Model specifications
- Context
- 500,000 tokens
- Maximum output
- 450,000 tokens
- Architecture
- text+image+file->text
- Tokenizer
- Grok
- Knowledge cutoff
- Not provided
- Moderated
- No
Input → Output
Yes · xhigh · high · medium · low
Supported API parameters
include_reasoninglogprobsmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p5 providers
xAI
unknown- Context
- 500K
- Maximum output
- 450K
- Input
- $2.00
- Output
- $6.00
- Cache read
- $0.500
- Cache write
- Not provided
xAI
unknown- Context
- 500K
- Maximum output
- 450K
- Input
- $4.00
- Output
- $12.00
- Cache read
- $1.00
- Cache write
- Not provided
xAI
unknown- Context
- 500K
- Maximum output
- 450K
- Input
- $2.00
- Output
- $6.00
- Cache read
- $0.500
- Cache write
- Not provided
xAI
unknown- Context
- 500K
- Maximum output
- 450K
- Input
- $4.00
- Output
- $12.00
- Cache read
- $1.00
- Cache write
- Not provided
Amazon Bedrock
unknown- Context
- 500K
- Maximum output
- 450K
- Input
- $2.20
- Output
- $6.60
- Cache read
- $0.550
- Cache write
- Free