Best AI model for invoices and document processing

One job here means a two-page invoice or form read; the fields pulled out. Costs use each vendor’s list price; a product built on the model charges its own price on top. See every model and job.

1. 1

   Claude Haiku 5.5 · Anthropic

   The pick for high-volume routine work: a twentieth of Claude Sonnet 5.5's list price, with users reporting near-perfect sorting in production, as long as each request stays short.

   $0.35 per 1,000 documents processedScore 73 of 100High-volume workIntelligence Index 36$0.10 read · $0.50 written per 1M tokensReads 1M tokens at once

   Caveat: The price is five times higher on any request that feeds it more than 100,000 tokens of text at once (a long document or a long back-and-forth).

2. 2

   Gemini 3.8 Flash · Google

   Fast and well liked in blind votes for the money, at under half the list price of Gemini 4 Argon, but users report more made-up answers than rivals and Google doubles the price on 1 January 2027.

   $2.63 per 1,000 documents processedScore 65 of 100High-volume workIntelligence Index 31$0.75 read · $3.75 written per 1M tokensReads 1M tokens at once

   Caveat: $0.75 in / $3.75 out per million tokens (the unit vendors bill by) is introductory; Google's pricing page says $1.50 / $7.50 from 1 January 2027.

3. 3

   GPT-6 Luna · OpenAI

   OpenAI's cheapest model, at the same list price as Claude Haiku 5.5 but eight points behind it on Artificial Analysis's index (28 against 36).

   $0.35 per 1,000 documents processedScore 64 of 100High-volume workIntelligence Index 28$0.10 read · $0.50 written per 1M tokensReads 1M tokens at once

   Caveat: It ranks 14th largely because price is 30% of the board's score; its test result is low (28 on the index, down from 38 when Artificial Analysis rebuilt it).

4. 4

   DeepSeek V4.1 Flash (1017) · DeepSeek

   About a seventh of Kimi K3.1 Pro's list price for 33 on Artificial Analysis's index, and now sold by Google's and Microsoft's clouds as well as DeepSeek itself.

   $0.96 per 1,000 documents processedScore 62 of 100High-volume workIntelligence Index 33$0.30 read · $1.20 written per 1M tokensReads 1M tokens at once

   Caveat: DeepSeek's own service is in China and charges more at peak hours: $0.15 to $0.30 in and $0.60 to $1.20 out per million tokens. Read its data terms, or buy through a US cloud.

5. 5

   Gemini 3.5 Flash-Lite · Google

   Google's model for sorting and extraction at volume: the fastest measured on the board at about 430 tokens (word-pieces) a second, but 12 on Artificial Analysis's index means no judgement calls.

   $1.35 per 1,000 documents processedScore 57 of 100High-volume workIntelligence Index 12$0.30 read · $2.50 written per 1M tokensReads 1M tokens at once

   Caveat: Its output price ($2.50 per million tokens) is five times that of GPT-6 Luna or Claude Haiku 5.5: you are paying for speed.

6. 6

   Amazon Nova 2 Lite · Amazon

   Amazon's own low-cost model, sold only on Amazon Bedrock: a reasonable default for routine work if you are already there, but it has no current independent test score.

   $1.35 per 1,000 documents processedScore 37 of 100High-volume work$0.30 read · $2.50 written per 1M tokensReads 1M tokens at once

   Caveat: No independent score: Artificial Analysis lists it unscored on its rebuilt index, so it ranks below every measured model until someone tests it.

7. 7

   GPT-6.1 Sol · OpenAI

   The sensible OpenAI default: 55 on Artificial Analysis's index against 57 for GPT-6 Astra, at a fifth of Astra's list price.

   $7 per 1,000 documents processedScore 70 of 100Everyday defaultIntelligence Index 55$2 read · $10 written per 1M tokensReads 1M tokens at once

   Caveat: Two points separate it from Astra on the index, which is within noise; test Astra only where Sol's answers fall short.

8. 8

   Claude Sonnet 5.5 · Anthropic

   A sound everyday default: 55 on Artificial Analysis's index, four points behind Claude Opus 5.5, at half its list price.

   $7 per 1,000 documents processedScore 66 of 100Everyday defaultIntelligence Index 55$2 read · $10 written per 1M tokensReads 1M tokens at once

   Caveat: The saving depends on the effort setting: at the top setting Artificial Analysis's test run cost $10.02 per task, level with Opus 5.5 ($10.04).

9. 9

   GPT-6.1 Terra · OpenAI

   Half the list price of GPT-6.1 Sol for four points less on Artificial Analysis's index (51 against 55): the cheaper OpenAI default where the work is routine.

   $3.50 per 1,000 documents processedScore 65 of 100Everyday defaultIntelligence Index 51$1 read · $5 written per 1M tokensReads 1.05M tokens at once

   Caveat: Requests that feed it more than 272,000 tokens of text at once are billed at twice the input price and 1.5 times the output price, per OpenAI.

10. 10

    Qwen3.8 Max · Alibaba

    Alibaba's hosted flagship scores 34 on Artificial Analysis's index, a little above the open models GLM-5.3 (32) and MiMo-V2.6-Pro (30), at about 1.4 times GLM's list price and about five times MiMo's.

    $5.80 per 1,000 documents processedScore 63 of 100Everyday defaultIntelligence Index 34$2 read · $6 written per 1M tokensReads 984K tokens at once

    Caveat: The hosted model is closed; the open version is a different model that Artificial Analysis has not scored and that needs data-centre hardware.

11. 11

    Muse Spark 1.3 · Meta

    Meta's earlier everyday model: near the top of Scale's test of replies to people in distress (84.88) but mid-table on hard exams, with no vendor list price on record.

    No list price publishedScore 59 of 100Everyday default$0.78 per 1M tokens, typical mix (estimate)

    Caveat: No vendor list price was found; the board uses Artificial Analysis's blended figure of $0.78 per million tokens from 10 October.

12. 12

    Mistral Large 4 · Mistral AI

    The European option: about a quarter of Claude Sonnet 5.5's list price and free to host yourself, but independent scores are mid-table (26 on Artificial Analysis's index).

    $2.03 per 1,000 documents processedScore 58 of 100Everyday defaultIntelligence Index 26$0.70 read · $2.10 written per 1M tokensReads 524K tokens at once

    Caveat: Free to use and build on, but a business that resells the model as a service needs a separate commercial licence from Mistral.

13. 13

    Grok 4.7 · xAI

    Carried by all three big clouds and listed by xAI at $2 in / $6 out per million tokens (the unit vendors bill by), but mid-table: 35 on Artificial Analysis's index against 55 for GPT-6.1 Sol.

    $5.80 per 1,000 documents processedScore 52 of 100Everyday defaultIntelligence Index 35$2 read · $6 written per 1M tokensReads 500K tokens at once

    Caveat: It can read half as much text at once as most models on this board.

Every figure links to its source on the model profile pages. Vendor figures are labelled as vendor figures and never counted as independent tests.