DocumentationQuickstart

A clean API for the Inferfare model.

Generate an Inferfare virtual key once, then use the standard OpenAI Chat Completions interface from your app, agent, SDK, or compatible client.

Local setup The examples use https://api.inferfare.com/v1. In production, replace it with your public Inferfare gateway domain.

01 / SET UP

Get ready in three steps

Choose a planSign in and select Starter, Pro, or Scale. Each includes monthly Inferfare model credit.

Create a virtual keyOpen Settings → API keys and generate a key for your application.

Make a requestUse that key as a Bearer token and set model to orbit.

02 / MAKE A REQUEST

Chat Completions

Send a standard OpenAI-compatible request to POST https://api.inferfare.com/v1/chat/completions. Responses use the familiar choices[0].message.content shape.

curl https://api.inferfare.com/v1/chat/completions \
  -H "Authorization: Bearer $INFERFARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "orbit",
    "messages": [
      { "role": "user", "content": "Write a launch note for Inferfare." }
    ]
  }'

03 / KEEP YOUR SDK

Use the OpenAI SDK you already have

Set the SDK base URL to https://api.inferfare.com/v1 and use an Inferfare virtual key. No provider secret belongs in your application code.

Keep INFERFARE_API_KEY in your server-side environment or a secure secret manager. Never expose it in a browser bundle or commit it to source control.

04 / DISCOVER MODELS

List models available to your key

Use GET /v1/models to confirm that the key is valid and see the model IDs your application can call. The included model is orbit. Models you add in the Inferfare workspace remain private to that workspace and are not exposed by your public virtual key.

curl https://api.inferfare.com/v1/models \
  -H "Authorization: Bearer $INFERFARE_API_KEY"

05 / VIRTUAL KEYS

Use a key per app or environment

Virtual keys identify the calling application and apply your Inferfare entitlement. Generate a separate key for production, staging, agents, or internal tools; revoke a key immediately if it is no longer needed.

Open API key settings

06 / MODEL CONNECTIONS

Add your own provider or deployment

In Settings → Connections, add a model from OpenAI, Anthropic, Google AI Studio, Groq, Mistral, or an OpenAI-compatible deployed endpoint. Inferfare validates the connection before saving it, then makes it available in the workspace model picker. Your provider credential stays server-side and the provider charges remain with that provider.

Connected models use the provider account you add. Inferfare model credit applies only to the included orbit model.

07 / CREDIT & BILLING

Understand model credit

Starter includes $10, Pro includes $50, and Scale includes $150 of Inferfare model credit per monthly billing period. The workspace shows the remaining balance; add credit when more Inferfare usage is needed.

Local preview can activate a plan for testing. Production must activate entitlements only after a verified payment-gateway webhook; invoice settlement is handled by that gateway and your billing system.

CURSOR / OPENAI-COMPATIBLE CLIENTS

Connect a compatible client

In your client's custom OpenAI provider settings, use Base URL https://api.inferfare.com/v1, your Inferfare virtual key, and model ID orbit. The same values work for other OpenAI-compatible tools.

08 / TROUBLESHOOT

Common responses

401

Invalid Inferfare API keyGenerate a new active virtual key and send it as a Bearer token.

400

Model unavailable for this keyUse the exact model ID returned by GET /v1/models.

429

No Inferfare credit remainingAdd credit or wait for the next active billing period.