TheRouter.aiTheRouter.ai
Back to Models

Qwen3 30B Thinking

qwenqwen/qwen3-30b-thinking

Qwen3 30B Thinking — efficient reasoning model (MoE, 3B active) for cost-effective chain-of-thought.

Context Length
131K
Max Output
33K
Input Price
$0.168/ 1M tokens
Output Price
$0.504/ 1M tokens

Modalities

text→text

Pricing Breakdown

TypeRate
Input$0.168 / 1M tokens
Output$0.504 / 1M tokens

Supported Parameters

temperaturemax_tokenstop_pstop

API Usage Examples

cURL
curl https://api.therouter.ai/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "qwen/qwen3-30b-thinking",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'