Model specifications
- Context
- 1,048,576 tokens
- Maximum output
- 943,718 tokens
- Architecture
- text->text
- Tokenizer
- DeepSeek
- Knowledge cutoff
- Not provided
- Moderated
- No
Input → Output
No · max · high · low
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p16 providers
StreamLake
unknown- Context
- 1.0M
- Maximum output
- 384K
- Input
- $1.12
- Output
- $3.35
- Cache read
- $0.037
- Cache write
- Not provided
GMICloud
fp8- Context
- 1.0M
- Maximum output
- 944K
- Input
- $1.12
- Output
- $3.37
- Cache read
- $0.037
- Cache write
- Not provided
Alibaba
unknown- Context
- 1M
- Maximum output
- 393K
- Input
- $1.12
- Output
- $3.37
- Cache read
- $0.112
- Cache write
- Not provided
DeepInfra
fp8- Context
- 1.0M
- Maximum output
- 16K
- Input
- $1.30
- Output
- $2.60
- Cache read
- $0.100
- Cache write
- Not provided
CoreWeave
fp8- Context
- 1.0M
- Maximum output
- 944K
- Input
- $1.31
- Output
- $3.96
- Cache read
- $0.044
- Cache write
- Not provided
Sail Research
fp4- Context
- 1.0M
- Maximum output
- 384K
- Input
- $1.32
- Output
- $3.96
- Cache read
- $0.044
- Cache write
- Not provided
DeepSeek
unknown- Context
- 1.0M
- Maximum output
- 384K
- Input
- $1.32
- Output
- $3.96
- Cache read
- $0.044
- Cache write
- Not provided
Together
unknown- Context
- 1.0M
- Maximum output
- 944K
- Input
- $1.32
- Output
- $3.96
- Cache read
- $0.130
- Cache write
- Not provided
Novita
fp8- Context
- 1.0M
- Maximum output
- 393K
- Input
- $1.32
- Output
- $3.96
- Cache read
- $0.132
- Cache write
- Not provided
Parasail
fp8- Context
- 1.0M
- Maximum output
- 944K
- Input
- $1.32
- Output
- $3.96
- Cache read
- $0.044
- Cache write
- Not provided
SiliconFlow
fp8- Context
- 1.0M
- Maximum output
- 393K
- Input
- $1.32
- Output
- $3.96
- Cache read
- $0.440
- Cache write
- Not provided
BaseTen
fp4- Context
- 1.0M
- Maximum output
- 262K
- Input
- $1.32
- Output
- $3.96
- Cache read
- $0.132
- Cache write
- Not provided
DigitalOcean
unknown- Context
- 1.0M
- Maximum output
- 944K
- Input
- $1.32
- Output
- $3.96
- Cache read
- $0.044
- Cache write
- Not provided
Cloudflare
unknown- Context
- 1.0M
- Maximum output
- 944K
- Input
- $1.32
- Output
- $3.96
- Cache read
- $0.044
- Cache write
- Not provided
Fireworks
unknown- Context
- 1.0M
- Maximum output
- 944K
- Input
- $1.32
- Output
- $3.96
- Cache read
- $0.044
- Cache write
- Not provided
Phala
unknown- Context
- 1.0M
- Maximum output
- 393K
- Input
- $1.45
- Output
- $4.36
- Cache read
- $0.150
- Cache write
- Not provided