Models

StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window

DeepSeek V4.1 Flash model for reasoning and agentic coding

A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.

Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work

Dense 27B vision-language model for coding, agent tasks, and image and video understanding

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows

Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.

Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Open MoE flagship with million-token context for coding and long agent runs

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

Open MiMo model for multimodal coding agents and long-context automation

Open Gemma instruction model for efficient chat and self-hosted deployments

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Multimodal model for analyzing text, images, documents, and rich media

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

DeepSeek chat model for instruction following, coding, and analysis

Thinking Kimi model for slower research passes, planning, and hard technical questions

Safety model for policy screening, moderation, and risk-aware routing workflows

September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding

Qwen instruction model for multilingual chat, reasoning, and tool use

Open GPT reasoning model for self-hosted agents and controllable deployments

Open GPT reasoning model for self-hosted agents and controllable deployments

Open Qwen coding heavyweight for repository reasoning and agentic engineering

Open audio-language model for speech transcription, audio understanding, and voice-driven tool use

Kimi model for long-context chat, coding, and agentic reasoning

DeepSeek chat model for instruction following, coding, and analysis

Cohere command model for multilingual enterprise agents, tools, and chat

Open multimodal Gemma instruction model for efficient text generation and image understanding

Open multimodal Gemma instruction model for multilingual text generation and image understanding

Largest open Gemma 3 instruction model for multilingual text generation and visual understanding

Open Llama instruction model for multilingual chat, reasoning, and coding

Cohere retrieval model for long-context chat and enterprise RAG workflows

Cohere retrieval model for long-context chat and enterprise RAG workflows

Cohere's RAG workhorse for long-context enterprise search and tool use

Open Llama instruction model for multilingual chat, reasoning, and coding

Mistral model for multilingual chat, reasoning, and tool-assisted workflows