Build with our API.

Everything you can do in the web app you can do via the API. Same credits, same ABN employees and workflows, exposed as HTTPS endpoints under https://automatebusinessnow.com/api/v1. ABN handles execution internally; the API is service-native (e.g. image:generate), not model-native.

Use the key as an ABN app key

Your backend can use one abn_* key to power an entire application: employees, coding, images, video, voice, transcription, agents, jobs, credits, and short-lived client tokens. Call the ABN capability endpoint that matches the product action and send intent fields. ABN handles the underlying model/runtime work internally.

If a field is not documented for an ABN endpoint, do not send it. The standard app API does not accept modelId, provider, or vendorApiKey routing fields. If you are building browser or mobile flows, keep the root abn_* key on your backend and mint scoped abnct_* client tokens with /v1/tokens/mint.

// Do: call an ABN capability with intent fields.
POST /api/v1/images
Authorization: Bearer abn_YOUR_KEY_HERE
{
  "prompt": "A pixel-art mushroom on cream paper",
  "aspectRatio": "1:1",
  "quality": "high",
  "style": "illustration"
}

// Not part of the standard app API:
// modelId, provider, vendorApiKey

Your first call

The status endpoint is unauthenticated - paste it into your terminal to confirm the API is reachable from your machine.

curl https://automatebusinessnow.com/api/v1/status

You should see something like:

{
  "ok": true,
  "service": "automatebusinessnow",
  "version": "v1",
  "timestamp": "2026-04-25T00:00:00.000Z"
}

Now run a real job. Replace abn_YOUR_KEY_HERE with a key from your API keys page.

curl https://automatebusinessnow.com/api/v1/chat \
  -H "Authorization: Bearer abn_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -H "X-Request-ID: req_your_trace_id_123" \
  -d '{
    "employeeSlug": "copywriter",
    "prompt": "Visitor asks whether Detroit Auto Parts has brake pads in stock",
    "latencyProfile": "website_chat",
    "responseFormat": "plain_text",
    "stream": true
  }'

Credits & billing

Every API call deducts from the same credit balance you see at /app/credits. Failed jobs auto-refund. Plan credits refresh monthly; top-up credits never expire.

Heads-up: when a single API key burns more than 100,000 credits in 60 seconds ($1,000/min sustained), the key is auto-revoked as a safety circuit. That ceiling sits well above any legitimate single-call cost, but it stops a runaway loop dead before it bleeds your balance. Generate a new key from /app/api-keys if it ever trips. For vetted high-volume accounts we lift the cap - email hello@automatebusinessnow.com.

All /v1/* endpoints (except /v1/status) require a bearer token. You can have an unlimited number of keys per account, name them per integration, and revoke them individually.

Creating keys

Open /app/api-keys in the web app, give your key a name ("Zapier", "internal-script", etc.), and copy the resulting abn_... string. Keys are shown once at creation and never again - store them in your secret manager.

Sending the bearer

Authorization: Bearer abn_YOUR_KEY_HERE

Anything else (no header, malformed prefix, revoked key) returns 401 { "ok": false, "error": "Unauthorized" }.

Every endpoint that runs a model accepts a synchronous call, but for production workloads the async submit-then-poll patternis cleaner: submit returns instantly with a job id, you poll a status endpoint until the result is ready - drop-in compatible with any poll-loop you've already written.

GET /v1/jobs/{id}

Single-shot poll. Non-blocking. Returns the current status; on completion finalizes the credit ledger atomically and returns the output URL. Subsequent polls of a completed job are idempotent - they re-read the cached terminal state, balance doesn't change.

curl https://automatebusinessnow.com/api/v1/jobs/abn_job_... \
  -H "Authorization: Bearer abn_YOUR_KEY_HERE"

While running:

{
  "ok": true,
  "jobId": "abn_job_...",
  "status": "running",
  "estimateCredits": 18,
  "createdAt": "..."
}

On completion:

{
  "ok": true,
  "jobId": "abn_job_...",
  "status": "completed",
  "outputUrl": "https://...png",
  "creditsUsed": 18,
  "balance": 18093,
  "createdAt": "...",
  "completedAt": "..."
}

On failure (credits auto-refunded):

{
  "ok": false,
  "jobId": "abn_job_...",
  "status": "failed",
  "error": "human-readable sentence",
  "creditsUsed": 0,
  "createdAt": "..."
}

Polling cadence: 4"8 seconds is plenty. Most image jobs land in 30"60s; longer agent runs vary by workflow.

