Models

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Flagship GLM model for long-horizon coding, agents, and complex project delivery

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

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

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

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

Lower-latency Kimi Code variant for interactive edits and coding-agent loops

MiniMax multimodal model for long-context coding, perception, and agent planning

Balanced Mistral model for enterprise assistants, multilingual work, and tools

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

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

Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads

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

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

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

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...

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

Open MiniMax flagship for coding agents, office automation, and complex environments

Efficient Mistral model for fast chat, extraction, and production assistants

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

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

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

High-speed MiniMax model for low-latency coding and agent workflows

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

Efficient GLM model for fast reasoning, coding, and agent workflows

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...

Earlier MiniMax agent model for practical coding and productivity tasks

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

Mistral's coding-agent model for repository work, terminal tasks, and software fixes

Mistral coding agent model for repository tasks and software engineering workflows

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...

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

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...

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

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

Efficient Qwen thinking model for local reasoning, math, and coding agents

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

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

Compact Nemotron model for efficient reasoning and deployable AI agents

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...