NewDeepSeek V4.1 Flash 1017 is now availableTry it now

Blog

Launches, research and engineering notes from the Inference.net team.

Announcing our $11.8M Series Seed
Sam Hogan

Announcing our $11.8M Series Seed

We raised $11.8 million in funding led by Multicoin Capital and a16z CSX to train and hosti custom language models that are faster, more affordable, and more accurate than what the Big Labs offer.

Read post
Schematron: An LLM trained for HTML -> JSON at scale
Sam Hogan

Schematron: An LLM trained for HTML -> JSON at scale

Schematron-8B and Schematron-3B deliver frontier-level extraction quality at 1-2% of the cost and 10x+ faster inference than large, general-purpose LLMs.

Read post
Introducing ClipTagger-12b: SoTA Video Understanding at 15x Lower Cost
Sam Hogan

Introducing ClipTagger-12b: SoTA Video Understanding at 15x Lower Cost

We're thrilled to announce the release of ClipTagger-12b, a groundbreaking open-source vision-language model that delivers GPT-4.1-level performance for video understanding at a fraction of the cost.

Read post
On the Economics of Hosting Open Source Models
Amar Singh

On the Economics of Hosting Open Source Models

The open source community is buzzing around the new Wan release, but what are the economics of the businesses hosting it right now? Or hosting open source models in general?

Read post
Batch vs Real-Time LLM APIs: When to Use Each
Michael Ryaboy

Batch vs Real-Time LLM APIs: When to Use Each

Not every LLM request needs an immediate response. Chat interfaces need real-time. But data extraction, enrichment, and background jobs can wait hours.

Read post
Do You Need Model Distillation? The Complete Guide
Sam Hogan

Do You Need Model Distillation? The Complete Guide

Model distillation is particularly valuable in scenarios where large models are impractical due to resource constraints or performance requirements.

Read post
The Cheapest LLM Call Is the One You Don’t Await
Michael Ryaboy

The Cheapest LLM Call Is the One You Don’t Await

Asynchronous requests – fire‑and‑forget calls that finish whenever idle GPUs are free.

Read post
Osmosis-Structure-0.6B: The Tiny Model That Fixes Structured Outputs
Michael Ryaboy

Osmosis-Structure-0.6B: The Tiny Model That Fixes Structured Outputs

We're excited to announce that Osmosis-Structure-0.6B is now available on the Inference.net platform alongside our comprehensive DeepSeek R1 family.

Read post
How Smart Routing Saved Exa 90% on LLM Costs During Their Viral Moment
Michael Ryaboy

How Smart Routing Saved Exa 90% on LLM Costs During Their Viral Moment

They thought of a clever solution that saved them 90% on tokens: route people with the most followers to Claude, and everyone else to dirt cheap open-source models

Read post
Migrating our Website and Dashboard to TanStack Start
Sean

Migrating our Website and Dashboard to TanStack Start

We evaluated a few frontend frameworks and eventually settled on TanStack Start as the tool of choice to re-implement are dashboard and website. In particular, we wanted a flexible solution that would allow us to server-render static content while also powering a rich, JS-heavy client side application.

Read post