Infer API · live

One API. Four price options.

Infer provides one Responses-compatible API with private supply, locked prices, spending limits, a prepaid balance, and clear receipts.

Quickstart

Go from a new account to the first API request:

1. Create an account, then confirm the one-time verification link sent by Infer.
2. Open Wallet and add at least $20 of wallet credit through checkout.
3. Open API keys, create an API key, and copy it when shown. Set the copied value as INFER_API_KEY in your local shell or secret manager; never put it in a URL, repository, or chat.
4. Send the Responses request below. The selected model must show as available on current status.

curl https://infer.flow7.org/v1/responses \
  -H "Authorization: Bearer $INFER_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: first-request" \
  -d '{
    "model": "infer/claude-haiku-4-5:balanced",
    "input": "Create a typed retry helper with exponential backoff.",
    "max_output_tokens": 1200,
    "relay": {
      "session_id": "repo-acme-42",
      "privacy": "standard"
    }
  }'

Price options

The customer-facing options are Low cost, Balanced, Stable, and Official API. Their API suffixes are :low-cost, :balanced, :stable, and :official. Official API is available only when an exact first-party route has passed verification.

Model IDs

A model ID combines the model name and price option. Exact model IDs stay within that model family. Dynamic model IDs return the model that actually ran in the response metadata.

Responses API

Infer returns the normal model response plus the selected price option, final charge, token usage, and receipt under relay. The serving supply identity is never returned.

{
  "id": "resp_…",
  "object": "response",
  "status": "completed",
  "model": "infer/gpt-5.6-terra:balanced",
  "output_text": "…",
  "usage": {
    "input_tokens": 8240,
    "input_tokens_details": {"cached_tokens": 7100},
    "output_tokens": 932
  },
  "relay": {
    "receipt_id": "rcpt_…",
    "price_version": "pv_…",
    "tier": "balanced",
    "resolved_model_class": "GPT-5.6 Terra",
    "cache_status": "partial",
    "environment": "live",
    "provider_disclosed": false,
    "customer_cost_usd": 0.004992
  }
}

How requests are routed

• The API key type, model ID, routing option, and price are locked before the request starts.
• Infer checks model support, context size, privacy needs, current health, and price before choosing a route.
• When a client supplies relay.session_id, the session stays on the same route while that route remains healthy.
• Retries stay within the selected option’s price and reliability limits.
• The supplier and exact route remain private.

Billing and receipts

Customers fund a prepaid Infer service-credit wallet through secure checkout with no separate Infer checkout fee. The first funding minimum is $20 and later reloads are $50. Applicable tax may be added separately. Wallet credit becomes available only after payment is confirmed. Before a request starts, Infer temporarily holds the maximum estimated cost. After it finishes, Infer charges the actual amount and immediately returns the rest to the wallet. Inspect a completed receipt locally.

Errors