Forge LLMs supports Claude models across three tiers: Haiku, Sonnet, and Opus. You choose the model per request, allowing you to balance latency, capability, and cost for each use case.

Supported models

You can use the list method from the @forge/llm SDK to dynamically fetch the list of supported models and their current status.

Model ID	Tier	Family	Status	Tentative retirement date
`claude-haiku-4-5-20251001`	Haiku	Claude	`ACTIVE`	Not sooner than October 15, 2026
`claude-sonnet-4-5-20250929`	Sonnet	Claude	`ACTIVE`	Not sooner than September 29, 2026
`claude-sonnet-4-6`	Sonnet	Claude	`ACTIVE`	Not sooner than February 17, 2027
`claude-sonnet-5`	Sonnet	Claude	`ACTIVE`	Not sooner than June 30, 2027
`claude-opus-4-6`	Opus	Claude	`ACTIVE`	Not sooner than February 5, 2027
`claude-opus-4-7`	Opus	Claude	`ACTIVE`	Not sooner than April 16, 2027
`claude-opus-4-8`	Opus	Claude	`ACTIVE`	Not sooner than May 28, 2027
`claude-opus-5`	Opus	Claude	`ACTIVE`	Not sooner than July 24, 2027

AI model availability can change quickly.

Check model status and tentative retirement dates regularly, and update your app before a model reaches end-of-life.
Tentative retirement dates come from Anthropic and may change. For the latest values, see Model status.
Where possible, Forge provides at least six months' notice for model deprecations.

Some models do not support the temperature and top_p sampling parameters. Omit both parameters from requests to any affected model. For the current list of affected models, see the validation rules.

Only text input/output is currently supported; multimodal support may be considered later.

Claude - Opus

Most capable (best for complex, deep reasoning tasks)
Slowest (higher latency due to depth)
Highest cost

Claude - Sonnet

Balanced capability
Moderate speed
Moderate cost

Claude - Haiku

Fast and efficient (best for lightweight or high‑volume tasks)
Lowest cost