Gateway
Inferada API
Use one API and one bearer token to access models and AI services across providers. Inferada applies consistent authentication, routing, usage accounting, and limits to every request.
Make your first request
Create an API token in the portal, then send it as a bearer token with each request. This example creates a chat completion.
bash
curl https://api.inferada.com/v1/chat/completions \
-H "Authorization: Bearer inf_YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3.5-35b",
"messages": [{ "role": "user", "content": "Hello!" }]
}'Endpoints
Chat completions
OpenAI-compatible chat with Inferada extensions
Embeddings
OpenAI-compatible text embeddings
Rerank
Order documents by relevance to a query
Decisions
Typed decisions via /v1/decisions or native System One
Images
Generate and edit images from a prompt
OCR
Extract text and structure from document images
Language
Grammar and spell checking
PII
Detect, redact and restore personal data
Audio
Speech-to-text and text-to-speech
Services
Discover services and select one for a request
Guides
Processors
Add redaction, policy checks, and routing controls
Haystack
Attach structured customer-side context to chat completions
System prompt assembly
How the gateway combines model default + processors + caller content
Prompt templating
Render gateway values in system prompts
Managed Apps
Flowise, n8n and OpenWebUI, hosted for you
Tools
Configure gateway-managed and client-run tools
Agents
Run TypeScript apps on a schedule or from a webhook
MCP servers
Add an MCP server's tools and skills to selected models
Usage accounting
Understand counters, request history, and attribution
Billing
Pricing, allowances, spending caps and monthly invoices
Rate limits
Limits hierarchy, metrics and error shapes
Errors
Response formats and HTTP status codes
Create an API token
Open the portal to create a token and choose the scopes your application needs.
Open the portal