Models / Qwen3.5 397B A17B

Qwen3.5 397B A17B

Name: Qwen3.5 397B A17B
Brand: qwen3.5
Price: 0.35 USD
Availability: InStock

Qwen Tier 1Apache-2.0

Flagship open-weight MoE model. 397B total parameters with 17B active per forward pass. Hybrid-Attention architecture with 262K context.

qwen/qwen3.5-397b-a17b

Context Window

262K

Max Output

33K

Providers

Released

2026-02

Capabilities

chatcodevisionreasoningthinkingtoolsfunction_callingstreamingjson_mode

Pricing by Provider

Provider	Input $/1M	Output $/1M	Latency p50	Latency p95
deepinfra	$0.35	$2.10	480ms	1300ms
alibaba	$0.39	$2.34	450ms	1200ms
together	$0.42	$2.50	520ms	1400ms

Quick Start

Python

import magicrouter

mr = magicrouter.Client(
    provider_keys={"deepinfra": "your-api-key"}
)

response = mr.chat(
    "qwen/qwen3.5-397b-a17b",
    "Your prompt here"
)
print(response.choices[0].message.content)

TypeScript

import { MagicRouter } from "magicrouter";

const mr = new MagicRouter({
  providerKeys: { deepinfra: "your-api-key" }
});

const response = await mr.chat({
  model: "qwen/qwen3.5-397b-a17b",
  messages: [{ role: "user", content: "Your prompt here" }]
});
console.log(response.choices[0].message.content);

cURL

curl https://api.deepinfra.com/v1/openai/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3.5-397B-A17B",
    "messages": [{"role": "user", "content": "Your prompt here"}]
  }'

Use this model

Get Started