Claude Fable 5.2 is the strongest model for reading scans and images. GPT-6.1 Terra extracts text for 5% of the cost, and Kimi K3.1 Pro answers fastest.
Claude Fable 5.2 is the strongest model for reading scans and images. GPT-6.1 Terra extracts text for 5% of the cost, and Kimi K3.1 Pro answers fastest.
32 models · Updated November 2026 · Data from Artificial Analysis
Claude Fable 5.2
Anthropic · Max effort
The highest score of any model that accepts images at this setting.
GPT-6.1 Terra
OpenAI · Max effort
79% of Claude Fable 5.2's score for 5% of the cost.
Kimi K3.1 Pro
Moonshot AI · Standard effort
The quickest full answer from a model scoring 46 or more.
Over 45 s at every tested setting
Claude Fable 5.2
Anthropic · Max effort
The highest score of any model that accepts images at this setting.
GPT-6.1 Terra
OpenAI · Max effort
79% of Claude Fable 5.2's score for 5% of the cost.
Kimi K3.1 Pro
Moonshot AI · Standard effort
The quickest full answer from a model scoring 46 or more.
Each job favors a different model. Pick the one closest to yours.
Messy scans, handwriting and tables
Use
Claude Fable 5.2
Anthropic · Max effort
The strongest reasoning of any model that reads images, which helps most when the layout is complicated or the writing is hard to make out. $173 per 1,000 pages.
Messy scans, handwriting and tables
Use Claude Fable 5.2
The strongest reasoning of any model that reads images, which helps most when the layout is complicated or the writing is hard to make out. $173 per 1,000 pages.
Digitizing thousands of pages
Use GPT-6.1 Terra
$8.38 per 1,000 pages.
Receipts and IDs in a live app
Use Kimi K3.1 Pro
Reads a page in about 85 seconds for $26.60 per 1,000 pages. With every model held to answers under 45 seconds, GPT-6 Astra is quickest, at about 22 seconds for a score of 51.6.
Clean printed text on a tight budget
Use Muse Ember
$1.06 per 1,000 pages, the cheapest paid option. Fine for clear print; check a sample before trusting it with handwriting.
Staying with Google
Use Gemini 4 Carbon
Google's strongest current model for this, at 60 and $49.40 per 1,000 pages.
Whole PDFs, invoices and forms
Pulling specific fields out of multi-page documents is its own job, with its own ranking.
Understanding charts and photos
Explaining what an image shows needs more reasoning than reading its text.
Each dot is a model. Higher scores better, further left is cheaper, so the best deals sit top left. The cost axis is logarithmic: every step left is a big saving. Hover a dot for its numbers.
Sort by the pillar you care about, and set your monthly volume to see the bill. Costs include each model's thinking tokens at the setting shown.
Gemini 4 Carbon. It scores 60 to Gemini 4 Hydrogen's 53.9 and costs $49.40 per 1,000 pages at high effort. Gemini 4 Hydrogen costs $22.18, so it's the one for high volume if its lower score is enough.
Thinking helps with messy layouts, tables and handwriting. It helps much less with clean printed text, and every thinking token is billed.
For plain text extraction, start each model at its lowest reasoning setting, check a sample of pages, and raise the setting only where the output slips. Our costs assume max effort, so a low setting will come in well under the prices shown.
Every model on this page accepts image input. We rank each model at max effort, the setting that gives its best score and the one Artificial Analysis and the labs quote. Cost and answer time are shown at that same setting, so you can see what the top score costs. Claude Fable 5.2 takes about 4 minutes per answer at max effort and costs $173 per 1,000 pages. At high effort it answers in 36 seconds for $74.80 and scores 61.8 instead of 64.6. Switch to Answers under 45 s above to see each model at its strongest setting that gives a full answer within 45 seconds. Effort labels mean different things at different labs, so that view picks each setting by wait time, not by name.
Intelligence is the Artificial Analysis Intelligence Index at that setting. No public OCR benchmark covers every current model, so we rank on general intelligence and show cost per page and speed next to it. Accuracy on your own scans can differ, so test a sample before you commit.
Cost starts from a typical page: 3,000 input tokens for the image and your prompt, and 2,000 output tokens for the text. We scale the output by how much each model wrote, thinking included, in Artificial Analysis's tests, so a model that thinks a lot pays for it.
Speed is the median time to a full answer in the same tests.
Best value is the most intelligence per dollar and fastest is the quickest full answer, both among models scoring 46 or more (within 30% of the leader). Neither pick goes to a model its maker has replaced.
Claude Fable 5.2 is the strongest model that reads images (64.6 on the Artificial Analysis Intelligence Index at max effort), at about $173 per 1,000 pages. For volume, GPT-6.1 Terra costs $8.38 per 1,000 pages. No public OCR benchmark covers every model, so test a sample of your own documents.
Gemini 4 Carbon. It scores 60 to Gemini 4 Hydrogen's 53.9 and costs $49.40 per 1,000 pages at high effort. Gemini 4 Hydrogen costs $22.18, so it's the one for high volume if its lower score is enough.
Muse Ember, at about $1.06 per 1,000 pages (list price $0.10/$0.50 per million tokens). It's fine for clean print. Inkling 2 Small is free on OpenRouter, but the free tier is rate-limited.
Kimi K3.1 Pro, at about 85 seconds per page at standard effort. With every model held to answers under 45 seconds, GPT-6 Astra is quickest, at about 22 seconds for a score of 51.6.
Not for clean printed text. Reasoning helps with handwriting, tables and complicated layouts. Start with a low setting and raise it only where the output slips, since thinking tokens are billed.
Answer three questions and get a pick for each part of your workload, with the monthly cost.