Qwen3.5 397B A17B
QwenReleased Feb 16, 2026
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...
- Context window
- 256K tokens
- Input
- text, image, video
- Output
- text
- Tokenizer
- Qwen3
- Released
- Feb 16, 2026
- Reasoning
- optional
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | $0.385 | $0.012 | $0.397 |
| Output | $2.45 | $0.073 | $2.52 |
Benchmarks
Artificial Analysis
- Intelligence index
- 33.7
- Coding index
- 48.2
- Agentic index
- 19.8
Design Arena
| Category | Elo | Win rate | Rank |
|---|---|---|---|
| 3Dmodels | 1238 | 56.7% | #33 |
| Codemodels | 1229 | 52.6% | #35 |
| Data vizmodels | 1219 | 53.2% | #38 |
| Game devmodels | 1206 | 50.1% | #44 |
| SVGmodels | 1199 | 56.1% | #30 |
| UI componentsmodels | 1218 | 51.4% | #42 |
| Websitesmodels | 1233 | 52.6% | #37 |
Head-to-head preference voting. How we filter and rank
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model qwen/qwen3.5-397b-a17b.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen3.5-397b-a17b",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="qwen/qwen3.5-397b-a17b",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "qwen/qwen3.5-397b-a17b",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Questions
- How much does Qwen3.5 397B A17B cost via API?
- Through OpenKey, Qwen3.5 397B A17B costs $0.397 per 1M input tokens and $2.52 per 1M output tokens. That is the provider price ($0.385 / $2.45) plus a flat 3% fee — nothing else.
- What is Qwen3.5 397B A17B's context window?
- Qwen3.5 397B A17B accepts up to 256K tokens of context.
- Is Qwen3.5 397B A17B OpenAI-compatible?
- Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "qwen/qwen3.5-397b-a17b" using any OpenAI SDK — only the base URL and API key change.
- What inputs does Qwen3.5 397B A17B support?
- Qwen3.5 397B A17B accepts text, image, video input and produces text output.
More from Qwen
All Qwen models →Qwen3.7 Plus
Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...
ctx 1Min $0.330out $1.32
Qwen3.7 Max
Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...
ctx 1Min $1.29out $3.86
Qwen3.5 Plus 2026-04-20
Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...
ctx 1Min $0.309out $1.85
Qwen3.6 27B
Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...
ctx 262Kin $0.294out $2.47