3 extraction models, every provider
Each model is tested on every provider that serves it, because price, speed and limits differ from host to host.
- ClairicCloudflare · Text and images · closed weightsCloudflare's extraction model, in preview on Workers AI since 19 Oct 2026. It takes text and up to four images plus a map of typed fields and returns a value, a confidence and a probability the value is absent for each field. It charges $0.10 per million input tokens and nothing for output.
- NuExtract3NuMind · Text and images · open weightsNuMind's open vision-language extraction model, built on Qwen3.5-4B. It fills a JSON template from text or images. It returns no confidence and no character positions. It is served by NuMind's own API; we test it there, and optionally on our own Mac Mini, reported separately.
- GLiNER2Fastino · Text only · open weightsFastino's small open encoder for entity and structured extraction, about 200 to 290 million parameters, text only. It returns spans with confidence scores. It can't read images or compute values that aren't printed, so those measurements show not supported rather than a score.
Every model on every provider
| Model | Input | Weights | Provider | List price | Status |
|---|---|---|---|---|---|
| ClairicCloudflare | Text and images | Closed | Cloudflare Workers AIserverless | $0.10 per million input tokens, no output charge | Not run yet |
| NuExtract3NuMind | Text and images | Open, Apache 2.0 | NuMind APIserverless | $1 per million input tokens, $5 per million output tokens | Not tested yet: needs an account |
| Hugging Face Inference Endpointsdedicated | per GPU hour | Not tested yet: needs an account | |||
| Our Mac Mini (run it yourself)self-run | no per-document price | Optional, after hosted results | |||
| GLiNER2Fastino | Text only | Open, Apache 2.0 | Fastino APIserverless | $0.03 per million input tokens, no output charge | Not tested yet: needs an account |
| Hugging Face Inference Endpointsdedicated | per CPU hour | Not tested yet: needs an account | |||
| Our Mac Mini (run it yourself)self-run | no per-document price | Optional, after hosted results |
Not tested yet
- NuExtract 2.0 (2B and 8B): no ready hosted API; needs a dedicated Hugging Face endpoint.
- Clairic open weights: not released yet.
As of 20 Oct 2026, extractingbench has not published results. The planned lineup is Clairic, NuExtract3 and GLiNER2. Before this benchmark, every published accuracy figure we could find for these extraction models came from the vendors themselves.