Every endpoint accepts and returns application/json. Responses are always shaped { ok, ... } on success and { ok: false, error } on failure. Customer-debuggable responses include requestId and latencyMs; send X-Request-ID if you want ABN to echo your own trace id.

(no body)

{
  "ok": true,
  "employees": [
    {
      "slug": "copywriter",
      "name": "Copywriter",
      "scopeRequired": "employee:copywriter",
      "accessible": true,
      "responseFormats": ["markdown", "plain_text"]
    }
  ]
}

{
  "employeeSlug": "copywriter",
  "prompt": "Visitor asks whether Detroit Auto Parts has brake pads in stock",
  "imageUrl": null,
  "fileContext": null,
  "latencyProfile": "website_chat",
  "responseFormat": "plain_text",
  "stream": true
}

# stream=false response
{
  "ok": true,
  "employeeSlug": "copywriter",
  "kind": "text",
  "message": "1. \"Your inbox is leaking leads...\"\n2. ...",
  "imageUrl": null,
  "executionClass": "ai",
  "latencyProfile": "website_chat",
  "responseFormat": "plain_text",
  "requestId": "req_your_trace_id_123",
  "latencyMs": 1800,
  "creditsUsed": 1,
  "balance": 18119
}

# stream=true response
Content-Type: text/event-stream

event: start
data: {"ok":true,"employeeSlug":"copywriter","latencyProfile":"website_chat","requestId":"req_..."}

event: text
data: {"delta":"Your inbox is leaking leads...","requestId":"req_..."}

event: done
data: {"ok":true,"creditsUsed":1,"balance":18119,"requestId":"req_..."}

Streaming: set stream to true or send Accept: text/event-stream. The stream emits start, text, optional stage/image, terminal done, or terminal error. For website chat, set latencyProfile to website_chat, pair it with responseFormat plain_text, display a typing state, and log requestId for support.

{
  "prompt": "Minimalist logo for a coffee shop named Hearth",
  "aspectRatio": "1:1",
  "quality": "high",
  "style": "brand mark"
}

{
  "ok": true,
  "outputUrl": "https://...png",
  "creditsUsed": 8,
  "balance": 18111
}

{
  "text": "Hi, thanks for calling. How can I help you today?",
  "voice": "warm-female",
  "format": "mp3",
  "model": "fast"
}

Streamed audio bytes (Content-Type: audio/mpeg or audio/L16).
Headers: X-Credits-Used, X-Voice-Format.

Catalog voices: warm-female, deep-male, energetic-female,
  british-male, young-female, podcast-host.
Formats: mp3 (default) | pcm_16000 (telephony pipelines).
Models:  fast (~300ms TTFB) | quality (better prosody, slower).
Billing: 1 credit per 50 chars on fast,
         1 credit per 25 chars on quality.

# multipart/form-data
audio:    <binary mp3/wav/m4a/ogg/webm>
language: en          # optional - auto-detect if omitted
diarize:  true        # optional - speaker labels per word

{
  "ok": true,
  "text": "the full transcript here",
  "words": [
    { "word": "the",  "start": 0.12, "end": 0.18 },
    { "word": "full", "start": 0.18, "end": 0.42 }
  ],
  "languageCode": "en",
  "durationSeconds": 12.4,
  "creditsUsed": 7
}

Billing: 1 credit per 2 seconds of audio (~$18/hr retail).

POST https://automatebusinessnow.com/api/v1/voice/synthesize
Headers:  Authorization: Bearer abn_live_xxx
Body:     { text, voice: "warm-female", format: "mp3", model: "fast" }

POST https://automatebusinessnow.com/api/v1/voice/transcribe
Headers:  Authorization: Bearer abn_live_xxx
Form:     audio=<bytes>     # field name is "audio", not "file"

{
  "input": "Process new leads in HubSpot from today"
}

{
  "ok": true,
  "runId": "run_3a8b...",
  "status": "queued"
}

(no body)

{
  "ok": true,
  "balance": 18121
}

(no body)

{
  "ok": true,
  "service": "automatebusinessnow",
  "version": "v1",
  "timestamp": "2026-04-25T00:00:00.000Z"
}

Every endpoint has a per-key rate limit. The cap scales with your plan tier - Power users get 10x the Free baseline. When you exceed it, the response is 429 Rate limit exceeded and your credits are not charged.

