Skip to main content

1. Create an account

Sign up at app.infery.ai/register. Onboarding walks you through a workspace, a plan and an API key — and includes a card-verification step (no charge) that unlocks 50 trial credits, enough to try chat, a few images and some voice. Skip that step and you start at 0 credits instead.

2. Open the Studio

Once you’re in, the Studio is the first screen you see.
  • Type a prompt in the input at the bottom, pick a model (default: auto-routed) and press Enter.
  • Switch between Chat · Generate Image · Text to Speech · Speech to Text · Generate Video · Generate Music at the top.
  • Drop a PDF, image or audio file on the message box to attach it.
Your first chat becomes a Chat. Create a Project to group related chats and share settings. See Chats and Projects.

3. Create an API key

Go to API Keys (main navigation) and click Create key. Give it a name (“Production”, “Local dev”), copy the plaintext key — it’s only shown once. API keys look like:
Treat API keys as secrets. Never commit them to git. Revoke a key immediately if exposed — it takes ~5 seconds in the dashboard.

4. Make your first API call

Our gateway is OpenAI-compatible. Point the OpenAI SDK at https://api.infery.ai:
You’ll get back a standard OpenAI-format response with an added credits_used field carrying the cost in credits — inside the final SSE chunk instead, when streaming.
A Dashboard page reading Welcome to Infery Studio, with three cards: credits remaining 2,840, requests (30 days) 510, and active API keys 2. Below them a dual-axis 30-day usage chart — a blue Requests line (right axis, 0 to 60) and a green Credits line (left axis, 0 to 240) that closely track each other, both peaking around Aug 12, Aug 19 and most sharply Aug 25 — beside a Recent activity panel listing individual calls, most recent first: Seedream 4 (succeeded, 3.75 credits), GPT-5.5 (succeeded, 0.543088 credits), GPT-5.5 (succeeded, 13.926578 credits) and a fourth, partly visible, row.A Dashboard page reading Welcome to Infery Studio, with three cards: credits remaining 2,840, requests (30 days) 510, and active API keys 2. Below them a dual-axis 30-day usage chart — a blue Requests line (right axis, 0 to 60) and a green Credits line (left axis, 0 to 240) that closely track each other, both peaking around Aug 12, Aug 19 and most sharply Aug 25 — beside a Recent activity panel listing individual calls, most recent first: Seedream 4 (succeeded, 3.75 credits), GPT-5.5 (succeeded, 0.543088 credits), GPT-5.5 (succeeded, 13.926578 credits) and a fourth, partly visible, row.

The dashboard: balance, 30-day volume, and recent activity

Recent activity is the fastest way to confirm a call landed: it names the model, whether it succeeded, and what it cost, within seconds of the request — empty until your first Studio message or API call, then filling in most-recent-first as shown above.

5. Explore

Add teammates

Invite, assign roles, keep billing people out of your Studio.

Set a budget

Get notified by email when spend crosses a credit threshold you set.

Upload reusable files

POST /v1/files once, reference them by file_id forever.

Set up fallbacks

Route to a backup model automatically when the primary rate-limits.