QwQ 32B
Qwen's QwQ reasoning model. Specialized for math, logic, and step-by-step problem solving.
Model highlights
- Specialized reasoning
- Advanced math
- Logic problems
- Step-by-step solving
- Cost-efficient
- Modalities
- IntextOuttext
- Input / output
- $0.29 / $0.59USD per 1M tokens
- Context
- 32K
- Providers
- Live
- Released
- Mar 5, 2025
Playground
Preparing playground
API
POST/api/v1/chat/completionsOpenAI-compatible
qwq-32b
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwq-32b",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingresponse_formatreasoningreasoning_effort
Pricing
- Input
- $0.29/M tokens
- Cached input
- $0.029/M tokens
- Output
- $0.59/M tokens
Published USD rates. Actual cost depends on input, output, cache usage and request options.
