Skip to main content

​
Arcee AI

Arcee AI provides access to the Trinity family of mixture-of-experts models through an OpenAI-compatible API. All Trinity models are Apache 2.0 licensed. Arcee AI models can be accessed directly via the Arcee platform or through OpenRouter.
PropertyValue
Providerarcee
AuthARCEEAI_API_KEY (direct) or OPENROUTER_API_KEY (via OpenRouter)
APIOpenAI-compatible
Base URLhttps://api.arcee.ai/api/v1 (direct) or https://openrouter.ai/api/v1 (OpenRouter)

​
Getting started

1

Get an API key

Create an API key at Arcee AI.
2

Run onboarding

openclaw onboard --auth-choice arceeai-api-key
3

Set a default model

{
  agents: {
    defaults: {
      model: { primary: "arcee/trinity-large-thinking" },
    },
  },
}

​
Non-interactive setup

openclaw onboard --non-interactive \
  --mode local \
  --auth-choice arceeai-api-key \
  --arceeai-api-key "$ARCEEAI_API_KEY"

​
Built-in catalog

OpenClaw currently ships this bundled Arcee catalog:
Model refNameInputContextCost (in/out per 1M)Notes
arcee/trinity-large-thinkingTrinity Large Thinkingtext256K0.25/0.25 / 0.90Default model; reasoning enabled
arcee/trinity-large-previewTrinity Large Previewtext128K0.25/0.25 / 1.00General-purpose; 400B params, 13B active
arcee/trinity-miniTrinity Mini 26Btext128K0.045/0.045 / 0.15Fast and cost-efficient; function calling
The onboarding preset sets arcee/trinity-large-thinking as the default model.

​
Supported features

FeatureSupported
StreamingYes
Tool use / function callingYes
Structured output (JSON mode and JSON schema)Yes
Extended thinkingYes (Trinity Large Thinking)
If the Gateway runs as a daemon (launchd/systemd), make sure ARCEEAI_API_KEY (or OPENROUTER_API_KEY) is available to that process (for example, in ~/.openclaw/.env or via env.shellEnv).
When using Arcee models via OpenRouter, the same arcee/* model refs apply. OpenClaw handles routing transparently based on your auth choice. See the OpenRouter provider docs for OpenRouter-specific configuration details.

OpenRouter

Access Arcee models and many others through a single API key.

Model selection

Choosing providers, model refs, and failover behavior.