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.
16 models, on 4 inference providers. New models added every week.
MMetaOOthersShow all
?o1-mini
texttext
o1-mini is a fast, cost-efficient reasoning model tailored to coding, math, and science use cases. The model has 128K context and an October 2023 knowledge cutoff.
Inference by OpenAIInput: $3.00 / Output: $12.00
?gpt-4o
texttext
GPT-4o is our most advanced multimodal model that’s faster and cheaper than GPT-4 Turbo with stronger vision capabilities. The model has 128K context and an October 2023 knowledge cutoff.
Inference by OpenAIInput: $2.50 / Output: $10.00
?gpt-4o-mini
texttext
GPT-4o mini is our most cost-efficient small model that’s smarter and cheaper than GPT-3.5 Turbo, and has vision capabilities. The model has 128K context and an October 2023 knowledge cutoff.
Inference by OpenAIInput: $0.15 / Output: $0.60
?o1-preview
texttext
o1-preview is our new reasoning model for complex tasks. The model has 128K context and an October 2023 knowledge cutoff.
Inference by OpenAIInput: $15.00 / Output: $60.00
?mistral-large-2407
texttext
Top-tier reasoning for high-complexity tasks, for your most sophisticated needs.
Inference by Mistral AIInput: $2.00 / Output: $6.00
?mistral-small-2409
texttext
Cost-efficient, fast, and reliable option for use cases such as translation, summarization, and sentiment analysis.
Inference by Mistral AIInput: $0.20 / Output: $0.60
?codestral-2405
texttext
State-of-the-art Mistral model trained specifically for code tasks.
Inference by Mistral AIInput: $0.20 / Output: $0.60
?ministral-3b-latest
texttext
Most efficient edge model.
Inference by Mistral AIInput: $0.04 / Output: $0.04
?ministral-8b-latest
texttext
Powerful model for on-device use cases.
Inference by Mistral AIInput: $0.10 / Output: $0.10
?pixtral-12b
texttext
Version-capable small model.
Inference by Mistral AIInput: $0.15 / Output: $0.15
?mistral-nemo
texttext
State-of-the-art Mistral model trained specifically for code tasks.
Inference by Mistral AIInput: $0.15 / Output: $0.15
?open-mistral-7b
texttext
A 7B transformer model, fast-deployed and easily customisable.
Inference by Mistral AIInput: $0.25 / Output: $0.25
?open-mixtral-8x7b
texttext
A 7B sparse Mixture-of-Experts (SMoE). Uses 12.9B active parameters out of 45B total.
Inference by Mistral AIInput: $0.70 / Output: $0.70
?open-mixtral-8x22b
texttext
Mixtral 8x22B is currently the most performant open model. A 22B sparse Mixture-of-Experts (SMoE). Uses only 39B active parameters out of 141B.
Inference by Mistral AIInput: $2.00 / Output: $6.00
?Gemini 1.5 Flash
texttexttextembeddings
Fast, Lightweight Model
Inference by GoogleInput: $0.02 / Output: $0.02
Mmeta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
texttext
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
Inference by Together.aiInput: $0.18 / Output: $0.18