Try it
Policy GatewayDocsPricing
Log inGet API key
Docs

Using OpenClaw with abliteration.ai

Manually configure abliteration.ai as a custom Anthropic-compatible provider in OpenClaw. Add a models.providers entry, set baseUrl and apiKey, select abliterated-model.

Updated 2026-04-16

This guide shows how to use OpenClaw with abliteration.ai as a custom Anthropic-compatible model provider. For the packaged provider, use the OpenClaw ClawHub plugin guide. This page is the manual ~/.openclaw/openclaw.json setup.

OpenClaw is an open-source personal AI assistant that runs on macOS, Linux, and Windows (via WSL2). Its model layer reads custom provider definitions from ~/.openclaw/openclaw.json, so you can point its agent at any Anthropic- or OpenAI-compatible gateway.

abliteration.ai exposes the Anthropic Messages surface at /v1/messages and /v1/messages/count_tokens, which matches OpenClaw's anthropic-messages adapter one-for-one. Setup is entirely declarative: add one provider block under models.providers, register abliterated-model in its catalog, and set agents.defaults.model.primary.

Use openclaw onboard for guided setup, or edit ~/.openclaw/openclaw.json (JSON5) directly using the provider block below.

// ~/.openclaw/openclaw.json
{
  models: {
    mode: "merge",
    providers: {
      abliteration: {
        baseUrl: "https://api.abliteration.ai/v1",
        apiKey: "${ABLITERATION_API_KEY}",
        api: "anthropic-messages",
        models: [
          {
            id: "abliterated-model",
            name: "Abliterated Model",
            reasoning: false,
            input: ["text"],
            contextWindow: 128000,
            maxTokens: 8192,
            cost: {
              input: 0.005,
              output: 0.005,
            },
          },
        ],
      },
    },
  },
  agents: {
    defaults: {
      model: {
        primary: "abliteration/abliterated-model",
      },
    },
  },
}

Prerequisites

Before you start, make sure the basics are in place.

Provider settings

OpenClaw's model layer reads custom providers from models.providers.<name> inside ~/.openclaw/openclaw.json. For abliteration.ai, use the anthropic-messages adapter so OpenClaw talks to /v1/messages and /v1/messages/count_tokens.

SettingValuePurpose
models.providers.abliteration.baseUrlhttps://api.abliteration.ai/v1Targets the public abliteration.ai API under /v1. OpenClaw appends /messages and /messages/count_tokens.
models.providers.abliteration.apiKey${ABLITERATION_API_KEY}Sends your ak_ API key as the bearer token. The ${VAR} syntax reads the value from your shell at runtime.
models.providers.abliteration.apianthropic-messagesTells OpenClaw to speak the Anthropic Messages protocol to this provider.
models.providers.abliteration.models[].idabliterated-modelThe model id published by abliteration.ai. Must match exactly.
models.modemergeKeeps OpenClaw's built-in providers available alongside your custom provider. Use replace if you want to expose only abliteration.ai.
agents.defaults.model.primaryabliteration/abliterated-modelSelects abliteration.ai as the default model for new agent runs.

Configure openclaw.json

OpenClaw reads its primary config from ~/.openclaw/openclaw.json (legacy path ~/.clawdbot/clawdbot.json is still symlinked on upgraded installs). The file is JSON5, so comments, unquoted keys, and trailing commas are allowed.

Export your API key first so the ${ABLITERATION_API_KEY} interpolation resolves at runtime.

# Put this in ~/.bashrc, ~/.zshrc, or ~/.profile
export ABLITERATION_API_KEY="ak_YOUR_API_KEY"

# Reload your shell
source ~/.zshrc   # or source ~/.bashrc

# Open the config in your editor
${EDITOR:-vi} ~/.openclaw/openclaw.json

Provider block

Paste this provider block into ~/.openclaw/openclaw.json. The merge mode keeps OpenClaw's built-in providers intact so you can still switch to other models from openclaw onboard.

{
  models: {
    mode: "merge",
    providers: {
      abliteration: {
        baseUrl: "https://api.abliteration.ai/v1",
        apiKey: "${ABLITERATION_API_KEY}",
        api: "anthropic-messages",
        models: [
          {
            id: "abliterated-model",
            name: "Abliterated Model",
            reasoning: false,
            input: ["text"],
            contextWindow: 128000,
            maxTokens: 8192,
            cost: {
              input: 0.005,
              output: 0.005,
            },
          },
        ],
      },
    },
  },
  agents: {
    defaults: {
      model: {
        primary: "abliteration/abliterated-model",
        fallbacks: [],
      },
    },
  },
}

Validate the config

OpenClaw can dump its live JSON schema and validate the current config before you launch an agent.

# Print the schema OpenClaw uses to validate the config
openclaw config schema | less

# Show the resolved (merged) config that OpenClaw will use
openclaw config show

# Quick connectivity test against /v1/messages
curl -s https://api.abliteration.ai/v1/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ABLITERATION_API_KEY" \
  -d '{
    "model": "abliterated-model",
    "max_tokens": 64,
    "messages": [{"role": "user", "content": "ping"}]
  }' | python3 -m json.tool

Run the agent

Once the provider is in place and agents.defaults.model.primary is set, OpenClaw's agent uses abliteration.ai automatically. The agent command does not accept a positional prompt or a per-run --model flag — pass the prompt with --message and select an agent profile with --agent. The reserved default agent id is main.

To switch models, edit agents.defaults.model.primary in ~/.openclaw/openclaw.json, or create a dedicated agent profile with openclaw agents add that pins its own model.

# List available agents (main is the reserved default id)
openclaw agents list

# Send a one-off message to the default agent using the primary model
openclaw agent --agent main --message "summarize this directory"

# Raise the reasoning effort for a single run
openclaw agent --agent main --thinking high --message "refactor foo.py for readability"

# Emit structured JSON instead of the default formatted output
openclaw agent --agent main --json --message "list the files in this repo"

# Bypass the gateway and run the embedded agent directly
openclaw agent --agent main --local --message "ping"

How it works

OpenClaw's anthropic-messages adapter is a drop-in client for Anthropic-compatible gateways. The custom provider you defined has the same contract as OpenClaw's built-in Anthropic support.

Alternative: OpenAI-compatible wire format

If you prefer to route OpenClaw through the OpenAI Chat Completions surface, abliteration.ai also exposes /v1/chat/completions. Use api: "openai-completions" instead. This path is useful if another part of your stack already standardizes on OpenAI-style payloads.

Avoid api: "openai-responses" for custom providers on current OpenClaw releases — it has known issues for user-defined providers (see openclaw/openclaw#43018). Prefer the anthropic-messages config at the top of this page.

{
  models: {
    mode: "merge",
    providers: {
      "abliteration-openai": {
        baseUrl: "https://api.abliteration.ai/v1",
        apiKey: "${ABLITERATION_API_KEY}",
        api: "openai-completions",
        models: [
          {
            id: "abliterated-model",
            name: "Abliterated Model (OpenAI wire)",
            input: ["text"],
            contextWindow: 128000,
            maxTokens: 8192,
            cost: { input: 0.005, output: 0.005 },
          },
        ],
      },
    },
  },
  agents: {
    defaults: {
      model: {
        primary: "abliteration-openai/abliterated-model",
      },
    },
  },
}

Troubleshooting

Most setup issues are config resolution, env var interpolation, or model id mismatches.