Skip to content

Qwen3 235B A22B (Instruct 2507)

Tools
qwen/qwen3-235b-a22b

Text · 262K context · Jul 2025 · 8 upstreams

Qwen3 235B A22B (Instruct 2507) is Qwen's open-weight, non-thinking Mixture-of-Experts model with 235B total and 22B active parameters. It is licensed Apache-2.0 and covers 119 languages and dialects, coding and tool use.

Needs your own keyTo use Qwen3 235B A22B (Instruct 2507), add a key from AIHubMix, OpenRouter, Nous Research or 5 more. AnyRouter adds no fee.
context
262K
input / 1M (list)
$0.09
output / 1M (list)
$0.35
routes
8
speed, 24h
No data yet

Upstreams

8
  1. 1AIHubMixYour keynot addedBilled to your key
  2. 2OpenRouterYour keynot addedBilled to your key
  3. 3Nous ResearchYour keynot addedBilled to your key
  4. 4InfronYour keynot addedBilled to your key
  5. 5NanoGPTYour keynot addedBilled to your key
  6. 6FluenceYour keynot addedBilled to your key
  7. 7QiniuYour keynot addedBilled to your key
  8. 8RequestyYour keynot addedBilled to your key

Benchmarks

GPQA Diamond
70.7%

Benchmark data from Epoch AI (CC-BY 4.0).

Quick start

curl
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "qwen/qwen3-235b-a22b",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'

Details

Owner
Qwen
Kind
Chat
Released
Jul 2025
Context
262K
Data policy
Provider retention
Endpoint
/api/v1/chat/completions