Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

today, we're launching Light Parse Extend can now parse documents up to 70% cheaper than other solutions - light parse starts at $0.00625 per page, and scales down significantly with volume discounts - it's SOTA on Databricks OfficeQA Pro (a 3rd party agent benchmark) among all non-agentic parsing providers... show more

Kushal Byatnal

7,813 subscribers

57,730 Aufrufe • vor 2 Monaten •via X (Twitter)

Wissenschaft & Technologie Nachrichten & Politik

Anya Rossi• Live Now

Private livecam show

45 Kommentare

Profilbild von Kushal Byatnal

Kushal Byatnalvor 2 Monaten

light parse outperforms and outprices alternatives on document parsing Databricks OfficeQA Pro is a benchmark that measures how accurately an LLM can answer questions from scanned U.S. government financial documents this benchmark is truly independent. we ran the evaluation against it, but we had no part in designing it (nor did we commission it)

Profilbild von Ammaar Reshi

Ammaar Reshivor 2 Monaten

whenever I see kb in a video, I’m airplaying it to my TV

Profilbild von Kushal Byatnal

Kushal Byatnalvor 2 Monaten

filming this video is what convinced me to go get a haircut

Profilbild von Ammaar Reshi

Ammaar Reshivor 2 Monaten

I don’t see the difference

Profilbild von Davis Treybig

Davis Treybigvor 2 Monaten

Extend defining the full Pareto frontier for document processing!

Profilbild von Kushal Byatnal

Kushal Byatnalvor 2 Monaten

🫡

Profilbild von Pri

Privor 2 Monaten

Pleasure working on the launch video! 🔥

Profilbild von aiden brotman

aiden brotmanvor 2 Monaten

even more affordable and accurate? what can't extend do?

Profilbild von Darren Chow

Darren Chowvor 2 Monaten

@chaneratextend extend ml team is so cracked

Profilbild von Kushal Byatnal

Kushal Byatnalvor 2 Monaten

@chaneratextend wait until they see next weeks launch

Profilbild von bo lau

bo lauvor 2 Monaten

this is huge

Profilbild von Kushal Byatnal

Kushal Byatnalvor 2 Monaten

don't tell them what's coming next week

Profilbild von scott

scottvor 2 Monaten

mr krabs approves

Profilbild von Hansen Qian

Hansen Qianvor 2 Monaten

Congrats!!! Big accomplishment

Profilbild von Kushal Byatnal

Kushal Byatnalvor 2 Monaten

ty hansen!

Profilbild von Mike Bedarev

Mike Bedarevvor 2 Monaten

The Pareto Frontier had no idea what our next move was

Profilbild von Victor Dubeux

Victor Dubeuxvor 2 Monaten

light & cheap, let's go!!!!

Profilbild von James Russo

James Russovor 2 Monaten

Congrats on the launch!

Profilbild von Kushal Byatnal

Kushal Byatnalvor 2 Monaten

thanks James!

Profilbild von Jordan Meyer

Jordan Meyervor 2 Monaten

they said it couldn't be done

Profilbild von Kushal Byatnal

Kushal Byatnalvor 2 Monaten

that's because they've never met @ameyaajoshi and @joon_kim96

Profilbild von Cody

Codyvor 2 Monaten

ACORD forms?

Profilbild von Kushal Byatnal

Kushal Byatnalvor 2 Monaten

yup! very common use case for us

Profilbild von Pierre-Louis Vouteau

Pierre-Louis Vouteauvor 2 Monaten

@ycombinator Congrats!!

Profilbild von Kushal Byatnal

Kushal Byatnalvor 2 Monaten

@ycombinator thank you! we are big fans of @Ooakdata btw 🔥

Profilbild von Guhan

Guhanvor 2 Monaten

Congrats to your team. Cost really matters; I am currently using LlamaParse. Would you be able to explain how your product works? Is it agentic because I am working on legal workflows that need pure reflection rather than interpretation?

Profilbild von John Wei

John Weivor 2 Monaten

congrats, lfg!

