Back to Models

Qwen3 8B

qwenqwen/qwen3-8b

Qwen3 8B — compact and fast, ideal for lightweight tasks and high-throughput scenarios.

Context Length
131K
Max Output
33K
Input Price
$0.036/ 1M tokens
Output Price
$0.072/ 1M tokens

Modalities

texttext

Pricing Breakdown

TypeRate
Input$0.036 / 1M tokens
Output$0.072 / 1M tokens

Supported Parameters

temperaturemax_tokenstop_ptoolstool_choiceresponse_formatstop

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/qwen3-8b",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'