DeepSeek R1 Just Got Eyes with Fireworks Document Inlining

Blogs

A smart reasoning LLM is good, but a smart reasoning VLM is better! We’re excited to demonstrate how DeepSeek R1, a state-of-the-art reasoning model from DeepSeek AI, can now process and reason over both text and image inputs using the Fireworks Document Inlining feature.

Visit Site

Blogs Fireworks

BlogsDeepSeek V3 just got vision capabilities!Fireworks BlogsDeepSeek V4 Pro: Validating Frontier Models for ProductionFireworks

BlogsThe DeepSeek Model Lineup: V3.2, R1, and Distilled Variants Mapped to Production WorkloadsFireworks BlogsDeepSeek-V4.1-Flash on Fireworks: Astra-level DeepSWE at 1/15th the costFireworks BlogsQwen 3.7 Plus is now live on FireworksFireworks BlogsFireLLaVA: the first commercially permissive OSS LLaVA modelFireworks BlogsHow NetEase Games achieved 30-second LLM cold starts on KubernetesCncf BlogsJust Sharing My GulpfileCss Tricks BlogsWrangling Control Over PDFs with the Adobe PDF Embed APICss Tricks BlogsWhat Makes a Great Dive? The DiveMaxxing WinnersMotherduck BlogsJust Released: Hybrid Query Processing Paper at CIDR 2024Motherduck ResourcesSelector (CSS) - GlossaryDeveloper Mozilla BlogsWe're Cutting L40S Prices In HalfFly BlogsHost your frontend applications on the edge!Bunny ResourcesNO_DOCUMENT_WRITEVercel BlogsEmail Parser: Automatically copy email dataZapier BlogsHTML BoilerplatesCss Tricks BlogsCustom Property Brain TwistersCss Tricks BlogsChrome + System Fonts SnafuCss Tricks EventsJust use Postgres (and DuckDB): a Postgres + DuckDB Community Night #SFTechWeekMotherduck