Anthropic · Text

OpenClaw x Claude

Claude is Anthropic's LLM family, spanning Opus (frontier), Sonnet (balanced), and Haiku (fast). Through RunAPI, all Claude variants share the same API shape and per-token billing.

Public versions and endpoints

Model IDVersionEndpointsStarting priceCatalog
claude-fable-5Mythos-class 1M context; state-of-the-art coding, reasoning, and vision
/v1/messages
$0.010Model detail
claude-haiku-4-5-20251001Dated snapshot of Haiku 4.5 for reproducible outputs
/v1/messages
$0.0006Model detail
claude-opus-4-1-20250805claude-opus-4-1-20250805
/v1/messages
$0.0090Model detail
claude-opus-4-5-20251101claude-opus-4-5-20251101
/v1/messages
$0.0030Model detail
claude-opus-4-61M token context; frontier reasoning at $5/$25 per M tokens
/v1/messages
$0.0030Model detail
claude-opus-4-71M context; enhanced coding and tool use over 4.6
/v1/messages
$0.0030Model detail
claude-opus-4-81M context; strongest judgment and long-workflow reliability
/v1/messages
$0.0030Model detail
claude-opus-51M context; frontier reasoning and long-workflow reliability
/v1/messages
$0.0030Model detail
claude-sonnet-4-5-20250929claude-sonnet-4-5-20250929
/v1/messages
$0.0018Model detail
claude-sonnet-4-61M context; matches Opus coding at 40% lower cost
/v1/messages
$0.0018Model detail
claude-sonnet-51M context; near-Opus coding and agentic skill at Sonnet cost
/v1/messages
$0.0014Model detail

Configuration

Guide endpoint: <endpoint>

Select <model-id> to generate a request with the endpoint's public input contract.

Verify

Select <model-id> to generate verification commands.

How it works

  1. 1. Choose a model ID

    Select a public catalog model ID and review its endpoint and current starting price.

  2. 2. Configure RunAPI

    Add the provider configuration for this agent.

  3. 3. Verify the result

    Run the agent status and model-selection commands shown below.

FAQ

Which model ID should I use?

Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.

Does this guide configure a chat model?

Yes. This Model Line supports a client-facing LLM protocol.