Profilbild von Arvind

Arvindvor 2 Monaten

🔥 always cooking

Profilbild von Kushal Byatnal

Kushal Byatnalvor 2 Monaten

a true chef never stops

Profilbild von Gordon Wintrob

Gordon Wintrobvor 2 Monaten

Congrats Kushal and team!! ⚡️⚡️⚡️

Profilbild von Launch Archive

Launch Archivevor 2 Monaten

Light Parse offers a cost-effective solution for document parsing, making it easier for developers to manage large data. Congrats @kushalbyatnal on #2 on Launch Archive today.

Profilbild von Kalyan

Kalyanvor 2 Monaten

cheap parsing is huge - I lean on vision models to read grocery receipts in my new iOS pantry app:

Profilbild von Elise Tech Ai

Elise Tech Aivor 2 Monaten

70% lower costs with strong benchmark performance is a huge win—efficient document parsing is getting seriously competitive.

Profilbild von RAZA | AI EXPLORER

RAZA | AI EXPLORERvor 2 Monaten

70% cheaper while maintaining strong benchmark performance is a huge win for document AI.

Profilbild von Luke Beck

Luke Beckvor 2 Monaten

How is strikethrough detection?

Profilbild von SomacoSF

SomacoSFvor 2 Monaten

add municipal permits by zipcode. meaning oull all munucipal permit data by zipcode so you can see what is being permitted for build. then you can extrapolate from there

Profilbild von Alice The Ai Expert

Alice The Ai Expertvor 2 Monaten

Huge win 70% cheaper with SOTA accuracy is exactly what teams need!

Profilbild von Lokesh Sanapalli

Lokesh Sanapallivor 2 Monaten

Congratulations! How does it compare with firecrawl pdf inspector?

Profilbild von Internet Labs

Internet Labsvor 2 Monaten

At $0.00625 a page, I’m about to parse every obnoxiously long CVS receipt I’ve ever received just to test the table models. Huge win for the builders.

Profilbild von Saurabh Jambure

Saurabh Jamburevor 2 Monaten

Interesting

Profilbild von Romero Rodrigues

Romero Rodriguesvor 2 Monaten

70 percent cheaper on the page is the actual product. Doc AI just became a cost line, not a seat. Whoever owns the parse at a fraction of a cent owns the agent workflow that sits on top of it.

Profilbild von Haseeb

Haseebvor 2 Monaten

70% cheaper gets especially interesting once parsing becomes a default step in every document workflow.

Profilbild von Modelplane

Modelplanevor 2 Monaten

The 70% cheaper claim is bold—curious how it holds up on complex layouts like tables or handwriting, where parsing costs usually spike. Databricks OfficeQA Pro is a solid benchmark, but real-world docs always find the edge cases.

Profilbild von Dinesh | Umbra

Dinesh | Umbravor 2 Monaten

the real ai race is becoming a race to zero inference cost

Profilbild von Vakada Rohit

Vakada Rohitvor 2 Monaten

70% cheaper without sacrificing accuracy is a seriously impressive improvement.

Ähnliche Videos

Over 1 billion PDFs are created every day, but your agents still can’t read them reliably. Today we’re releasing Parse 2.0, the most accurate document parsing API in the world. Extend already processes millions of pages daily for leading AI teams like Brex, Mercury, Opendoor, Flatiron Health, and hundreds of others. Now, its even better. Parse 2.0 is SOTA quality on RealDoc-Bench, our open source benchmark that measures agent success rate on real world docs that agents actually encounter in production. We trained Parse 2.0 on 1M+ pages of the hardest documents seen in production. Here’s how it stacks up: - #1 in healthcare, real estate, logistics, and financial services - 95.7% agent Q&A accuracy on 581 docs (next best: 92%) - 0.847 F1 on layout (next best: 0.759) Give it a try today and build production-ready document agents with Extend.

Over 1 billion PDFs are created every day, but your agents still can’t read them reliably. Today we’re releasing Parse 2.0, the most accurate document parsing API in the world. Extend already processes millions of pages daily for leading AI teams like Brex, Mercury, Opendoor, Flatiron Health, and hundreds of others. Now, its even better. Parse 2.0 is SOTA quality on RealDoc-Bench, our open source benchmark that measures agent success rate on real world docs that agents actually encounter in production. We trained Parse 2.0 on 1M+ pages of the hardest documents seen in production. Here’s how it stacks up: - #1 in healthcare, real estate, logistics, and financial services - 95.7% agent Q&A accuracy on 581 docs (next best: 92%) - 0.847 F1 on layout (next best: 0.759) Give it a try today and build production-ready document agents with Extend.

