qwen3.5-397b-a17bAlibaba (Qwen)
- endpoints
- 4
- regions
- 1
- api
- chat
- released
- February 2026
capabilities 5/8
The same weights cost 1.7x more on nebius ai than on deepinfra inc.. That is what the endpoints table is for.
| # | flags | ||||||
|---|---|---|---|---|---|---|---|
| 1 |  DeepInfra Inc. | Global | 262K | $0.36 | $2.40 | $0.18 | zdr |
| 2 | DeepInfra Inc. | Global | 262K | $0.49 | $3.60 | $0.30 | zdr |
| 3 |  Nebius AI | Global | 128K | $0.60 | $3.60 | $0.60 | zdr |
| 4 |  Novita AI | Global | 262K | $0.60 | $3.60 | $0.60 | zdr |
no measured traffic for this model yet. the endpoints table above carries provider pricing
| eval | Score as a share of 100 | /100 |
|---|---|---|
| GPQA Diamond | 86.1 | |
| τ²-Bench | 83.9 | |
| Terminal-Bench Hard | 35.6 | |
| Intelligence Index | 21.4 | |
| Humanity's Last Exam | 19.8 | |
| 5 evals | mean | 49.4 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-02-16.
deepinfra/Qwen/Qwen3.5-397B-A17B:flexthis model has no managed policy yet, so call the provider endpoint directly. every id in the endpoints table works the same way
Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="deepinfra/Qwen/Qwen3.5-397B-A17B:flex", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models
The Qwen3.5 series 397B-A17B native vision-language model is based on a hybrid architecture design that integrates linear attention mechanisms with sparse Mixture-of-Experts (MoE), achieving higher inference efficiency. Across a variety of tasks—including language understanding, logical reasoning, code generation, agentic tasks, image understanding, video understanding, and graphical user interface (GUI) interaction—it demonstrates exceptional performance comparable to current top-tier frontier models. Possessing robust code generation and agentic capabilities, it exhibits strong generalization across various agent scenarios.
questions 5
Which providers serve qwen3.5-397b-a17b?
How much does qwen3.5-397b-a17b cost?
Is qwen3.5-397b-a17b open weights?
What is the context window of qwen3.5-397b-a17b?
How do I use qwen3.5-397b-a17b with the OpenAI SDK?
more from alibaba (qwen) 6
| model | context | from /M | providers |
|---|---|---|---|
| qwen3.8-2.4t-a95b | 1M | $2.50 | 1 |
| qwen3.8-flash-next | 262K | $0.20 | 1 |
| qwen3.8-flash | 1.0M | $0.16 | 1 |
| qwen3.8-max | 1.0M | $2.00 | 3 |
| qwen3.7-plus | 1.0M | $0.32 | 2 |
| qwen3.7-max | 1.0M | $2.50 | 1 |
route qwen3.5-397b-a17b through one endpoint
One key for 3 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology