OpenAI-Compatible API Docs

OpenAI-compatible API docs for abliteration.ai. Change the SDK base URL, keep Chat Completions or Responses request shapes, use role/content messages and response_format, and migrate Python, Node, or framework clients.

Compatibility overview of popular SDKs and frameworks that work with abliteration.ai, with links to ready-to-run guides.

Run the abliteration.ai API in Postman, download the collection/environment, and import the OpenAPI schema into tooling.

Use the OpenAI Python SDK with abliteration.ai by setting base_url and api_key. OpenAI-compatible chat completions.

Use the OpenAI Node SDK with abliteration.ai by setting baseURL and apiKey. OpenAI-compatible chat completions.

Use Codex CLI or the Codex TUI with abliteration.ai as a custom OpenAI Responses provider. Configure base_url, env_key, model_providers, and wire_api = responses.

Route Claude Code through abliteration.ai as an Anthropic Messages gateway. Set the base URL and one auth variable, pick a model-selection style, and persist your config via ~/.claude/settings.json or your shell profile.

Install @abliterationai/openclaw-abliteration-provider from ClawHub or npm to register abliteration.ai as an OpenClaw provider.

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

Model specs and benchmark scores for abliterated-model.

Use LangChain OpenAI integrations with abliteration.ai. Configure ChatOpenAI with base_url, api_key, abliterated-model, and the OpenAI-compatible chat completions endpoint.

Point LlamaIndex's OpenAI LLM to abliteration.ai by setting api_base and api_key. OpenAI-compatible chat completions.

Use the official abliteration.ai provider with the Vercel AI SDK. Configure ABLIT_KEY once and choose chat, responses, or messages.

Call abliteration.ai from a Cloudflare Worker using fetch. Store your API key in env and call /v1/chat/completions.

Call abliteration.ai from a Next.js Route Handler with a minimal fetch wrapper. OpenAI-compatible /v1/chat/completions.

Proxy abliteration.ai through FastAPI with an async httpx client. OpenAI-compatible chat completions.

Send OpenAI-compatible chat completions from Spring Boot using WebClient.

Call the OpenAI-compatible /v1/chat/completions endpoint from Bun with fetch.

Deploy a minimal Cloud Run service that proxies prompts to abliteration.ai.

Call abliteration.ai from AWS Lambda with a minimal handler and fetch.

Use Codex CLI or the Codex TUI with abliteration.ai as a custom OpenAI Responses provider. Configure base_url, env_key, model_providers, and wire_api = responses.

Route Claude Code through abliteration.ai as an Anthropic Messages gateway. Set the base URL and one auth variable, pick a model-selection style, and persist your config via ~/.claude/settings.json or your shell profile.

Install @abliterationai/openclaw-abliteration-provider from ClawHub or npm to register abliteration.ai as an OpenClaw provider.

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

Stream chat completions with abliteration.ai. Set stream: true and iterate over delta chunks.

Send images and text to vision-capable models using the OpenAI-compatible message content array.

Send short videos to vision-capable models on /v1/chat/completions. Authenticated callers only — anon free-tier is text + image.

Learn how rate limits work and how to implement backoff, retries, and concurrency control.

Full reference for the OpenAI-compatible POST /v1/responses endpoint on abliteration.ai. Request schema, structured input, streaming events, authentication, rate limits, and billing fields.

Full reference for the Anthropic-compatible POST /v1/messages endpoint on abliteration.ai. Request schema, streaming, authentication, rate limits, and error codes.

Configure Policy Gateway, manage projects and keys, and enforce policy with /policy/chat/completions.

Open-source connectors for Next.js, FastAPI, LangChain, and LiteLLM to route traffic through Policy Gateway.

The request/response contract for /policy/chat/completions: custom moderation rules, policy_id, optional headers, quotas, and audit decision metadata.

What Policy Gateway stores, what it does not store, and how audit logs, redaction, and scoped keys work.

Set up an AI model gateway with custom moderation rules, scoped keys, quotas, shadow mode, canary rollout, and structured audit logs.

Move your Azure OpenAI workloads to Policy Gateway to gain full control over safety filters, quotas, and audit logs.

Compare Azure AI Content Safety with Policy Gateway. Understand the difference between provider-imposed filters and full policy control.

Minimal MCP governance guard for tool allowlists, audit trails, and policy tagging with policy_user and policy_project_id.