Run Models on Your Data
Choose the right model, get to the perfect prompt, kick off the data flywheel.
Oxen makes it easy to improve your use of state of the art AI.
57 models, on 7 inference providers. New models added every week.
DeepSeek
Google
Meta
Mistral AI
Nous Research
OpenAI
QwenShow allDeepseek R1 (FP8)
Jan 2025
texttext
DeepSeek-R1 is an advanced large language model (LLM) that achieves performance comparable to OpenAI's o1 across math, code, and reasoning tasks.
Inference by Together.aiInput: $7.00 / Output: $7.00
Deepseek R1
Jan 2025
texttext
DeepSeek R1 demonstrates emergent behaviors like chain-of-thought reasoning, self-verification, and error correction.
Inference by Fireworks AIInput: $3.00 / Output: $8.00
Deepseek V3 (FP8)
Dec 2024
texttext
DeepSeek-V3 is a 671B parameter Mixture-of-Experts (MoE) language model with 37B active parameters per token
Inference by Together.aiInput: $1.25 / Output: $1.25
Deepseek V3
Dec 2024
texttext
DeepSeek V3 is a state-of-the-art open-source large language model (LLM) with 671 billion parameters, of which 37 billion are activated per token.
Inference by Fireworks AIInput: $0.90 / Output: $0.90
Deepseek R1 Distill Llama 70B
texttext
R1's reasoning capability distilled into the smaller Llama 3.3 70B for faster and cheaper inference.
Inference by GroqInput: $0.59 / Output: $0.79