Models

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

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

Budget GLM lane for fast coding help, routing, and everyday automation

Mature GLM model for dependable coding, reasoning, and structured agent tasks

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

GLM vision model for visual reasoning, documents, and multimodal agents

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

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

Efficient open MiniMax model built for coding agents and tool-heavy workflows

Open vision-language MoE model for image and video understanding, documents, and visual agents

Late GLM-4 workhorse for coding agents, reasoning, and structured tasks

Flagship Qwen3 model for coding agents, complex reasoning, and tool use

Multimodal reasoning model accepting text, images, video, and audio with text output

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

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes

GLM vision model for visual reasoning, documents, and multimodal agents

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

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

Hybrid-reasoning GLM release that made the 4.5 line broadly useful

Lighter GLM-4.5 variant for fast coding assistance and cheaper agents

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

Open ERNIE text MoE with 21B total and 3B active parameters

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

Open Llama with long-context vision for efficient multimodal agents

Open multimodal Llama for strong reasoning with efficient everyday serving

March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding

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 DeepSeek MoE chat model for coding, math, and general reasoning

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

Compact instruction-tuned Llama model for multilingual dialogue and on-device assistants

Compact open Llama model for lightweight chat, drafting, and self-hosting

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

Llama 3 fine-tune optimized for function calling, structured JSON responses, and dialogue