Model specifications
- Context
- 262,144 tokens
- Maximum output
- 131,072 tokens
- Architecture
- text+image+video->text
- Tokenizer
- Other
- Knowledge cutoff
- Not provided
- Moderated
- No
Input → Output
No · high · medium · low
Supported API parameters
frequency_penaltyinclude_reasoningmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_p1 Provider
Seed
fp8- Context
- 262K
- Maximum output
- 131K
- Input
- $0.500
- Output
- $3.00
- Cache read
- Not provided
- Cache write
- Not provided