qwen3-max-thinking
Explore qwen3-max-thinking: model specifications, capabilities, benchmark results, platform pricing and original sources.
cheaperInference/qwen3-max-thinking
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 256000
- Max output · tokens
- 65536
- Capabilities
- reasoning, structuredOutputs, toolCalling
Provider specifications & access
1–1 / 1
- source model id
- qwen3-max-thinking
- hosting
- gateway
- context length
- 256000
- max output tokens
- 65536
- capabilities
- reasoning
- structuredOutputs
- toolCalling
Explore more models