Delivers ultra-fast, high-resolution image generation, precise natural-language editing, and consistent multi-image output—ideal for creative, batch, or professional workflows.

State-of-the-art Mistral model trained specifically for code tasks.

A 7B sparse Mixture-of-Experts (SMoE). Uses 12.9B active parameters out of 45B total.

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.

A 7B transformer model, fast-deployed and easily customisable.

meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo

Powerful model for on-device use cases.

State-of-the-art Mistral model trained specifically for code tasks.

Version-capable small model.

Mixtral 8x22B is currently the most performant open model. A 22B sparse Mixture-of-Experts (SMoE). Uses only 39B active parameters out of 141B.

Cost-efficient, fast, and reliable option for use cases such as translation, summarization, and sentiment analysis.

Fast, Lightweight Model

Top-tier reasoning for high-complexity tasks, for your most sophisticated needs.

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.

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.

o1-preview is our new reasoning model for complex tasks. The model has 128K context and an October 2023 knowledge cutoff.

Most efficient edge model.