Gateway
API Reference
Use one bearer token to talk to chat completions, grammar checking, PII detection, and audio services — with consistent accounting, rate limits and vendor-agnostic routing.
TL;DR
You're going to Ctrl-F for curl anyway, so here it is. Grab an API token from the portal and call any endpoint with Authorization: Bearer inf_....
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
Guides
Processors
Anonymise and spellcheck on top of completions
Haystack
Attach structured customer-side context to chat completions
System prompt assembly
How the gateway combines model default + processors + caller content
Prompt Templating
Inject the date and other gateway facts into system prompts
Managed Apps
Self-hosted Flowise, n8n, OpenWebUI
Tools
Function-calling tools the gateway runs on your behalf
Agents
Scheduled / webhook-triggered apps that call your services with their own token
MCP Servers
Bring-your-own MCP server: tools through the agent loop, skills preloaded into the system prompt
Usage Accounting
What is counted per scope and how to read it
Billing
Pricing, allowances, spending caps and monthly invoices
Rate Limits
Limits hierarchy, metrics and error shapes
Errors
Response formats and HTTP status codes
Ready to build?
Head to the portal to create your first API token.
Open the portal