Kushal Byatnal

589,710 Aufrufe • vor 5 Monaten

Our default document parsing mode is now able to parse a complex research report with multiple embedded charts on a single page. This is the cheapest document OCR model out there that can turn complex visual documents into LLM-ready markdown. This is our agentic mode in LlamaParse. It starts at ~1c per page; if you’re looking to scale consumption we offer volume discounts. Come check it out! Sign up:

Our default document parsing mode is now able to parse a complex research report with multiple embedded charts on a single page. This is the cheapest document OCR model out there that can turn complex visual documents into LLM-ready markdown. This is our agentic mode in LlamaParse. It starts at ~1c per page; if you’re looking to scale consumption we offer volume discounts. Come check it out! Sign up:

Jerry Liu

15,479 Aufrufe • vor 9 Monaten

Astra is awesome, but if you're using it specifically to parse and extract a massive volume of documents, you will break the bank (10c+ per page on parsing and extraction!) We've added a native LlamaParse connector to ChatGPT that gives the model access to high-quality document OCR and extraction at the pareto frontier of accuracy and cost. It contains native access to our parse and extract endpoints. Upload your most complex documents, and you can do the following: * digitalize it into extremely accurate context for any QA task * perform large-scale extraction from a set of documents with accurate grounding and citations Offload the higher-level reasoning to Astra, leave specialized doc parsing and extraction to us. ChatGPT plugin: Come sign up here:

Astra is awesome, but if you're using it specifically to parse and extract a massive volume of documents, you will break the bank (10c+ per page on parsing and extraction!) We've added a native LlamaParse connector to ChatGPT that gives the model access to high-quality document OCR and extraction at the pareto frontier of accuracy and cost. It contains native access to our parse and extract endpoints. Upload your most complex documents, and you can do the following: * digitalize it into extremely accurate context for any QA task * perform large-scale extraction from a set of documents with accurate grounding and citations Offload the higher-level reasoning to Astra, leave specialized doc parsing and extraction to us. ChatGPT plugin: Come sign up here:

Jerry Liu

11,083 Aufrufe • vor 1 Monat

Launching our full PDF parsing suite: parse, extract, and split. Now live at The API is available too! ✌️

Launching our full PDF parsing suite: parse, extract, and split. Now live at The API is available too! ✌️

Damon Chen

59,902 Aufrufe • vor 11 Monaten

GPT-5.5 in Codex helps Databricks parse complex customer documents more reliably.

GPT-5.5 in Codex helps Databricks parse complex customer documents more reliably.

OpenAI Developers

57,874 Aufrufe • vor 5 Monaten

today, we're open sourcing the Extend CLI watch Fable use it to parse and extract an entire corpus of documents — end to end, without leaving the terminal try it yourself: npm install -g @extend-ai/cli it comes with a built-in agent skill, so claude code/codex/cursor know how to drive it out of the box

today, we're open sourcing the Extend CLI watch Fable use it to parse and extract an entire corpus of documents — end to end, without leaving the terminal try it yourself: npm install -g @extend-ai/cli it comes with a built-in agent skill, so claude code/codex/cursor know how to drive it out of the box

Kushal Byatnal

40,134 Aufrufe • vor 4 Monaten

Introducing NDI 1.0 - a small model for document processing. #1 on Parse Index Normalized (across 6 public benchmarks) GPT-6 Astra performance at 1/10th the cost 📈 Trained on 15M+ financial files for industry-grade accuracy. Get started with $25 in free credits: Reply "NDI" for a single file setup for Claude Code, Codex, PI, Opencode, Hermes, Prime Agent, and more. Start parsing and classifying documents.

