Documentation

Everything you need to integrate with the AllRoutes.ai API Gateway.

Quick Start

# Use any OpenAI-compatible SDK — just change the base URL
curl https://api.allroutes.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

AllRoutes.ai is fully OpenAI-compatible. Replace your base URL and you're set.

Getting Started

Quick Start

Get up and running with the AllRoutes AI gateway in under 5 minutes.

Authentication

API key types, scopes, rate limits, and authentication methods for the AllRoutes API.

Your First Request

A step-by-step guide to making your first chat completion request with AllRoutes.

API Reference

Chat Completions

Complete reference for the POST /v1/chat/completions endpoint, including all parameters, streaming, and AllRoutes-specific extensions.

Embeddings

Create vector embeddings using the POST /v1/embeddings endpoint.

Models

List, search, and compare available AI models via the Models API.

API Keys

Programmatically create, list, update, and delete API keys.

Billing & Credits

Manage your credit balance, view transactions, and understand AllRoutes pricing.

Streaming

Server-Sent Events protocol for chat completions, including chunk format, [DONE] handling, and stream_options.include_usage.

Rerank

Re-rank a list of documents against a query using Cohere, Voyage, Jina, or Mixedbread reranker models.

Fine-Tuning

Create, monitor, and deploy fine-tuned models across OpenAI, Together, Fireworks, and other supported providers.

Audio (TTS, STT, Translation)

Text-to-speech, speech-to-text, and audio translation across OpenAI, ElevenLabs, Deepgram, and Cartesia.

Images

Generate, edit, and create variations of images via DALL-E, Stable Diffusion, Flux, Imagen, and Ideogram models.

Files

Upload, list, download, and delete files used for fine-tuning, batch jobs, file-parser plugin, and assistants.

Realtime API

WebSocket-based bidirectional streaming for low-latency voice agents and live conversational AI.

Responses API

OpenAI's stateful conversation endpoint with built-in tool execution and conversation persistence.

Features

Smart Routing

Automatic model selection, fallback chains, and provider routing strategies.

Semantic Caching

3-tier caching system that saves 40-80% on repeated queries with exact match, semantic similarity, and provider passthrough.

Guardrails & Compliance

Budget limits, PII redaction, prompt injection detection, and compliance profiles for enterprise-grade AI safety.

Plugins

Extend AllRoutes requests with web search, file parsing, response healing, and more.

Presets

Named configurations for model, parameters, system prompts, and plugins that can be referenced by name in any request.

Broadcast & Observability

Send AI traces and logs to 15+ observability destinations including Datadog, Langfuse, and custom webhooks.

Analytics

Built-in dashboards for cost, latency, quality, and usage breakdowns by model, key, user, and session.

Webhooks

Subscribe to events: request completed, error, budget alert, key created, fine-tuning job done, and more.

Model Groups

Alias multiple concrete models behind a single virtual identifier with weighted routing, fallbacks, and per-group cost controls.

Free Tier

Free models, daily limits, and how community-hosted free routes work alongside paid tiers.

SDKs

Python SDK

Planned Python SDK for AllRoutes. Until it ships, use the OpenAI Python client pointed at https://api.allroutes.ai/v1.

Node.js / TypeScript SDK

Planned Node SDK for AllRoutes. Until it ships, use the OpenAI Node client pointed at https://api.allroutes.ai/v1.

Go SDK

Planned Go SDK for AllRoutes. Until it ships, use any OpenAI-compatible Go client pointed at https://api.allroutes.ai/v1.

Guides

Migrating from OpenRouter

Step-by-step guide to switching from OpenRouter to AllRoutes with a feature comparison and pricing advantages.

Bring Your Own Key (BYOK)

Connect your own provider API keys for 9 providers with 0% commission, automatic validation, and seamless fallback.

Self-Hosted Models

Connect Ollama, vLLM, TGI, or any OpenAI-compatible endpoint to AllRoutes for unified routing, caching, and observability.

OpenAI SDK Drop-in

Reuse the official OpenAI SDKs (Python, Node, Go, Java, etc.) with AllRoutes by changing only the base URL and API key.

Error Handling

Production patterns for catching, retrying, and recovering from AllRoutes API errors -- with typed examples for every SDK.

Cost Optimization

Patterns and AllRoutes features that compound to cut your AI bill 40-90% without quality loss.

Observability Setup

Wire AllRoutes to OpenTelemetry, Langfuse, Helicone, and Datadog for end-to-end tracing of every AI request.