API guide
Every model is called the same way: submit an asynchronous task, poll it, download the result. Base URL: https://api.hermes-ai.net
How it works
01
Submit
POST /api/v1/jobsSend a model slug and its input. You get a task ID right away.
02
Poll
GET /api/v1/jobs/{id}Check every few seconds until the task succeeds or fails.
03
Download
GET /api/v1/results/{id}Fetch each result with the same credentials.
Guides and reference
Get started
Quickstart
Create an API key and run your first image, video or music task in a few minutes.
ReadGuides
Authentication
Create API keys, send them with each request, and understand scopes and endpoints.
ReadGuides
Choose a model
Find a model, read its input schema and send only the fields it accepts.
ReadGuides
Tasks and results
Submit asynchronous tasks safely with idempotency, upload media, poll for status and download results.
ReadGuides
Chat completions (LLM)
Call language models through an OpenAI-compatible endpoint with per-token billing from prepaid credits.
ReadReference
Errors
Every error code the API returns, what it means and what to do next.
ReadReference
Pricing
Read live task prices, lock a quote, and understand how prepaid credits move.
ReadReference
FAQ
Answers to common questions about tasks, retries, credits and file uploads.
ReadAI agents
MCP & Skill
Connect Claude Code, Codex or Cursor with one prompt and sign in with OAuth.
Read