Introducing NDI 1.0 - a small model for document processing. #1 on Parse Index Normalized (across 6 public benchmarks) GPT-6 Astra performance at 1/10th the cost 📈 Trained on 15M+ financial files for industry-grade accuracy. Get started with $25 in free credits: Reply "NDI" for a single file setup for Claude Code, Codex, PI, Opencode, Hermes, Prime Agent, and more. Start parsing and classifying documents.

Nace AI

1,307,675 Aufrufe • vor 26 Tagen

$Parse lets you build APIs for any website— 100x cheaper and faster than browser automation. Parse makes deterministic APIs that use direct network requests that cost fractions of a cent and return in milliseconds. Congrats on the launch, Alex!$

Parse lets you build APIs for any website— 100x cheaper and faster than browser automation. Parse makes deterministic APIs that use direct network requests that cost fractions of a cent and return in milliseconds. Congrats on the launch, Alex!

Y Combinator

341,615 Aufrufe • vor 1 Jahr

An underrated issue with document parsing for RAG / agent use cases is dealing with multi-page tables - sometimes a big table spills over into multiple pages. This breaks chunking algorithms that generally operate at the page-level or smaller, and causes LLMs to lose the full view of the data. With LlamaParse Continuous Mode (in beta), you can now parse a document with multi-page tables and join them into a single table! This means you can now: 💡 Do contiguous chunking for RAG use cases OR 💡 Parse the table for text-to-SQL Check out our blog post highlighting this feature. Huge shoutout to Pierre-Loic Doulcet and Sacha Bron : Signup here: It's in beta, let us know your feedback!

An underrated issue with document parsing for RAG / agent use cases is dealing with multi-page tables - sometimes a big table spills over into multiple pages. This breaks chunking algorithms that generally operate at the page-level or smaller, and causes LLMs to lose the full view of the data. With LlamaParse Continuous Mode (in beta), you can now parse a document with multi-page tables and join them into a single table! This means you can now: 💡 Do contiguous chunking for RAG use cases OR 💡 Parse the table for text-to-SQL Check out our blog post highlighting this feature. Huge shoutout to Pierre-Loic Doulcet and Sacha Bron : Signup here: It's in beta, let us know your feedback!

Jerry Liu

24,245 Aufrufe • vor 2 Jahren

We just killed every single web search API you're using. We are excited to announce our partnership with parse[dot]bot to let agents use any site on the internet via API. Parse turns any website into a typed API and Locus puts all of the endpoints on one prepaid balance with our other providers. Travel, e-commerce, finance and more. Turn on the ones you want, and let your agents or platform call them by use. Live now!

We just killed every single web search API you're using. We are excited to announce our partnership with parse[dot]bot to let agents use any site on the internet via API. Parse turns any website into a typed API and Locus puts all of the endpoints on one prepaid balance with our other providers. Travel, e-commerce, finance and more. Turn on the ones you want, and let your agents or platform call them by use. Live now!

cole

10,793 Aufrufe • vor 2 Monaten

i'm flattered by the shoutout, but there's no free lunch for document parsing Cohere parse starts at $1.50 / 1k pages, which is indeed on the cheaper end of doc OCR solutions, but it scores ~50% when averaged across all 5 ParseBench dimensions: * It lacks high-quality visual grounding, doing coarse segmentation for tables and images, but lacking finer-grained bboxes at the word/cell/line-level. this is quite important for any sensitive AI application that requires precise citations back to the source. * It lacks general visual / chart parsing capabilities, which are prevalent across finance, manufacturing, healthcare, and more * to its credit, it does a decent job over tables (87%) compared to other comparable solutions at the price point our cost-effective mode in LlamaParse starts at 0.375c / page and is more consistently strong across all dimensions. also there's various ways to bring it down with volume discounts if you're interested in learning more about various document parsing modes and comparing tradeoffs in price/accuracy, come talk to us! LlamaParse:

i'm flattered by the shoutout, but there's no free lunch for document parsing Cohere parse starts at $1.50 / 1k pages, which is indeed on the cheaper end of doc OCR solutions, but it scores ~50% when averaged across all 5 ParseBench dimensions: * It lacks high-quality visual grounding, doing coarse segmentation for tables and images, but lacking finer-grained bboxes at the word/cell/line-level. this is quite important for any sensitive AI application that requires precise citations back to the source. * It lacks general visual / chart parsing capabilities, which are prevalent across finance, manufacturing, healthcare, and more * to its credit, it does a decent job over tables (87%) compared to other comparable solutions at the price point our cost-effective mode in LlamaParse starts at 0.375c / page and is more consistently strong across all dimensions. also there's various ways to bring it down with volume discounts if you're interested in learning more about various document parsing modes and comparing tradeoffs in price/accuracy, come talk to us! LlamaParse:

