Models

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

StepFun flash lane for quick multimodal reasoning and coding assistance

Lightly post-trained 398B MoE chat model for creative work, long-context prompts, and tool-using agents

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

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

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

Flagship model for demanding analysis, coding, and production agent workflows

ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows

Earlier MiniMax agent model for practical coding and productivity tasks

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

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

MiMo flash model for fast multimodal assistance and agent workflows

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

Reliable GPT generation for broad coding, writing, and tool-assisted product work

Code-specialist GPT for repository edits, reviews, and long-running software agents

Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows

Chat-tuned GPT model for conversational assistance, writing, and tool workflows

Compact multimodal coding model for repository exploration, file editing, and software agents

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

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

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

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

Mistral coding agent model for repository tasks and software engineering workflows

Multimodal reasoning model for visual analysis, planning, and tool use

DeepSeek chat model for instruction following, coding, and analysis

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

Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads

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

Flagship Claude model for deep reasoning, coding, and long-horizon agents

xAI's fast agentic tool-calling model with a 2M context window and built-in reasoning

xAI's fast agentic tool-calling model with a 2M context window; non-reasoning variant for low-latency responses

Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts

Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations

Codex GPT for repository edits, code review, and practical software agents

Sharper GPT-5 generation for coding, product work, and tool-assisted tasks

Coding-optimized GPT model for repository edits, reviews, and agentic software work

Coding-optimized GPT model for repository edits, reviews, and agentic software work

Kimi reasoning model for long-horizon research, planning, and tool use

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

Flagship Claude model for deep reasoning, coding, and long-horizon agents

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

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

Nemotron multimodal model for visual reasoning and agentic AI workflows

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

Fast Claude model for responsive assistance, classification, and lightweight agents

ByteDance Seed model for long-context reasoning, instruction following, and tool-assisted tasks

Fast Claude lane for lightweight agents, office tasks, and responsive chat

Specialized Gemini 2.5 model for browser-control agents that automate UI tasks

Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning

Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads