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.
| Property | Value |
|---|---|
| Provider | arcee |
| Auth | ARCEEAI_API_KEY (direct) or OPENROUTER_API_KEY (via OpenRouter) |
| API | OpenAI-compatible |
| Base URL | https://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 ref | Name | Input | Context | Max output | Cost (in/out per 1M) | Tools | Notes |
|---|---|---|---|---|---|---|---|
arcee/trinity-large-thinking | Trinity Large Thinking | text | 256K | 80K | $0.25 / $0.90 | No | Default model; extended thinking |
arcee/trinity-large-preview | Trinity Large Preview | text | 128K | 16K | $0.25 / $1.00 | Yes | General-purpose; 400B params, 13B active |
arcee/trinity-mini | Trinity Mini 26B | text | 128K | 80K | $0.045 / $0.15 | Yes | Fast and cost-efficient; function calling |
Tip
The onboarding preset configures
arcee/trinity-large-thinkingas 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
| Feature | Supported |
|---|---|
| Streaming | Yes |
| Tool use / function calling | Yes (Trinity Mini, Trinity Large Preview) |
| Structured output (JSON mode and JSON schema) | Yes |
| Extended thinking | Yes (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.
Related
-
OpenRouter, Reach Arcee models and many others with a single API key.
-
Model selection, Choosing providers, model references, and failover behavior.