OpenClaw

OpenClaw is an AI coding agent with support for custom OpenAI-compatible providers, fallback chains, and messaging gateway mode (Discord, Slack, Telegram, etc.).

AnyAPI is not a bundled provider in OpenClaw. You wire it in as a custom OpenAI-compatible provider under models.providers. Once registered, OpenClaw addresses models as anyapi/<vendor>/<model> (your provider ID prefix + the upstream model ID).

OpenClaw uses JSON5 at ~/.openclaw/openclaw.json — unquoted keys, trailing commas, and // comments are all valid.

Quick Start

The fastest path is the non-interactive onboarding wizard:

ANYAPI_API_KEY='your-key-here' openclaw onboard --non-interactive \
  --auth-choice custom-api-key \
  --custom-base-url "https://api.anyapi.ai/v1" \
  --custom-model-id "openai/gpt-4o" \
  --secret-input-mode ref \
  --custom-compatibility openai \
  --accept-risk

This registers a custom provider with baseUrl: https://api.anyapi.ai/v1, stores the API key as an env reference, and sets openai/gpt-4o as the default model. Then start OpenClaw:

openclaw

Prefer interactive setup? Run openclaw onboard without flags to walk through provider, URL, key, and model selection step by step.

Manual Configuration

Edit ~/.openclaw/openclaw.json directly for full control:

{
  env: {
    ANYAPI_API_KEY: "your-key-here",
  },
  models: {
    providers: {
      anyapi: {
        baseUrl: "https://api.anyapi.ai/v1",
        apiKey: {
          source: "env",
          provider: "default",
          id: "ANYAPI_API_KEY",
        },
        api: "openai-completions",
        models: [
          { id: "openai/gpt-4o" },
          { id: "openai/gpt-4o-mini" },
          { id: "anthropic/claude-sonnet-4.6" },
          { id: "google/gemini-2.5-pro" },
        ],
      },
    },
  },
  agents: {
    defaults: {
      model: {
        primary: "anyapi/openai/gpt-4o",
        fallbacks: [
          "anyapi/anthropic/claude-sonnet-4.6",
          "anyapi/openai/gpt-4o-mini",
        ],
      },
    },
  },
}

Restart OpenClaw for changes to take effect:

openclaw gateway restart   # if running as gateway daemon

Model Reference Format

OpenClaw composes model refs as <provider-id>/<upstream-model-id>. With provider ID anyapi:

anyapi/openai/gpt-4o — correct
anyapi/anthropic/claude-sonnet-4.6 — correct
openai/gpt-4o — won’t route through the anyapi provider
gpt-4o — missing vendor prefix, AnyAPI returns HTTP 400

The id field inside models.providers.anyapi.models[] is the upstream ID sent to AnyAPI (e.g. openai/gpt-4o). The anyapi/ prefix is added by OpenClaw based on your provider ID. Browse all available models at anyapi.ai/ai-models or query the API:

curl -sS -H "Authorization: Bearer $ANYAPI_API_KEY" \
  https://api.anyapi.ai/v1/models | jq -r '.data[].id'

Configuration Examples

GPT-4o
Claude Sonnet
Multi-model with fallbacks

{
  models: {
    providers: {
      anyapi: {
        baseUrl: "https://api.anyapi.ai/v1",
        apiKey: { source: "env", provider: "default", id: "ANYAPI_API_KEY" },
        models: [{ id: "openai/gpt-4o" }],
      },
    },
  },
  agents: {
    defaults: {
      model: { primary: "anyapi/openai/gpt-4o" },
    },
  },
}

{
  models: {
    providers: {
      anyapi: {
        baseUrl: "https://api.anyapi.ai/v1",
        apiKey: { source: "env", provider: "default", id: "ANYAPI_API_KEY" },
        models: [{ id: "anthropic/claude-sonnet-4.6" }],
      },
    },
  },
  agents: {
    defaults: {
      model: { primary: "anyapi/anthropic/claude-sonnet-4.6" },
    },
  },
}

{
  models: {
    providers: {
      anyapi: {
        baseUrl: "https://api.anyapi.ai/v1",
        apiKey: { source: "env", provider: "default", id: "ANYAPI_API_KEY" },
        models: [
          { id: "openai/gpt-4o" },
          { id: "anthropic/claude-sonnet-4.6" },
          { id: "openai/gpt-4o-mini" },
        ],
      },
    },
  },
  agents: {
    defaults: {
      model: {
        primary: "anyapi/openai/gpt-4o",
        fallbacks: [
          "anyapi/anthropic/claude-sonnet-4.6",
          "anyapi/openai/gpt-4o-mini",
        ],
        timeoutMs: 120000,
      },
    },
  },
}

Advanced Configuration

Per-model parameters

Set per-model defaults via agents.defaults.models:

