OpenRouter

ScaleDown's task-specific constrained-decoding models are live on OpenRouter. Summarize handles context compaction, Extract returns schema-driven JSON with confidence scores and source spans, and Classify-1 gives calibrated label probabilities. Launch pricing is 20% off at $0.04/M input, output free

Introduces TypeSafe's Jev, a System One decision model on OpenRouter that returns typed choices with calibrated probabilities across four primitives, with API examples, how to read confidence, pricing, and when to prefer it over an LLM.

OpenRouter added server-side Presets: model selection, provider routing, system prompts and generation parameters stored in the dashboard and referenced from a request as @preset/slug, with optional per-request model override.

OpenRouter's case study on Descript shows how a Claude Tag Slack integration lets anyone trigger model evals and open a PR from a Slack message, cutting the team's evaluation cycle from a week-long engineering queue to about two hours per new model.

A practical walkthrough for scoring agent outputs with a second model against a written rubric, covering judge-vs-candidate bias pitfalls, scoring modes, and how to keep judging cost and reliability in check.

Step-by-step configuration for pointing Cursor at OpenRouter through the OpenAI key and base URL override, using Moonshot's Kimi K2 as the worked example, including which Cursor warning is safe to ignore.

OpenRouter lists Meta's Muse Spark Open at launch: an open-weight model built for agentic coding with 1M context and image, video, audio and PDF input, priced at $1.25/M input and $4.25/M output, with four day-0 providers. Strength claims are OpenRouter's.

OpenRouter's postmortem on two February outages: an external caching layer dropped database connections, mass invalidation overwhelmed lookups, and timeouts were returned as 401 auth errors. A parallel DoS attack led the team to misdiagnose the first incident.

OpenRouter added video generation to its unified API: text-to-video and image-to-video across Seedance, Veo 3.1, Wan and Sora 2 Pro, with async job tracking, parameters normalized across models, and a models endpoint that reports what each one supports before you call it.

OpenRouter replaced its fixed Stripe charge with percentage platform fees: 5.5% and an $0.80 minimum on card payments, 5% flat on crypto, with a published comparison of old and new fees across order sizes.

OpenRouter launches a benchmark page scoring model routers on quality, speed and cost across six benchmarks, with a blended Router Index. It also explains why routing often loses to a single model: cache rebuilds, weak complexity signals and added latency.

OpenRouter reports open-weight models rising from 27% to 72% of top-50 model tokens in a year, at about a quarter of the per-token price, while closed models lead by about 11 points on an intelligence index.

A TypeScript walkthrough of a scheduled agent built on the OpenRouter Agent SDK. It covers cost and step caps per run, approval-gated tools, file-based memory that survives restarts, and measured monthly costs.

OpenRouter will scan all inference requests in flight for CSAM using hash matching and suspected-content review. ZDR traffic is included, with retention allowed only for review, reporting and legal preservation; training use stays off.

Workspaces split one OpenRouter account into isolated environments, each with its own API keys, routing defaults, guardrails, presets, plugins and observability. Billing, logs and privacy restrictions stay account-level, and existing setups land in a Default workspace.

MiniMax's open-weights Hailuo H3 is live on OpenRouter. The lightweight video model accepts text, image, audio and video input with native audio-visual output, targets instruction-led edits, brand text rendering and motion transfer, and supports up to 12 reference files per request.

A TypeScript walkthrough for building a tool-calling agent loop: executing tool calls by ID, capping iterations, handling repeated failed calls, and adding model fallback.

AssemblyAI's Universal-3.6 Pro speech-to-text model is on OpenRouter. It claims 30% fewer errors on short conversational utterances, 12% fewer overall, better formatting of codes and addresses, and 14 new languages.

Recursive's first model, Flint, is an open-weight 40B mixture-of-experts with about 2.5B active parameters, 262K context, reasoning and tool calling, tuned for coding agents. It launched free on OpenRouter, with benchmark scores self-reported by the lab.

A method for judging serving environments rather than models: latency, throughput, uptime and quantization, read at the tail instead of the average. The core point is that a shared model slug hides precision and infrastructure differences that show up in production quality.

OpenRouter and a16z publish an empirical study of a year of gateway traffic, more than 100 trillion tokens, tracking the move from single-pass generation to reasoning models and agentic workflows and the growing production use of open-weight models.

OpenRouter data shows a new model launch mainly cannibalized flash-tier models across labs, and nearly half of its users on the platform hadn't touched any model the week before its launch.

OpenRouter opens its first image endpoint with Gemini 2.5 Flash Image Preview: $0.30 per million input tokens, 32k context, multiple images per call, and character consistency across scenes for work like comic panels and bulk logo iterations.

A CLI that boots Claude Code, Codex, OpenCode, or Hermes against OpenRouter with the right configuration per model. The notable disclosure is the env matrix itself, particularly tool search, which Claude Code enables only for the first-party harness and which materially changes token use and turn count.