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

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

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

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

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

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

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

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

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

DeepSeek chat model for instruction following, coding, and analysis

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

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

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

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

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

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

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

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

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

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

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

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

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

Balanced Claude model for coding, analysis, agent workflows, and cost control

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

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

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

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

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

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

Nano Banana image model for fast generation, edits, and character-consistent assets

Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows

Small GPT-5 for responsive agents, coding help, and everyday automation

Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs

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

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

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

Qwen coding model for software agents, repository edits, and code reasoning

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

Nemotron model for efficient reasoning, coding, and specialized AI agents

Hosted Qwen coder for software agents, repo edits, and long-context code

Fast Gemini workhorse for multimodal apps where latency and price matter

Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

Google's proven reasoning model for coding, math, and multimodal analysis

High-effort o3 tier for difficult technical reasoning and careful answers

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

Fast o-series model for compact reasoning, coding, and tool use