Get started

Models

The model IDs you can call through the Messages and image endpoints.

Pass one of the model IDs below in the model field of your request. New models land as they ship, and live pricing for each is in the dashboard.

Text models

Call these through /v1/messages.

Model ID	Context	Best for
`claude-fable-5`	1M	The premium flagship, at the top of the lineup.
`claude-opus-5`	1M	The most capable Opus, for the hardest reasoning and agentic work.
`claude-opus-4-8`	1M	Top-tier reasoning and coding.
`claude-opus-4-7`	1M	A pinned earlier Opus snapshot.
`claude-opus-4-6`	1M	A pinned earlier Opus snapshot.
`claude-sonnet-5`	1M	The newest Sonnet, a strong, fast default.
`claude-sonnet-4-6`	1M	A pinned Sonnet snapshot, fast and balanced.
`claude-haiku-4-5`	200K	The fastest and most economical option.

All text models support tool use and extended thinking. The current-generation models also support effort control and web search. See Tool use and Extended thinking.

Image models

Call these through /v1/images/generations and /v1/images/edits.

Model ID	Best for
`nano-banana-pro`	Highest quality text-to-image and editing.
`nano-banana-2`	Fast, economical generation.

Image models support text-to-image, image editing, and a range of sizes and aspect ratios.

Pricing

Final per-token and per-image prices for every model are on the pricing page, settled onchain with nothing added on top.

Discover models programmatically

Point an agent at /v1/llms.txt for a plain-text list of the live models and endpoints.