Qwen3-Open-Source
Copied!
Try AIAdd to Compare
ReasoningText Generation
Overview
ReasoningText Generation
Qwen3 hybrid reasoning model enables seamless switching between thinking and non-thinking modes during conversations. It achieves SOTA reasoning performance at its scale and significantly outperforms Qwen2.5-14B in general capabilities.
Input
Text
Output
Text
Features
Prefix Completion
Function Calling
Cache
Structured Outputs
Batches
Web Search
Pricing
- Input$0.35Per 1M tokens
- Output$1.4Per 1M tokens
- Input(Thinking)$0.35Per 1M tokens
- Output(Thinking)$4.2Per 1M tokens
Context
Context
131.07K
Max Input
98.30K
Max Output
8.19K
Rate Limits
- RPMRequests Per Minute600
- TPMTokens Per Minute1M
API Reference
Get API KeyCopied!
123456789101112131415161718192021222324252627282930