Jerry Liu

25,896 Aufrufe • vor 1 Monat

Batch parsing used to mean writing API scripts. Now it's a button. 🦙 Parse or extract across up to 10,000 files in one run, straight from the LlamaParse UI. Point it at a folder and go — no code required. Available now on all paid plans. Bring your files and start parsing 👉

Batch parsing used to mean writing API scripts. Now it's a button. 🦙 Parse or extract across up to 10,000 files in one run, straight from the LlamaParse UI. Point it at a folder and go — no code required. Available now on all paid plans. Bring your files and start parsing 👉

LlamaIndex 🦙

11,792 Aufrufe • vor 3 Monaten

We Parse PDFs We spent 7 figures to put this on billboards throughout SF. I thought long and hard about putting something more creative and whimsical. But then you wouldn’t know what we do. AI agents (and humans) are consuming exponentially more documents as they do real work. They need the best quality document parser to not output garbage on downstream tasks. This is what we do today as a company. If you have any PDFs (or other documents), we parse them :) If you’re around SF in June for one of the following events, come stop by our booths: ✅ Snowflake Summit (this week, Booth 1123) ✅ Databricks Data+AI Summit (June 15-18, Booth 137) ✅ AI Engineer World Fair(June 29-July 2, Booth L-G47) You can find us by the same sign we put on our billboards! We Parse PDFs LlamaIndex 🦙

We Parse PDFs We spent 7 figures to put this on billboards throughout SF. I thought long and hard about putting something more creative and whimsical. But then you wouldn’t know what we do. AI agents (and humans) are consuming exponentially more documents as they do real work. They need the best quality document parser to not output garbage on downstream tasks. This is what we do today as a company. If you have any PDFs (or other documents), we parse them :) If you’re around SF in June for one of the following events, come stop by our booths: ✅ Snowflake Summit (this week, Booth 1123) ✅ Databricks Data+AI Summit (June 15-18, Booth 137) ✅ AI Engineer World Fair(June 29-July 2, Booth L-G47) You can find us by the same sign we put on our billboards! We Parse PDFs LlamaIndex 🦙

Jerry Liu

15,232 Aufrufe • vor 5 Monaten

Introducing LiteParse - the best model-free document parsing tool for AI agents 💫 ✅ It’s completely open-source and free. ✅ No GPU required, will process ~500 pages in 2 seconds on commodity hardware ✅ More accurate than PyPDF, PyMuPDF, Markdown. Also way more readable - see below for how we parse tables!! ✅ Supports 50+ file formats, from PDFs to Office docs to images ✅ Is designed to plug and play with Claude Code, OpenClaw, and any other AI agent with a one-line skills install. Supports native screenshotting capabilities. We spent years building up LlamaParse by orchestrating state-of-the-art VLMs over the most complex documents. Along the way we realized that you could get quite far on most docs through fast and cheap text parsing. Take a look at the video below. For really complex tables within PDFs, we output them in a spatial grid that’s both AI and human-interpretable. Any other free/light parser light PyPDF will destroy the representation of this table and output a sequential list. This is not a replacement for a VLM-based OCR tool (it requires 0 GPUs and doesn’t use models), but it is shocking how good it is to parse most documents. Huge shoutout to Logan Markewich and Clelia Bertelli (🦀/acc) for all the work here. Come check it out: Repo:

