Moonshot AI · Text

OpenClaw x Kimi

kimi-k3 is Kimi's current flagship and uses always-on reasoning. kimi-k2.5 and kimi-k2.6 remain available; their older K2 architecture has 1T parameters and 256K context, and the 58.6% SWE-bench Pro result belongs to kimi-k2.6. Kimi is available through OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, and Gemini native APIs. RunAPI's initial kimi-k3 release supports basic text requests with synchronous and SSE streaming responses.

Public versions and endpoints

Model IDVersionEndpointsStarting priceCatalog
kimi-k2.51T / 32B active; 256K context; native multimodal input
/v1/chat/completions
$0.0006Model detail
kimi-k2.61T / 32B active; 256K context; 58.6% SWE-bench Pro; 300-agent swarm
/v1/chat/completions
$0.0026Model detail
kimi-k2.7-codeDedicated coding model; always-on thinking; 256K context
/v1/chat/completions
$0.0006Model detail
kimi-k3Current Kimi flagship with always-on reasoning
/v1/chat/completions
$0.0018Model 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.