Models

Agentic coding model from Poolside in the XS size class for local deployment

Everyday Claude agent model for coding, planning, browsing, and general work

Quality-first multi-agent model for hard research, analysis, and competitions

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Claude model for creative writing, analysis, and controlled agent workflows

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

Fast Gemini model balancing multimodal reasoning, tool use, and cost

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

Open MoE flagship with million-token context for coding and long agent runs

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

Default frontier GPT for coding, computer use, research, and knowledge work

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

Open MiMo model for multimodal coding agents and long-context automation

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

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk

Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.

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

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

StepFun flash model for efficient multimodal reasoning, coding, and tool use

Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use

Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation

Strong small GPT for coding subagents, quick tool use, and high-volume work

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

More exact GPT-5.4 tier for demanding professional reasoning and agent tasks

Agent-ready GPT for coding and computer-use workflows at a lower cost

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

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

Reasoning-first Gemini preview for agentic coding and complex problem solving

Claude workhorse for coding agents, careful analysis, and production cost control

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

StepFun flash lane for quick multimodal reasoning and coding assistance

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

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

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

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

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

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

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

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

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

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

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

DeepSeek chat model for instruction following, coding, and analysis