Models

Efficient Indian-language reasoning model for chat, coding, and multilingual work

Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use

StepFun flash lane for quick multimodal reasoning and coding assistance

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

MiMo flash model for fast multimodal assistance and agent workflows

Small Nemotron 3 MoE for efficient coding, math, and long-context agents

Compact multimodal Mistral model for local assistants, edge agents, and efficient tool use

Open vision-language model for efficient local deployment, instruction following, and tool use

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

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

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

Qwen vision-language thinking model for visual reasoning, documents, and agent tasks

Qwen vision-language instruct model for visual reasoning, documents, and agent tasks

DeepSeek chat model for instruction following, coding, and analysis

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

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

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

Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents

Open hybrid-attention MoE reasoning model with a million-token context and an 80K thinking budget

May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

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

Efficient model for low-latency assistance, extraction, and routine automation

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

Open-weight instruction model for adaptable chat and self-hosted production workloads

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

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

Efficient Mistral-NVIDIA open model for multilingual chat and local deployment

Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks

Open-weight instruction model for adaptable chat and self-hosted production workloads