Skip to main content
Runable gives you access to models from Anthropic, Google, OpenAI, and xAI. Which models you see depends on whether you are in Agent Mode or Chat Mode.

​
Agent Mode tiers

In Agent Mode, you select a tier. The agent uses the corresponding model.
TierBest forCredit cost
LiteFast tasks, simple edits, quick answersLowest
ProMost tasks, good balance of speed and qualityMedium
MaxComplex reasoning, deep analysis, multi-step projectsHighest

​
Chat Mode models

In Chat Mode, you pick a specific model from the dropdown. All of the following models are available:
ModelProviderContext Window
Claude Haiku 4.5Anthropic200K
Claude Sonnet 4.5Anthropic200K
Claude Sonnet 4.6Anthropic200K
Claude Opus 4.5Anthropic200K
Claude Opus 4.6Anthropic200K
Gemini 2.5 FlashGoogle1M
Gemini 2.5 ProGoogle1M
Gemini 3 Flash PreviewGoogle1M
GPT-5.1OpenAI272K
GPT-5.2OpenAI400K
GPT-5 MiniOpenAI400K
GPT-5 NanoOpenAI400K
GPT-5 ProOpenAI400K
GPT-5.1 InstantOpenAI128K
GPT-5.1 ThinkingOpenAI400K
Grok 4.1 FastxAI2M
All models support file input, reasoning, tool use, and vision.

​
How credits work with models

Every AI operation costs credits. The cost depends on the model used and the amount of input and output processed. Higher-capability models cost more credits per message.
For most tasks, Pro is the best balance of quality and cost. Use Max for complex reasoning or when Pro produces unsatisfactory results. Use Lite for quick edits and simple questions.
Model availability may change as new models are released and older ones are retired. The models listed here reflect what is currently available.

​
Next steps

Plans and Credits

See how credits work and what each plan includes.

Agent Mode

Learn how the agent uses models in Agent Mode.