{
  agents: {
    defaults: {
      models: {
        "anyapi/openai/gpt-4o": {
          params: {
            temperature: 0.7,
            max_tokens: 4096,
          },
        },
        "anyapi/openai/o3": {
          params: {
            max_completion_tokens: 8192,  // o-series uses max_completion_tokens
          },
        },
      },
    },
  },
}

Model metadata (context window, image input)

Enrich model entries to enable image inputs and set context windows:

models: [
  {
    id: "openai/gpt-4o",
    name: "GPT-4o (via AnyAPI)",
    input: ["text", "image"],
    contextWindow: 128000,
    maxTokens: 16384,
  },
  {
    id: "google/gemini-2.5-pro",
    input: ["text", "image"],
    contextWindow: 1000000,
    reasoning: true,
  },
]

OpenClaw won’t infer image capability for custom providers automatically — declare it explicitly.

Custom headers

Add request headers for tracking:

anyapi: {
  baseUrl: "https://api.anyapi.ai/v1",
  apiKey: { source: "env", provider: "default", id: "ANYAPI_API_KEY" },
  headers: {
    "X-My-App": "my-app-v1",
  },
  models: [{ id: "openai/gpt-4o" }],
}

Auth profiles

For multi-account setups, OpenClaw supports auth profiles. Store a key in OS keychain:

openclaw models auth add --provider anyapi

CLI Reference

# Onboarding
openclaw onboard                          # interactive setup
openclaw onboard --non-interactive ...    # scripted setup

# Model management
openclaw models list                      # list configured models
openclaw models set anyapi/openai/gpt-4o  # set default model

# Config
openclaw config validate                  # validate config
openclaw config get models.providers.anyapi.baseUrl
openclaw config set agents.defaults.model.primary "anyapi/openai/gpt-4o"

# Gateway
openclaw gateway status
openclaw gateway restart
openclaw gateway logs

Troubleshooting

Provider not found / config validation fails

OpenClaw rejects unknown keys. Use the canonical field names:

baseUrl (camelCase, not baseURL)
apiKey (object or ${VAR} template, not apiKeyEnvVar)

Validate with openclaw config validate.

No API key for provider 'anyapi'

The apiKey reference doesn’t resolve.

Confirm the env var is set: echo $ANYAPI_API_KEY

Confirm the apiKey block points to it:

apiKey: { source: "env", provider: "default", id: "ANYAPI_API_KEY" }

Restart OpenClaw — env changes don’t apply to a running daemon.

Authentication failed (HTTP 401)

Your key is invalid, expired, or revoked.

Validate the key at dash.anyapi.ai

Test directly:

curl https://api.anyapi.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ANYAPI_API_KEY" \
  -d '{"model":"openai/gpt-4o-mini","messages":[{"role":"user","content":"test"}],"max_tokens":10}'

Model not found / Bad Request (HTTP 400)

The model ID is unknown or missing the vendor prefix.

List the catalog: curl -H "Authorization: Bearer $ANYAPI_API_KEY" https://api.anyapi.ai/v1/models
Use vendor/model form (e.g. openai/gpt-4o, not bare gpt-4o)
Confirm the model is listed under models.providers.anyapi.models[] in your config

Base URL errors

Set baseUrl to exactly https://api.anyapi.ai/v1 — no trailing slash, no /chat/completions suffix (OpenClaw appends that).

Rate limiting (HTTP 429)

Check usage at dash.anyapi.ai, upgrade your plan, or add fallbacks to spread load.

Best Practices

Store keys as env refs, not plaintext — prefer secret-input-mode ref during onboarding
Configure fallbacks across different vendors for cross-provider resilience
Set timeoutMs for slow models — reasoning models like openai/o3 can take minutes
Pin model capability metadata — declare input: ["text", "image"] explicitly for vision models
Always use vendor/model format — bare names return HTTP 400
Monitor usage at dash.anyapi.ai

Support

AnyAPI Dashboard: dash.anyapi.ai
AnyAPI Discord: Discord community
AnyAPI Email: support@anyapi.ai
OpenClaw Issues: github.com/openclaw/openclaw/issues

Get started

Features

Use Cases

Developer guides

Integrations

API Reference

OpenClaw

OpenClaw

Quick Start

Manual Configuration

Model Reference Format

Configuration Examples

Advanced Configuration

CLI Reference

Troubleshooting

Best Practices

Support

​OpenClaw

​Quick Start

​Manual Configuration

​Model Reference Format

​Configuration Examples

​Advanced Configuration

​CLI Reference

​Troubleshooting

​Best Practices

​Support

OpenClaw

Quick Start

Manual Configuration

Model Reference Format

Configuration Examples

Advanced Configuration

CLI Reference

Troubleshooting

Best Practices

Support