AI Recommendation
Should you use Qwen3.5-397B-A17B?
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.
Qwen3.5-397B-A17B Free API on ModelScope
Free API VerifiedLarge open Qwen multimodal MoE for visual agents and long technical tasks
Free APIOpenAI compatibleReasoningTool callingJSON mode
API Details
Copy-ready connection details
Base URL
https://api-inference.modelscope.cn/v1 Model ID
Qwen/Qwen3.5-397B-A17B API format OpenAI Chat Completions + OpenAI Responses
Technical Details
Qwen3.5-397B-A17B specifications
Context window 8K
Max output 4K
Status Online
Family qwen
Released Feb 15, 2026
Last updated Jul 7, 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 |
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 Qwen3.5-397B-A17B
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 Availability
Qwen3.5-397B-A17B availability by provider
We found 2 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 |
|---|---|---|---|---|---|
| | Qwen/Qwen3.5-397B-A17B | Free tier | 8K | Native | Varies |
| | Qwen3.5-397B-A17B | Free tier | 131K | OpenAI-style | 2 RPM (anonymous) |
Compare
Qwen3.5-397B-A17B alternatives to consider
| Model | Provider | Context | Access |
|---|---|---|---|
| Qwen3.5-397B-A17B | OVHcloud AI Endpoints | 131K | Free tier |
| Qwen/Qwen3.5-35B-A3B | ModelScope | 131K | Check provider |
| Qwen/Qwen3.5-27B | ModelScope | 131K | Check provider |
| MiniMax-M2.5-highspeed | ModelScope | 205K | Check provider |
| Kimi K2.5 | ModelScope | 262K | Check provider |
Typical Use Cases
Qwen3.5-397B-A17B use cases
Chat
Qwen3.5-397B-A17B is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
FAQ
Qwen3.5-397B-A17B free API FAQ
Is Qwen3.5-397B-A17B free to use?
Qwen3.5-397B-A17B is listed with free API access on ModelScope, subject to the provider's quota and account policy.
What is the Qwen3.5-397B-A17B model ID?
The model ID shown in this catalog is Qwen/Qwen3.5-397B-A17B.
What context window does Qwen3.5-397B-A17B support?
The listed context window is 8K tokens with up to 4K output tokens.
More about 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.