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.
76 models, on 10 inference providers. New models added every week.
Anthropic AI
DeepSeek
Google
Meta
Mistral AI
Nous Research
OpenAI
Perplexity
QwenShow allDeepseek V3
Mar 2025
texttext
Features a 671B-parameter Mixture-of-Experts architecture, excelling at advanced reasoning, code, and multilingual tasks with a 128K context window[1][3][6].
Inference by DeepSeekInput: $0.27 / Output: $1.10
Deepseek R1 (FP8)
Jan 2025
texttext
Efficient reasoning model using dynamic expert routing and chain-of-thought processing for complex tasks like math and coding.
Inference by Together.aiInput: $7.00 / Output: $7.00
Deepseek R1
Jan 2025
texttext
Specializes in logical inference and mathematical problem-solving with chain-of-thought reasoning, using a Mixture of Experts architecture for efficient computation.
Inference by Fireworks AIInput: $3.00 / Output: $8.00
Deepseek R1
Jan 2025
texttext
Reasoning-focused model excelling at complex problem-solving, math, and code with self-correction, cost efficiency, and open-source transparency.
Inference by DeepSeekInput: $0.55 / Output: $2.19
Deepseek V3 (FP8)
Dec 2024
texttext
Efficient Mixture-of-Experts model optimized for complex reasoning, code generation, and multilingual tasks with scalable 128K context processing.
Inference by Together.aiInput: $1.25 / Output: $1.25
Deepseek V3
Dec 2024
texttext
Efficient Mixture-of-Experts model with 37B active parameters per token, excelling in coding, math, and reasoning tasks while maintaining 128K token context length.
Inference by Fireworks AIInput: $0.75 / Output: $3.00
Deepseek R1 Distill Llama 70B
texttext
Specializes in complex problem-solving with step-by-step reasoning, excelling in math and coding tasks through chain-of-thought processing.
Inference by GroqInput: $0.59 / Output: $0.79