Blog — OpenRouter Blog

Batch API: half-price inference by bundling requests

Send a whole workload in one POST, collect the results within 24 hours, and typically pay half the per-token price. Across 230k+ batches that completed over our two week beta period, the median finished in 7 minutes.

September 22, 2026

Is Jev as Accurate as Frontier Models at Classification?

Claude Opus 5 leads OpenRouter's classification task ranking by spend. We sent the same 3,080 Banking77 utterances to it and to Jev 1.13 through the Decisions API. Opus scored 84.4% to Jev's 81.0%, and Jev answered in 175 ms at $0.11 per thousand requests against 2.3 seconds and $2.42 for Opus.

September 22, 2026

What Is Nemotron 3.5 Lightning

Nemotron 3.5 Lightning is NVIDIA's open-weight 30B mixture-of-experts model with about 3B active parameters per token, built for the high-volume execution calls in an agent run. This post covers what the architecture means, how the model compares with Nemotron 3 Ultra, what context and features each OpenRouter endpoint exposes, and how to call it with structured outputs.

September 22, 2026

Two Hours of Work That Takes a Week

For Descript, testing a new model was a couple of hours of work and a week of waiting. The team removed the waiting. Evaluations run in an hour or two now, and nobody has to ask an engineer for time. This post covers the queue, what replaced it, and what changed once evaluation ran several times a week.

September 21, 2026

Jev vs LLM: When to Use a Decision Model Instead of Generating Text

Jev returns typed judgments with probabilities. An LLM returns prose. We benchmarked both on 100 support cases through OpenRouter, then wired them together so Jev routes and the LLM writes.

September 19, 2026

Image Generation Models Compared: Cost, Edit, Quality

Image models are priced per token, per megapixel, or per image, so their listed rates do not compare. We sent the same prompt to 20 of them through the Image API, read usage.cost off each response, and tested text rendering, reference-image editing, seeds, and text-plus-image replies.

September 18, 2026

Build a Reliable Tool-Calling Agent Loop on OpenRouter

A tool-calling agent loop sends the conversation and tool definitions to a model, runs the tool calls the model returns, appends the results, and repeats until the model answers or a stop condition fires. This guide builds that loop in TypeScript with the OpenRouter SDK, then adds an iteration cap, repeated-call detection, model fallback, and history controls.

September 17, 2026

Does DeepSeek V4 Have Vision?

DeepSeek V4 is a family of models, and only some of them accept images. This guide maps every V4 slug on our catalog to its input modalities, shows how to send an image to the two that read images, and shows how to put a vision model in front of the text-only ones.

September 16, 2026

Case Study: How Descript Took New Models Off the Engineering Queue

Descript's Underlord video-editing agent runs 13 production models from Anthropic, Google, OpenAI, and xAI through one OpenRouter integration. Getting a new model through evaluation used to take more than a week. It now takes one to two hours, and the team does it several times a week.

September 15, 2026

LLM-as-a-Judge: Score AI Agent Outputs Automatically

An LLM judge is a second model that scores an agent's output against criteria you write in plain language. This guide explains where a judge fits beside deterministic tests and human review, then shows how to add one to an Ori Eval test, compare candidate models, calibrate the threshold against human-labeled examples, and keep evaluation cost under control.

September 14, 2026

View all posts RSS

Batch API: half-price inference by bundling requests

OpenRouter is Joining Stripe

Ori Eval: Find the Best Model for What You're Building

Surpassing Frontier Performance with Fusion

Is Jev as Accurate as Frontier Models at Classification?

What Is Nemotron 3.5 Lightning

Two Hours of Work That Takes a Week

Jev vs LLM: When to Use a Decision Model Instead of Generating Text

Image Generation Models Compared: Cost, Edit, Quality

Build a Reliable Tool-Calling Agent Loop on OpenRouter

Does DeepSeek V4 Have Vision?

Case Study: How Descript Took New Models Off the Engineering Queue

LLM-as-a-Judge: Score AI Agent Outputs Automatically