pricing for production agent apps.

Meet Qwen3.7-Max and its API access

Qwen3.7-Max is Alibaba's flagship proprietary model, launched May 20, 2026 at the Alibaba Cloud Summit and built for the agent era: long-horizon coding workflows, MCP tool orchestration, and autonomous task execution over hours (not seconds). Its context window grows from 262K on Qwen3.6-Max-Preview to 1 million tokens (roughly 2,000 pages), big enough to load most enterprise codebases without retrieval scaffolding; as a coding agent it excels from frontend prototyping to complex multi-file engineering. It is a text-only model, with a multimodal counterpart, Qwen3.7-Plus. Velokey provides an affordable, easy-to-integrate Qwen3.7-Max API: a unified chat endpoint, a clear request flow, and below-list pricing for production systems, agent pipelines, and automation tools.

Flagship agentic coding (frontend to multi-file)

Excels from frontend prototyping to complex multi-file engineering as a flagship coding agent that ships full applications end to end. Coding benchmarks: SWE-Pro 60.6, SWE-Multilingual 78.3, SciCode 53.5, QwenSVG 1608.

View Documentation →
Flagship agentic coding (frontend to multi-file)

1M-token context

The context window grows from 262K on Qwen3.6-Max-Preview to 1 million tokens (roughly 2,000 pages), big enough to load most enterprise codebases without retrieval scaffolding and reason over the whole repository.

View Documentation →
1M-token context

35-hour long-horizon execution

Sustains coherent reasoning across extremely long horizons — demonstrated by a 35-hour, fully autonomous kernel-optimization run comprising over 1,000 tool calls, pushing tasks from seconds to hours.

View Documentation →
35-hour long-horizon execution

MCP tool orchestration

Natively strong at MCP tool orchestration, coordinating many connected tool modules across long autonomous runs to keep complex workflows running as one coherent system.

View Documentation →
MCP tool orchestration

How to deploy the Qwen3.7-Max API on Velokey

Get started with just a few steps.

1

Sign up and get an API Key

Sign in to the Velokey console to generate an API Key that authenticates every request sent to Qwen3.7-Max.

2

Configure request parameters

Set model to qwen-3-7-max and submit messages. Use the full 1M-token window for very long context and attach MCP tools to power long-horizon autonomous execution.

3

Integrate and start calling

Send requests to Velokey's unified /v1/chat/completions endpoint to power coding agents and automation, with usage managed in one console.

Real-world use cases for Qwen3.7-Max

From engineering to enterprise agents, covering many high-autonomy scenarios.

End-to-end coding agent

From frontend prototyping to complex multi-file engineering, ships full applications end to end as a flagship coding agent.

Whole-codebase engineering

With a 1M-token context, load an entire enterprise codebase for development and refactoring without retrieval scaffolding.

Long-horizon autonomous tasks

Sustains coherent reasoning over hours-long horizons, fit for autonomous tasks with over 1,000 tool calls.

MCP tool orchestration

Coordinates many connected tool modules, keeping complex multi-tool workflows orchestrated as one coherent system.

Scientific & kernel-level optimization

Fit for SciCode-style scientific coding and kernel-level optimization that demand long-horizon reasoning and repeated iteration.

Autonomous DevOps & automation

Hours-long autonomous execution with tool orchestration, fit for long-horizon DevOps, batch processing, and automation pipelines.

Why choose Velokey for Qwen3.7-Max

Discount on list price

Call Qwen3.7-Max at a lower price on Velokey — pay-as-you-go with no forced subscription, reducing upfront cost.

Unified API interface

One API Key accesses Qwen3.7-Max and other models — no juggling multiple accounts and keys, simplifying integration.

Complete docs and migration guidance

Endpoint references, parameter details, and migration examples help you upgrade smoothly from Qwen3.6-Max-Preview and adopt the 1M-token context and MCP tools.

Stable and highly available

Automatic failover and stable fallback routes maintain availability when the primary route is down, keeping long-horizon agent tasks reliable.

API Reference

Complete API call examples and parameter descriptions

Endpoint

https://api.velokey.ai/v1/chat/completions

Authentication

Bearer YOUR_API_KEY

Request Example

curl https://api.velokey.ai/v1/chat/completions \
  -X POST \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.7-max",
    "messages": [{"role": "user", "content": "Hello!"}],
    "temperature": 0.7
  }'

Response Example

{
  "id": "req_abc123",
  "model": "qwen3.7-max",
  "created": 1234567890,
  "data": { ... }
}

Qwen3.7-Max API FAQ

What is Qwen3.7-Max?

It is Alibaba's flagship proprietary model, launched May 20, 2026 at the Alibaba Cloud Summit and built for the agent era — long-horizon coding workflows, MCP tool orchestration, and autonomous task execution over hours. It is a text-only model (a multimodal counterpart, Qwen3.7-Plus, exists).

How does the 1M-token context work?

The context window grows from 262K on Qwen3.6-Max-Preview to 1 million tokens (roughly 2,000 pages), big enough to load most enterprise codebases without retrieval scaffolding and reason over the whole repository directly.

How good is long-horizon execution?

It sustains coherent reasoning across extremely long horizons — demonstrated by a 35-hour, fully autonomous kernel-optimization run comprising over 1,000 tool calls.

How does it do on coding benchmarks?

Coding-agent benchmarks are SWE-Pro 60.6, SWE-Multilingual 78.3, SciCode 53.5, and QwenSVG 1608, spanning frontend prototyping to complex multi-file engineering.

How is it billed on Velokey?

This page's pricing area shows the current Velokey price, billed by input and output tokens with a discount on list price. One API Key gives you unified access.

Start building with Qwen3.7 Max today

Use one API key to access low-cost, stable AI models through Velokey.

Get API KeyView Docs