Models
27 models, one API
Each model is named for its job and versioned (sieve-1). The bare name (sieve) always points at the newest version; pin the number in production.
Understand text
Language, sentiment, emotions, entities, topics and your own labels.Lingo
lingo-1
Language detection. Which language is this? 183 of them, from a few words up.
$0.02 per 1,000 texts
Tone
tone-1
Sentiment analysis. Positive, neutral or negative, in 30+ languages.
$0.02 per 1,000 texts
Mood
mood-1
Emotion detection. 28 emotions, plus the six basic ones, in one call.
$0.02 per 1,000 texts
Spot
spot-1
Named entity recognition. People, organizations and places, with character offsets.
$0.02 per 1,000 texts
Sort
sort-1
Zero-shot classification. Classify text into your own labels. No training.
$0.01 per 1,000 label checks
Topic
topic-1
Topic and format classification. What a page is about and what kind of page it is.
$0.02 per 1,000 texts
Route
route-1
Prompt task and complexity. Send easy prompts to a small model and hard ones to a big one.
$0.02 per 1,000 texts
Safety and trust
Toxicity, policy violations, prompt injection, PII, scams and unsupported claims.Sieve
sieve-1
Toxicity detection. Insults, threats and slurs flagged in milliseconds.
$0.02 per 1,000 texts
Warden
warden-1
Content safety policy check. 15 policy categories for prompts and LLM replies.
$0.03 per 1,000 texts
Moat
moat-1
Prompt injection detection. Catch "ignore previous instructions" before your agent reads it.
$0.02 per 1,000 texts
Veil
veil-1
PII detection and redaction. Find and mask 29 kinds of personal data.
$0.02 per 1,000 texts
Bait
bait-1
Phishing, scam and spam detection. Is this message a scam, spam or the real thing?
$0.04 per 1,000 texts
Ground
ground-1
Grounding check (hallucination detection). Does the source back up what your model said?
$0.04 per 1,000 sentences
Search and retrieval
Embeddings, reranking, keyphrases and emoji for search, RAG and recommendations.Atlas
atlas-1
Text embeddings. 384-dimension embeddings in 100 languages, OpenAI-compatible.
$0.005 per 1,000 texts
Ladder
ladder-1
Reranking. Put the best search result first. 100+ languages.
$0.01 per 1,000 documents
Pluck
pluck-1
Keyphrase extraction. The phrases a text is about, ready for tags and SEO.
$0.03 per 1,000 texts
Glyph
glyph-1
Emoji suggestions. The right emoji for a message, out of 1,800.
$0.01 per 1,000 texts
Write and restructure
Punctuation, summaries, titles and typed JSON from messy text.Comma
comma-1
Punctuation and capitalization. Fix lowercase, run-on text from speech and chat.
$0.02 per 1,000 texts
Brief
brief-1
Summarization. A few sentences that say what a long text says.
$0.30 per 1,000 summaries
Mold
mold-1
Structured extraction (JSON from text). Messy text in, JSON that matches your schema out.
$0.40 per 1,000 texts
Headline
headline-1
Title and description writing. A specific title, a one-line description and a URL slug.
$0.20 per 1,000 texts
Audio
Speech to text with word timestamps.Scribe
scribe-1
Speech to text. Transcripts with word timestamps, $0.001 a minute.
$0.001 per minute
Vision
Tags, text, objects, cutouts and NSFW checks for images.Prism
prism-1
Image tagging and image embeddings. Tag images with any labels, or embed them for search.
$0.10 per 1,000 images
Ink
ink-1
Text recognition (OCR). Every line of text in an image, with boxes.
$0.50 per 1,000 images
Scout
scout-1
Object detection. Find and count 80 kinds of objects, with boxes.
$0.30 per 1,000 images
Cutout
cutout-1
Background removal. Transparent PNG of the subject, background gone.
$2.00 per 1,000 images
Curtain
curtain-1
NSFW image detection. Keep explicit images out of your uploads.
$0.10 per 1,000 images