Introducing LiteParse - the best model-free document parsing tool for AI agents 💫 ✅ It’s completely open-source and free. ✅ No GPU required, will process ~500 pages in 2 seconds on commodity hardware ✅ More accurate than PyPDF, PyMuPDF, Markdown. Also way more readable - see below for how we parse tables!! ✅ Supports 50+ file formats, from PDFs to Office docs to images ✅ Is designed to plug and play with Claude Code, OpenClaw, and any other AI agent with a one-line skills install. Supports native screenshotting capabilities. We spent years building up LlamaParse by orchestrating state-of-the-art VLMs over the most complex documents. Along the way we realized that you could get quite far on most docs through fast and cheap text parsing. Take a look at the video below. For really complex tables within PDFs, we output them in a spatial grid that’s both AI and human-interpretable. Any other free/light parser light PyPDF will destroy the representation of this table and output a sequential list. This is not a replacement for a VLM-based OCR tool (it requires 0 GPUs and doesn’t use models), but it is shocking how good it is to parse most documents. Huge shoutout to Logan Markewich and Clelia Bertelli (🦀/acc) for all the work here. Come check it out: Repo:

Jerry Liu

257,589 Aufrufe • vor 7 Monaten

Today we’re announcing r-1, our new document parsing model. It’s more accurate than our most powerful agentic OCR models, faster, and up to 6x cheaper. At Reducto, we spent two years building specialized models for complex visual layouts, tables spanning multiple pages, and key formatting like strikethroughs. We then used everything we learned to build r-1, the first in a new generation of models designed to handle the hardest documents without multiplying cost. This early preview delivers a 20% lower error rate than our most accurate legacy agentic models and will keep improving with new checkpoints over the next few weeks. Accuracy is only the beginning. r-1 preview is available at 1¢ per page all-in, with additional volume discounts as you scale. In the near term we’re also going to release r-1 mini, and an auto mode that intelligently selects the right approach for each page. If you’re currently using another parser, we’re offering up to $5,000 in credits to evaluate and migrate. You can claim the migration offer and learn more about r-1 using the links in the comments. Happy parsing!

Today we’re announcing r-1, our new document parsing model. It’s more accurate than our most powerful agentic OCR models, faster, and up to 6x cheaper. At Reducto, we spent two years building specialized models for complex visual layouts, tables spanning multiple pages, and key formatting like strikethroughs. We then used everything we learned to build r-1, the first in a new generation of models designed to handle the hardest documents without multiplying cost. This early preview delivers a 20% lower error rate than our most accurate legacy agentic models and will keep improving with new checkpoints over the next few weeks. Accuracy is only the beginning. r-1 preview is available at 1¢ per page all-in, with additional volume discounts as you scale. In the near term we’re also going to release r-1 mini, and an auto mode that intelligently selects the right approach for each page. If you’re currently using another parser, we’re offering up to $5,000 in credits to evaluate and migrate. You can claim the migration offer and learn more about r-1 using the links in the comments. Happy parsing!

Adit

305,651 Aufrufe • vor 2 Monaten

$We're making Extract even better! It's now twice as fast, more accurate, and a fraction of the cost. What's new: → Faster v4 model with better schema adherence & up to 99% citation coverage → Flat 2¢/page pricing, all-in. No added parse costs. → Upcoming MCP tools to help teams set up and optimize extraction schemas The team Reducto has a lot more coming soon — stay tuned!$

We're making Extract even better! It's now twice as fast, more accurate, and a fraction of the cost. What's new: → Faster v4 model with better schema adherence & up to 99% citation coverage → Flat 2¢/page pricing, all-in. No added parse costs. → Upcoming MCP tools to help teams set up and optimize extraction schemas The team Reducto has a lot more coming soon — stay tuned!

Adit

20,431 Aufrufe • vor 1 Monat

Today, we're launching @PolarBrowser for Windows. The AI browser that beats Anthropic and OpenAI on every single major web benchmark. Now it's on the other 70% of desktops. Try for free now:

Today, we're launching @PolarBrowser for Windows. The AI browser that beats Anthropic and OpenAI on every single major web benchmark. Now it's on the other 70% of desktops. Try for free now:

