Skip to content
OpenKey

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...

Try in playground
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 tokensProvider+ 3% feeYou 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

CategoryEloWin rateRank
3Dmodels123856.7%#33
Codemodels122952.6%#35
Data vizmodels121953.2%#38
Game devmodels120650.1%#44
SVGmodels119956.1%#30
UI componentsmodels121851.4%#42
Websitesmodels123352.6%#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.

Code sample language
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 →