Models

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

Open flagship GLM for long-horizon coding agents and million-token context work

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

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

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

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

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Strong GLM coding model for agentic engineering, terminals, and repository generation

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

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

Low-latency M2.7 variant for interactive coding plans and agent loops

Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

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

High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes

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

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

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

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

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

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

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

R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving

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