WizardLM-2 8x22B

Phi 4 Mini

Phi 4 Mini by Microsoft. A small multilingual model.

Phi 4 Multimodal

Phi 4 by Microsoft. A small multimodal model that can handle images and text.

Mixtral 8x22B

Mixtral 8x22B is a powerful sparse Mixture of Experts (MoE) model with 141B total parameters and 39B active per token. Features a 64K context window, exceptional math performance, and cost-efficient inference. Supports English, French, German, Spanish, and Italian. Apache 2.0 licensed.

Clef

Cloudflare's open decision model evaluates application state and answers typed Choice, Score and Noul questions. Use /v1/decisions or /v1/systemone, or a questions response format through Chat Completions, Messages or Responses. It supports 16K tokens of text context and generates no text tokens; only input tokens are billed.

Sakana Namazu

Sakana AI's Japanese-specialized model, based on Kimi K2.6 and tuned for Japanese language, culture, and business contexts. Supports reasoning, image understanding, function calling, and structured output.

Liquid D1

Liquid AI's D1 evaluates application state and returns typed Choice, Score and yes/no answers with calibrated probabilities. Use /v1/decisions or /v1/systemone, or a questions response format through Chat Completions, Messages or Responses. It supports a 65,536-token context and generates no text tokens; only input tokens are billed.