Mistral OCR 4 (opens in new tab)

(I did work for one which had an office in Vancouver, instead; same tz.)

Was this... not basically a solved problem like 30 years ago? I'm pretty sure the shareware OCR tool that came with a black and white scanner I had at one point would do better than 20% wrong.

But with Gemini the API the model does do the OCR resulting in much better accuracy.

Opus 4.8 scanned hundreds of PDFs for me recently with the worst handwriting imaginable. 100% successful, other than one record where even I could not figure out what was written.

Been using Claude in parallele, it's better not not that much, just 10x (or 100x ?) more expensive.

For OCR?

Even if you are able to read someone's scratches, having a model to do the bulk lifting saves your eyes a lot of squinting. One thing that makes Transkribus useful for research vs a chat interface is that it can line up its interpretation alongside the original image so you can examine its work directly.

They won't have the capacity to be fed an image of handwritten text and say "Ahh, this is a note written by Winston Churchill!". You could very easily use these models and your agent framework of choice, like Hermes, the Segment Anything models, and other foss tooling to build a dedicated, specialist handwriting recognition system. Or facial recognition, or fingerprint recognition, etc - these sorts of things can be done very procedurally, without a lot of interpretive AI.

Mistral is just a bit more forward about this. I guess because they don't need/want to "wow" an audience with generalist user-facing tools (chat) that seem to be experts in everything (but in reality quite often will be a lot of such specialist models chained together).

Here, what you want, is really just a few python scripts away. Voxtral to turn your spoken prompt into text, piped into mistral large 3 with extra system prompts that creates a prompt for ocr and paths to files. It could do this in a loop to actually find those files. which you throw at ocr3, is pased back to misteal large 3 to interpret and turn into decisions.

This is common. It's rather uncommon, really, to build something like this using only one model for everything.

https://www.ssllabs.com/ssltest/analyze.html?d=mistral.ai&la...

Looks good so far, A+ on ipv4 as well as ipv6

Edit: I also asked Gemini 3.1 Pro to analyze the certificate and it looks good

It looks like you have shared an `about:certificate` URL containing a chain of three Base64-encoded X.509 TLS/SSL certificates. This specific chain is used to secure connections to *mistral.ai*.

Here is the decoded breakdown of the certificate chain you provided:

## Certificate Chain Overview

This is a standard three-tier certificate chain issued by Google Trust Services for the Mistral AI domain.

---

### 1. Leaf Certificate (End-Entity)

This is the specific certificate issued to the website to verify its identity and encrypt traffic.

* *Subject (Common Name):* `mistral.ai` * *Subject Alternative Names (SANs):* `mistral.ai`, `workers.mistral.ai` * *Issuer:* WE1 (Google Trust Services) * *Valid From:* June 13, 2026 * *Valid To:* September 11, 2026 * *Key Type:* Elliptic Curve (ECDSA)

### 2. Intermediate Certificate

This certificate acts as a bridge between the website's certificate and the trusted Root CA.

* *Subject:* WE1 (Google Trust Services) * *Issuer:* GTS Root R4 (Google Trust Services LLC) * *Valid From:* December 13, 2023 * *Valid To:* February 20, 2029 * *Key Type:* Elliptic Curve (ECDSA)

### 3. Root Certificate

This is the foundational trust anchor pre-installed in browsers and operating systems.

* *Subject:* GTS Root R4 (Google Trust Services LLC) * *Issuer:* GTS Root R4 (Self-signed) * *Valid From:* June 22, 2016 * *Valid To:* June 22, 2036 * *Key Type:* Elliptic Curve (ECDSA)

I'm personally using the small Qwen 3.5 models. If you have an OCR problem, Mistral OCR 4 is probably great. Open weights models that you can run on a laptop may also work great.