Arcee AI Provider Setup: Auth & Model Selection

Learn how to set up the Arcee AI provider for OpenClaw, including authentication and model selection. This guide covers direct API access via Arcee or through OpenRouter.

Read this when

  • You want to use Arcee AI with OpenClaw
  • You need the API key env var or CLI auth choice

Arcee AI offers the Trinity family of mixture-of-experts models through an API that works with OpenAI's format. Every Trinity model carries an Apache 2.0 license. Arcee is an official OpenClaw plugin, not part of the core package, so you must install it before you can use it.

You can reach Arcee models either directly through the Arcee platform or via 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)

Install plugin

openclaw plugins install @openclaw/arcee-provider
openclaw gateway restart

Getting started

Direct (Arcee platform)

Get an API key

Generate an API key at Arcee AI.

Run onboarding

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

Set a default model

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

Via OpenRouter

Get an API key

Generate an API key at OpenRouter.

Run onboarding

openclaw onboard --auth-choice arceeai-openrouter

Set a default model

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

The same model references work whether you connect directly or through OpenRouter.

Non-interactive setup

Direct (Arcee platform)

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

Via OpenRouter

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

Direct Arcee catalog

Model refNameInputContextMax outputCost (in/out per 1M)ToolsNotes
arcee/trinity-large-thinkingTrinity Large Thinkingtext256K80K$0.25 / $0.90NoDefault model; extended thinking
arcee/trinity-large-previewTrinity Large Previewtext128K16K$0.25 / $1.00YesGeneral-purpose; 400B params, 13B active
arcee/trinity-miniTrinity Mini 26Btext128K80K$0.045 / $0.15YesFast and cost-efficient; function calling

Tip

The onboarding preset configures arcee/trinity-large-thinking as the default model.

OpenRouter catalog

OpenRouter onboarding exposes arcee/trinity-large-preview and arcee/trinity-large-thinking. OpenClaw keeps those provider-qualified model references in configuration and sends OpenRouter's canonical arcee-ai/* runtime IDs. Trinity Mini is no longer available through OpenRouter; use the direct Arcee API for that model.

Supported features

FeatureSupported
StreamingYes
Tool use / function callingYes (Trinity Mini, Trinity Large Preview)
Structured output (JSON mode and JSON schema)Yes
Extended thinkingYes (Trinity Large Thinking; tools disabled)

Environment note

If the Gateway runs as a daemon (launchd/systemd), make sure ARCEEAI_API_KEY (or OPENROUTER_API_KEY) is accessible to that process, for example in ~/.openclaw/.env or via env.shellEnv.

OpenRouter routing

OpenRouter uses the same arcee/trinity-large-thinking OpenClaw model reference. OpenClaw routes it using the canonical arcee-ai/trinity-large-thinking OpenRouter runtime ID. Refer to the OpenRouter provider docs for OpenRouter-specific configuration details.

  • OpenRouter, Reach Arcee models and many others with a single API key.

  • Model selection, Choosing providers, model references, and failover behavior.