TheRouter.aiTheRouter.ai
Back to Models

Qwen3 235B-A22B Thinking (2507)

qwenqwen/qwen3-235b-a22b-thinking-2507

Qwen3 235B-A22B MoE thinking model, July 2025 snapshot. Frontier reasoning for math, code, and agents.

Context Length
256K
Max Output
33K
Input Priceper 1M tokens
$0.2484/ 1M tokens
Output Priceper 1M tokens
$2.48/ 1M tokens

Modalities

text→text

Pricing Breakdown

TypeRate
Input$0.2484 / 1M tokens
Output$2.48 / 1M tokens

Supported Parameters

temperaturemax_tokenstop_ptoolstool_choiceresponse_formatstop

API Usage Examples

Use the global api.therouter.ai endpoint shown below for new integrations; the legacy China accelerated endpoint is retired.

cURL
curl https://api.therouter.ai/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "qwen/qwen3-235b-a22b-thinking-2507",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'
Help & contact