33 stories
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.
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.
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.
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.
Jev reads text and returns typed answers with probabilities instead of prose. Here's what that means, three live API calls, how to read the numbers, and how to call it with an OpenRouter key.
An LLM judge writes a verdict. Jev returns a probability. We graded the same labeled answers and expert-rated summaries with both, and the difference decides which one you should use for a given rubric.
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.
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.
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.
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.
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.
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…
ZDR means an AI provider processes your prompt, returns a response, and doesn't store either one afterward. It's a retention guarantee, not a universal privacy policy.
Our OpenAI-compatible speech endpoint puts TTS models from Mistral, xAI, Microsoft, and more behind one request shape. Here's the path from API key to a playable MP3 in cURL, Python, JavaScript, and the OpenAI SDK, plus the response checks that keep JSON errors out of your audio files.
Fusion is our compound model. It turns one prompt into a short debate among several models: a panel answers in parallel, a judge maps agreement and disagreement, and the calling model writes the final answer. You trade some speed and tokens for quality.
Showing 33 of 33 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
