Clairic
Cloudflare extraction model that returns typed values with confidence scores instead of text
Context window
65,536
Input / 1M tokens
$0.10
Output / 1M tokens
N/A (no generated text)
Provider
Cloudflare
Priced per input token only: it returns typed values in one forward pass and generates no tokens, so there is no output charge. Preview on Cloudflare Workers AI; Cloudflare calls the current endpoint an early checkpoint. · Data verified 2026-10-23
Clairic (October 19, 2026) is an extraction model from Cloudflare, in preview on Workers AI. You pass messy input such as an email, a receipt photo or a CSV together with a list of typed fields, and it returns one typed value per field (text, number, date, duration, list, estimate or forecast) with a confidence score, in a single pass and without generating text. It accepts up to four images per request and costs $0.10 per million input tokens.
Capability index
Relative estimates (0-100) to place this model against its peers, grounded in published benchmarks.
How to access it
Preview on Cloudflare Workers AI (model ID @cf/cloudflare/clairic), through a Workers AI binding or the REST API.
Strengths
- ✓Very low price ($0.10 per 1M input tokens, no output charge)
- ✓Typed outputs with confidence scores and a null probability per field
- ✓Vision input (up to four images per request)
- ✓Single forward pass, faster than prompting an LLM for extraction
Best for developers who...
Benchmarks
| Benchmark | Score | Notes |
|---|---|---|
| Cloudflare test pipeline | 69% faster, 49% cheaper | Cloudflare-reported, versus the same pipeline using an LLM at every step (19.3s vs 61.7s) |
Source: Cloudflare changelog
Compare Clairic
Compare Clairic with any other model
Build a comparison →All model comparisons →