Supported AI Models

Run agents with managed cloud AI, your own API keys (BYOK), or fully local models.

Managed cloud AI

No keys to manage. Billed in credits at provider cost + 20%. Requires a paid plan.

Bring your own key (BYOK)

Use your own OpenAI, Anthropic, Gemini, or DeepSeek API key. We never see or bill for this usage.

Local models

Ollama, LM Studio, llama.cpp and other local servers run free on your machine.

Managed AI Models & Pricing

ModelModel IDInput/1MOutput/1M
DeepSeek Chatdeepseek-chat$0.33$1.32
DeepSeek Reasonerdeepseek-reasoner$0.66$2.63
GPT-4ogpt-4o$3.00$12.00
GPT-4o minigpt-4o-mini$0.18$0.72
GPT-4 Turbogpt-4-turbo$12.00$36.00
GPT-3.5 Turbogpt-3.5-turbo$0.60$1.80
Claude 3.5 Sonnetclaude-3-5-sonnet-20241022$3.60$18.00
Claude 3.5 Haikuclaude-3-5-haiku-20241022$0.96$3.00
Claude 3 Opusclaude-3-opus-20240229$18.00$90.00
Gemini 2.0 Flashgemini-2.0-flash$1.20$4.80
Gemini 1.5 Progemini-1.5-pro$42.00$126.00
Gemini 1.5 Flashgemini-1.5-flash$4.20$12.60

Per 1M tokens, billed in credits (1 credit = $0.01). Provider cost + 20%, rounded up to the nearest cent.