ModelScope logo

Qwen/Qwen3.5-397B-A17B Free API on ModelScope

Free API Verified
Available from ModelScope
★★★★★★★★★★ 3.5 Benchmark-backed score

Large open Qwen multimodal MoE for visual agents and long technical tasks

Free APIModelScope nativeReasoningTool callingJSON mode
Try in Playground Compare Save
Context window 8K
Max output 4K
API format ModelScope native
Status Online
AI Recommendation

Should you use Qwen/Qwen3.5-397B-A17B?

Qwen/Qwen3.5-397B-A17B is listed for chat workloads and supports a 8K context window.

Use it when ModelScope's free tier is enough for evaluation, demos, or light production traffic.

Best for
  • Chat
Strengths & Weaknesses

Strengths

  • Reasoning mode listed
  • Tool calling support
  • Structured JSON output
  • Open weights available

Watch outs

  • Vision support is not listed
Benchmark Overview

Benchmark signals for Qwen/Qwen3.5-397B-A17B

Measured data
Intelligence General reasoning and instruction following
33.7/100
Coding Programming and code generation
48.2/100
Agentic Tool use and multi-step tasks
19.8/100
Context Maximum listed context window
8K
Model Metadata

Qwen/Qwen3.5-397B-A17B model ID and technical details

Provider and model catalog
Model ID Qwen/Qwen3.5-397B-A17B
Family qwen
Released Feb 15, 2026
Last updated Jun 30, 2026
Free listing since Feb 16, 2026
Input text, image, video, audio
Output text
Capabilities reasoning, tool calling, structured output, file attachments, temperature control
Open weights Yes
Weights Hugging Face

External benchmark references

Benchmark Score Metric Date
SWE-Bench Verified 76.4 resolved Not listed
Availability

Qwen/Qwen3.5-397B-A17B availability by provider

2 alternatives

We found 3 provider listings for qwen3-5-397b-a17b. Check model ID, quota, pricing, and API format before switching providers.

Provider Model listing Access Context API Limits
ModelScope Qwen/Qwen3.5-397B-A17B Free tier 8K Native Varies
OVHcloud AI Endpoints Qwen3.5-397B-A17B Free tier 131K OpenAI-style 2 RPM (anonymous)
NVIDIA NIM qwen/qwen3.5-397b-a17b Free tier 256K OpenAI-style Up to 40 RPM
View ModelScope setup guide →
Typical Use Cases

Qwen/Qwen3.5-397B-A17B use cases

Chat

Qwen/Qwen3.5-397B-A17B is tagged for chat in this catalog.

FAQ

Qwen/Qwen3.5-397B-A17B free API FAQ

Is Qwen/Qwen3.5-397B-A17B free to use?

Qwen/Qwen3.5-397B-A17B is listed with free API access on ModelScope, subject to the provider's quota and account policy.

What is the Qwen/Qwen3.5-397B-A17B model ID?

The model ID shown in this catalog is Qwen/Qwen3.5-397B-A17B.

What context window does Qwen/Qwen3.5-397B-A17B support?

The listed context window is 8K tokens with up to 4K output tokens.

Related Models

Related free models similar to Qwen/Qwen3.5-397B-A17B

View all models
Qwen3.5-397B-A17B OVHcloud AI Endpoints · 131K · Free tier qwen/qwen3.5-397b-a17b NVIDIA NIM · 256K · Free tier Qwen/Qwen3.5-35B-A3B ModelScope · 131K · Free tier Qwen/Qwen3.5-27B ModelScope · 131K · Free tier Qwen/Qwen-Image ModelScope · 131K · Check provider deepseek-ai/DeepSeek-V3.2 ModelScope · 8K · Free tier

More about Qwen/Qwen3.5-397B-A17B

Qwen3.5 397B (17B active via MoE) is Alibaba's largest publicly-hosted model, free on NVIDIA NIM with up to 40 RPM and no daily token cap. The enormous expert pool at 397B total parameters brings frontier-level capability while 17B active parameters maintain manageable inference cost. OpenAI-compatible API. Requires NVIDIA Developer Program membership and phone verification.

For API keys, setup steps, and provider-level limits, see the ModelScope provider page.