Large open Qwen multimodal MoE for visual agents and long technical tasks
https://integrate.api.nvidia.com/v1 qwen/qwen3.5-397b-a17b | Benchmark | Score | Metric | Date |
|---|---|---|---|
| SWE-Bench Verified | 76.4 | resolved | Not listed |
qwen3.5-397b-a17b is listed for chat workloads and supports a 262K context window.
Check NVIDIA NIM's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
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 |
|---|---|---|---|---|---|
| | qwen/qwen3.5-397b-a17b | Check provider | 262K | OpenAI-style | Up to 40 RPM |
| | Qwen3.5-397B-A17B | Free tier | 131K | OpenAI-style | 2 RPM (anonymous) |
| | Qwen/Qwen3.5-397B-A17B | Free tier | 8K | Native | Varies |
| Model | Provider | Context | Access |
|---|---|---|---|
| Qwen3.5-397B-A17B | OVHcloud AI Endpoints | 131K | Free tier |
| Qwen/Qwen3.5-397B-A17B | ModelScope | 8K | Free tier |
| 01-ai/yi-large | NVIDIA NIM | 131K | Free tier |
| adept/fuyu-8b | NVIDIA NIM | 131K | Free tier |
| ai21labs/jamba-1.5-large-instruct | NVIDIA NIM | 131K | Free tier |
qwen3.5-397b-a17b is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
qwen3.5-397b-a17b appears in the free model catalog for NVIDIA NIM, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is qwen/qwen3.5-397b-a17b.
The listed free tier limit is Up to 40 RPM. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 262K tokens with up to 66K output tokens.
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 NVIDIA NIM provider page.