Back to Models

QwQ 32B

qwenqwen/qwq-32b

QwQ 32B — Qwen reasoning model with 32B dense parameters. Strong chain-of-thought reasoning with tool calling support.

Context Length
131K
Max Output
33K
Input Price
$0.264/ 1M tokens
Output Price
$1.02/ 1M tokens

Modalities

texttext

Pricing Breakdown

TypeRate
Input$0.264 / 1M tokens
Output$1.02 / 1M tokens

Supported Parameters

temperaturemax_tokenstop_ptoolstool_choicereasoningstop

API Usage Examples

China users: replace api.therouter.ai with api.therouter.com.cn in the examples below for lower latency.

cURL
curl https://api.therouter.ai/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "qwen/qwq-32b",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'