Every error response is JSON-shaped. The HTTP status tells you the category; the error field is a stable machine code (e.g. scope_required) that your handler can switch on; the hint field is a human-readable sentence safe to surface in your UI; some errors include extra fields (e.g. scope, requiredScope, capCredits) you can use to render a tailored error or upsell.

{
  "ok": false,
  "error": "scope_required",
  "code": "scope_required",
  "message": "This key does not hold image:generate.",
  "requestId": "req_01HX...",
  "latencyMs": 14,
  "scope": "image:generate",
  "hint": "Your key isn't approved for image generation yet.",
  "upgradeUrl": "/app/api-keys"
}

HTTP status reference

Error code reference

Use the error string to branch your handler - HTTP statuses collapse several distinct conditions into a single number.

{
  "ok": false,
  "error": "scope_required",
  "scope": "image:generate",
  "upgradeUrl": "/app/api-keys"
}

{
  "ok": false,
  "error": "verified_org_required",
  "hint": "Add a payment method or verify your domain to enable this capability.",
  "verifyUrl": "/app/billing#verify-org"
}

{
  "ok": false,
  "error": "end_user_id_required",
  "hint": "Send X-ABN-End-User-ID: <stable opaque id> on every call."
}

{
  "ok": false,
  "error": "end_user_id_invalid",
  "hint": "End-user ids must be 1"128 printable ASCII characters."
}

{
  "ok": false,
  "error": "origin_not_allowed",
  "hint": "This token cannot be called from the requesting origin."
}

{
  "ok": false,
  "error": "capability_unavailable",
  "capability": "image:generate",
  "hint": "This capability isn't available on your key right now."
}

{
  "ok": false,
  "error": "capability_temporarily_unavailable",
  "capability": "video:generate",
  "hint": "This capability is in limited release on partner API keys while ABN finalizes the underlying service agreement."
}

{
  "ok": false,
  "error": "key_daily_cap_exceeded",
  "capCredits": 5000,
  "spentToday": 5020,
  "estimate": 8
}

{
  "ok": false,
  "error": "key_monthly_cap_exceeded",
  "capCredits": 50000,
  "spentMonth": 50020,
  "estimate": 8
}

{
  "ok": false,
  "error": "cap_check_failed",
  "hint": "Retry after a few seconds."
}

{
  "ok": false,
  "error": "unauthorized",
  "hint": "Send Authorization: Bearer abn_... or a valid abnct_... token."
}

{
  "ok": false,
  "error": "unknown_employee",
  "code": "unknown_employee",
  "message": "Unknown employee slug: parts-agent. Call /api/v1/employees to list valid slugs.",
  "employeeSlug": "parts-agent",
  "requestId": "req_01HX...",
  "latencyMs": 3
}

{
  "ok": false,
  "error": "invalid_response_format",
  "code": "invalid_response_format",
  "message": "responseFormat must be markdown or plain_text.",
  "requestId": "req_01HX...",
  "latencyMs": 2
}

{
  "ok": false,
  "error": "invalid_latency_profile",
  "code": "invalid_latency_profile",
  "message": "latencyProfile must be standard or website_chat.",
  "requestId": "req_01HX...",
  "latencyMs": 2
}

{
  "ok": false,
  "error": "unsupported_routing_field",
  "fields": ["modelId"],
  "hint": "ABN service endpoints accept intent fields only."
}

We don't ship a vendor SDK - every endpoint is plain HTTPS JSON, so any HTTP library works. We do publish two integration surfaces for AI tools:

• OpenAPI 3.1 spec at /api/v1/openapi- feed it to ChatGPT custom GPTs, Postman, or any tool-calling agent.
• MCP server config for Claude Desktop, Cursor, and other MCP-aware clients. Drop the snippet into your mcp.json and your AI assistant can call us directly. See /developers for the full config.