Vibekollen Nytt
Hämtar senaste nytt…
Vibekollen Nytt
Modeller, verktyg och händelser som formar AI-världen. Hitta nyheter, video och poddar – och följ vad som händer på Vibekollen.
BloggOpenRouter
The cheapest model that clears your quality bar is usually not the model at the top of a leaderboard. This framework sets the bar for one task, measures cost per quality point across a cheap, a mid-tier, and a frontier model on your own examples, and picks the cheapest one that clears the bar with margin. It uses live catalog prices and the cost each OpenRouter response reports.
1 okt. openrouter.ai
BloggOpenRouter
Confidence-based escalation keeps most requests on a cheap model and sends only the ones it is unsure about to a stronger one. This guide covers forcing a numeric confidence field with structured outputs, setting the threshold from error rates on your own traffic, tuning it against accuracy, cost, and latency, routing the escalation in your code, and re-tuning it after launch.
1 okt. openrouter.ai
BloggOpenRouter
An agent can call the wrong tool, or call the right tool with the wrong arguments. This guide covers three ways to test each failure mode, a Python harness that grades both, and how to run the same test cases against several tool-capable models through OpenRouter.
30 sep. openrouter.ai
BloggOpenRouter
A golden eval dataset is a curated set of production inputs with reviewed expected outputs, versioned in Git and run before every deploy. This guide covers the five steps to build one from live traffic and how to run the same set against many candidate models through one API.
30 sep. openrouter.ai
BloggOpenRouter
An agent's behavior can change when you edit a prompt, swap a model, change a tool schema, or change what retrieval returns. This guide covers the locked case set, the per-case behavioral contract, and how to run the same suite against two concrete model slugs through OpenRouter so the diff shows what the change did.
30 sep. openrouter.ai
BloggOpenRouter
If you already have the image a video should start from, the model choice comes down to what has to happen after that frame. This post compares the Veo 3.1, Seedance, Kling, and Grok Imagine Video lines on duration, resolution, first-frame and last-frame control, generated audio, reference inputs, and current per-second price, then shows how to submit an image-to-video job with the TypeScript SDK.
29 sep. openrouter.ai
BloggOpenRouter
We audited our own OpenRouter account and found over 1,000 active API keys for 85 employees, 168 of them hadn't been used in months. The new Security Center helps you manage and de-risk your API keys with one place to see every key, know which ones are risky and why, clean them up, and lock them to your own network.
28 sep. openrouter.ai
BloggOpenRouter
Qwen 3.8 is Alibaba's August 2026 model generation. Four models share the name and they differ in whether you can download them, which license applies, whether they read images and video, and whether you can turn reasoning off. This post covers each model, the license terms, local serving, benchmark scores, and what changes your bill on OpenRouter.
28 sep. openrouter.ai
PoddLatent Space
From the earliest days of open-weight models to becoming the neutral routing layer for more than 10 million developers, OpenRouter is one of the clearest bets that the future of AI will be multi-model. In this episode, OpenRouter co-founder & CEO Alex Atallah, with AMP’s Anjney Midha returning with swyx to unpack how OpenRouter emerged from the first wave of Llama, Alpaca, Mistral, and Midjourney, why model diversity mattered before it was consensus, and how a company dismissed as “just a wrapper” became critical infrastructure for the AI ecosystem.We go deep on the product and distribution lessons behind OpenRouter: why model labs can spend billions training a checkpoint and still struggle to get it into developers’ hands, how Mistral helped prove the value of a competitive inference marketplace, why OpenRouter chose focus over expanding into fine-tuning, memory, and other adjacent products, and how its rankings became a real-time map of how AI usage was changing.
26 sep. latent.space
BloggOpenRouter
ByteDance's Seedance video models are available through hosted APIs, and we found no downloadable checkpoint or model license for any of them. This post covers where we looked, what the repositories named Seedance on GitHub and Hugging Face actually contain, when a checkpoint is a hard requirement, and how to run a Seedance job through the asynchronous video endpoint on OpenRouter.
25 sep. openrouter.ai
BloggOpenRouter
Kimi K3 ships public weights under Moonshot AI's own Kimi K3 License, which is not an OSI-approved open-source license. This post explains the difference, what the license grants and requires, what the checkpoint contains, and how to call the model on OpenRouter with reasoning, vision, and tool calling.
24 sep. openrouter.ai
BloggOpenRouter
A method for putting Jev to work on a new problem, worked end to end on marketplace listing moderation: what stays in code, what Jev sees, how to phrase the questions, and how to turn its probabilities into publish, hold, or reject.
23 sep. openrouter.ai
BloggOpenRouter
An embedding model decides what your retrieval system can find. We shortlisted the embedding models in our catalog for English RAG, multilingual retrieval, code search, text-and-image retrieval, and low-cost indexing, sent live requests to each one, and recorded their prices, context windows, and default vector sizes so you can pick a candidate and test it on your own data.
23 sep. openrouter.ai
BloggOpenRouter
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.
22 sep. openrouter.ai
BloggOpenRouter
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.
22 sep. openrouter.ai
BloggOpenRouter
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.
22 sep. openrouter.ai
BloggOpenRouter
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.
21 sep. openrouter.ai
BloggOpenRouter
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 matched the LLM judge on agreement at a fifth of the cost and a tenth of the latency, and its probabilities meant what they said. The LLM judge won on the open rubric.
21 sep. openrouter.ai
BloggOpenRouter
Descript, ett AI-verktyg för video- och ljudredigering, löste ett långsamt problem i sitt arbete med att testa nya AI-modeller. Tidigare krävdes det några timmars arbete plus en veckas väntan för att testa en ny modell, eftersom en ingenjör måste lägga till den manuellt. Genom att använda OpenRouter och automatisering med Claude Tag (Anthropics Slack-integration) tar testningen nu bara en till två timmar, och vem som helst kan starta en utvärdering direkt från Slack. Det betyder att Descript nu testar modeller flera gånger i veckan istället för att välja en modell tidigt och hålla sig till den. Teamet kan nu snabbt integrera nya modeller — till exempel lägga till Grok 4.5 från xAI utan att bygga en egen integration.
21 sep. openrouter.ai
BloggOpenRouter
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.
19 sep. openrouter.ai
