Models/Deepseek R1 (FP8)
DeepSeekDeepSeek / Deepseek R1 (FP8)
Released: 1/20/2025
texttext
Input: $7.00 / Output: $7.00

Deepseek R1 is an LLM that excels in step-by-step reasoning, code generation, and numerical problem solving, enabled by its reinforcement learning fine-tuning, chain-of-thought capabilities, and efficient Mixture of Experts architecture.

Some other noteworthy features of Deepseek R1 include its ability to produce structured and transparent responses, and its use of FP8 mixed precision and Multihead Latent Attention to optimize inference speed and resource use.

MetricValue
Parameter Count671 billion
Mixture of ExpertsYes
Active Parameter Count37 billion
Context LengthUnknown
MultilingualUnknown
Quantized*Yes
Precision*FP8

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.

DeepSeek models available on Oxen.ai
ModalityPrice (1M tokens)
ModelInference providerInputOutputInputOutput
Fireworks AIFireworks AI
texttext$3.00$8.00
DeepSeekDeepSeek
texttext$0.55$2.19
Together.aiTogether.ai
texttext$7.00$7.00
GroqGroq
texttext$0.59$0.79
DeepSeekDeepSeek
texttext$0.27$1.10
Fireworks AIFireworks AI
texttext$0.75$3.00
Together.aiTogether.ai
texttext$1.25$1.25
See all models available on Oxen.ai