Models

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

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

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

Prior MiniMax coding model for agent workflows, office edits, and automation

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

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

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

Earlier MiniMax agent model for practical coding and productivity tasks

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

Mistral's largest general model for enterprise agents, coding, and multilingual reasoning

Compact open vision-language model for edge deployment, instruction following, and tool use

Compact open vision-language model for edge deployment, instruction following, and tool use

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...

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

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

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

Open multimodal reasoning model for transparent analysis of text and images

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

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

Smaller Qwen coder for efficient local agents and repo-level fixes

Open Qwen coding heavyweight for repository reasoning and agentic engineering

Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use

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

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

Dense open Qwen model for self-hosted chat, reasoning, and coding

Open Llama with long-context vision for efficient multimodal agents

Open multimodal Llama for strong reasoning with efficient everyday serving

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Classic open reasoning model for transparent math, coding, and deliberate problem solving