Pay for calls, not seats.
Add credit from $5. It never expires. Each call draws down the balance by its listed price, and the response tells you exactly what it cost. No subscription, no minimum spend, no charge for failed calls.
Top up
$5, $10, $25 or $100, or any amount up to $1,000. Card or Link through Stripe.
Auto top-up
Optional. When your balance drops below a threshold you pick, we charge your saved card back up to your target, before calls start failing.
Caps
A monthly cap for the account and a monthly limit per API key, so a runaway loop stops instead of draining your card.
| Model | Job | Price | How units count |
|---|---|---|---|
| Lingo lingo-1 | Language detection | $0.02 per 1,000 texts | One unit per text up to 2,000 characters; longer texts are split into 2,000-character chunks and each chunk is a unit. |
| Tone tone-1 | Sentiment analysis | $0.02 per 1,000 texts | One unit per text up to 2,000 characters; longer texts are split into 2,000-character chunks and each chunk is a unit. |
| Mood mood-1 | Emotion detection | $0.02 per 1,000 texts | One unit per text up to 2,000 characters; longer texts are split into 2,000-character chunks and each chunk is a unit. |
| Spot spot-1 | Named entity recognition | $0.02 per 1,000 texts | One unit per text up to 2,000 characters; longer texts are split into 2,000-character chunks and each chunk is a unit. |
| Sort sort-1 | Zero-shot classification | $0.01 per 1,000 label checks | One unit per label per text: classifying one text into 5 labels is 5 units ($0.00005). |
| Topic topic-1 | Topic and format classification | $0.02 per 1,000 texts | One unit per text up to 2,000 characters; longer texts are split into 2,000-character chunks and each chunk is a unit. |
| Route route-1 | Prompt task and complexity | $0.02 per 1,000 texts | One unit per text up to 2,000 characters; longer texts are split into 2,000-character chunks and each chunk is a unit. |
| Sieve sieve-1 | Toxicity detection | $0.02 per 1,000 texts | One unit per text up to 2,000 characters; longer texts are split into 2,000-character chunks and each chunk is a unit. |
| Warden warden-1 | Content safety policy check | $0.03 per 1,000 texts | One unit per text up to 4,000 characters; longer texts are split into 4,000-character chunks and each chunk is a unit. |
| Moat moat-1 | Prompt injection detection | $0.02 per 1,000 texts | One unit per text up to 4,000 characters; longer texts are split into 4,000-character chunks and each chunk is a unit. |
| Veil veil-1 | PII detection and redaction | $0.02 per 1,000 texts | One unit per text up to 2,000 characters; longer texts are split into 2,000-character chunks and each chunk is a unit. |
| Bait bait-1 | Phishing, scam and spam detection | $0.04 per 1,000 texts | One unit per text up to 2,000 characters; longer texts are split into 2,000-character chunks and each chunk is a unit. |
| Ground ground-1 | Grounding check (hallucination detection) | $0.04 per 1,000 sentences | One unit per sentence of the answer checked against the context. |
| Atlas atlas-1 | Text embeddings | $0.005 per 1,000 texts | One unit per text up to 2,000 characters; longer texts are truncated, and billed one unit per started 2,000 characters. |
| Ladder ladder-1 | Reranking | $0.01 per 1,000 documents | One unit per document reranked. |
| Pluck pluck-1 | Keyphrase extraction | $0.03 per 1,000 texts | One unit per started 2,000 characters. |
| Glyph glyph-1 | Emoji suggestions | $0.01 per 1,000 texts | One unit per text. |
| Comma comma-1 | Punctuation and capitalization | $0.02 per 1,000 texts | One unit per text up to 2,000 characters; longer texts are split into 2,000-character chunks and each chunk is a unit. |
| Brief brief-1 | Summarization | $0.30 per 1,000 summaries | One unit per started 3,000 characters of input. |
| Mold mold-1 | Structured extraction (JSON from text) | $0.40 per 1,000 texts | One unit per started 2,000 characters of input. |
| Headline headline-1 | Title and description writing | $0.20 per 1,000 texts | One unit per started 2,000 characters of input. |
| Scribe scribe-1 | Speech to text | $0.001 per minute | Billed per second of audio, rounded up, at least one second. |
| Prism prism-1 | Image tagging and image embeddings | $0.10 per 1,000 images | One unit per image; every 10 `texts` add one unit. |
| Ink ink-1 | Text recognition (OCR) | $0.50 per 1,000 images | One unit per image. |
| Scout scout-1 | Object detection | $0.30 per 1,000 images | One unit per image. |
| Cutout cutout-1 | Background removal | $2.00 per 1,000 images | One unit per image. |
| Curtain curtain-1 | NSFW image detection | $0.10 per 1,000 images | One unit per image. |
What things cost
Moderate 1 million chat messages
Redact PII in 100,000 support tickets
Embed 1 million documents
Transcribe 100 hours of audio
Read 10,000 receipts
Extract JSON from 10,000 emails
Billing questions
Is there a free tier or trial?
No. Credit starts at $5 and it never expires. You can browse the playground's preset examples without an account.
Can a call cost more than I expect?
No. Before a call runs we hold its maximum cost (from the input size); you're billed the units it used, never more than that hold. POST /v1/estimate returns the maximum without running anything.
Do failed calls cost anything?
No. Errors, timeouts and anything we couldn't process are never charged.
How do I get receipts?
Stripe emails a receipt for every top-up and auto top-up. Your dashboard lists them with your usage by day and model.
Can I pay by invoice?
Not yet. Write to hello@greatwork.company if you need it.