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

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

MiniMax M2 variant tuned for conversational and character-driven agent interactions

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

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

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

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

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

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

Tool-capable chat model for instruction following and agentic application workflows

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

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

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

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

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

DeepSeek chat model for instruction following, coding, and analysis

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

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

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

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

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

Image model for prompt-driven generation, editing, and visual design workflows

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

Image model for prompt-driven generation, editing, and visual design workflows

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

Open vision-language MoE model for image and video understanding, documents, and visual agents

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

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

Open-weight instruction model for adaptable chat and self-hosted production workloads

General-purpose chat model for instruction following, writing, and analysis

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

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

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

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

September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding

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

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

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