Kevin Jiang

987,994 Aufrufe • vor 3 Monaten

Today we’re releasing OCRia-1, a frontier VLM for document parsing that sets a new SOTA in accuracy, cost, and latency. It not only sets a new high score on ParseBench (87.4), but also leads in three 3rd-party benchmarks: olmOCR-bench* (83.5 overall, 92.9 on tables!), PulseBench-Tab (84.1), and fr-bench-pdf2md (72.1). OCRia-1 is really, really good at parsing complex tables: nested headers, merged cells, irregular grids, scanned tables, and more. It is also fantastic at parsing complex unlabeled charts (line, bar, pie, technical diagrams), and preserving complex formatting. Most real-world enterprise documents contain at least one of the these, whether it’s a big tax withholding table or a public economic report. It is a 4B model and outperforms all other models within a similar parameter class: LightOnOCR-3, Chandra-OCR 2, Mistral OCR 4.1, and more. It is also extremely fast. All credit goes to our research team, who spent countless hours on curating a diverse dataset, tuning our training pipeline, and squeezing every last drop out of model optimization so that it can process billions of pages at scale. OCRia-1 as a base is powering all of our modes within LlamaParse (cost-effective, agentic, agentic plus), so you can access its capabilities today! If you’re processing millions/billions of documents at scale, we’re offering enterprises that book a demo up to $3k in credits for a guided evaluation.** *olmOCR-bench scores are adjusted based on unifying rendering at 1,288px for all models **enterprise POC credits apply to eligible organizations that book a demo

Today we’re releasing OCRia-1, a frontier VLM for document parsing that sets a new SOTA in accuracy, cost, and latency. It not only sets a new high score on ParseBench (87.4), but also leads in three 3rd-party benchmarks: olmOCR-bench* (83.5 overall, 92.9 on tables!), PulseBench-Tab (84.1), and fr-bench-pdf2md (72.1). OCRia-1 is really, really good at parsing complex tables: nested headers, merged cells, irregular grids, scanned tables, and more. It is also fantastic at parsing complex unlabeled charts (line, bar, pie, technical diagrams), and preserving complex formatting. Most real-world enterprise documents contain at least one of the these, whether it’s a big tax withholding table or a public economic report. It is a 4B model and outperforms all other models within a similar parameter class: LightOnOCR-3, Chandra-OCR 2, Mistral OCR 4.1, and more. It is also extremely fast. All credit goes to our research team, who spent countless hours on curating a diverse dataset, tuning our training pipeline, and squeezing every last drop out of model optimization so that it can process billions of pages at scale. OCRia-1 as a base is powering all of our modes within LlamaParse (cost-effective, agentic, agentic plus), so you can access its capabilities today! If you’re processing millions/billions of documents at scale, we’re offering enterprises that book a demo up to $3k in credits for a guided evaluation.** *olmOCR-bench scores are adjusted based on unifying rendering at 1,288px for all models **enterprise POC credits apply to eligible organizations that book a demo

Jerry Liu

106,641 Aufrufe • vor 12 Tagen

Been wondering how to use Decision Models in your agent harness? Introducing Sage Router, in early access on Antseed: - 39% cheaper than Opus at the same accuracy, - and 31% more efficient than JevRouter - On OpenRouter's leaderboard (GPQA Diamond), it matches the top router's accuracy at a third of the cost. Benchmarks👇 Now live on the Antseed Network.

Been wondering how to use Decision Models in your agent harness? Introducing Sage Router, in early access on Antseed: - 39% cheaper than Opus at the same accuracy, - and 31% more efficient than JevRouter - On OpenRouter's leaderboard (GPQA Diamond), it matches the top router's accuracy at a third of the cost. Benchmarks👇 Now live on the Antseed Network.

Levanto Labs

34,059 Aufrufe • vor 16 Tagen

Massive update to Parse: connect via mcp to build & use APIs instantly book a table on resy, search flights, any action on any site 500x faster than browser agents 1000s of APIs already built. your agent gets them instantly. new ones add to the pool. try it: parse. bot

Massive update to Parse: connect via mcp to build & use APIs instantly book a table on resy, search flights, any action on any site 500x faster than browser agents 1000s of APIs already built. your agent gets them instantly. new ones add to the pool. try it: parse. bot

Alex Forman

114,726 Aufrufe • vor 8 Monaten