OpenRouter

OpenRouter added a paid zero-data-retention endpoint for Inception's Mercury Decide, priced at half the list input rate with free output and cached input and a 66K context window.

Ori Harness configures Codex, Claude Code, OpenCode, and Hermes to run on OpenRouter with settings tuned per harness. It spreads Opus traffic across eight endpoints on Anthropic, Bedrock, Vertex, and Azure, and flips a Claude Code setting that nearly halves the system prompt.

A tutorial on testing agent tool calling in layers: exact-match checks where the expected tool is known, an LLM judge where several choices are valid, schema plus value checks on arguments, and trajectory comparison. Ends with running the same eval across models.

DeepSeek charges different rates by hour of day. OpenRouter now shows the peak and off-peak windows in your local timezone on the model page and factors the schedule into which endpoint it sources, with the V4 Flash 0731 endpoint currently showing a 64 percent discount.

Two reliability layers, often confused: provider failover recovers inside a single model automatically, while model fallbacks are opt-in and recover across models. Covers what triggers each, why the last entry in your list should be a dependable floor model, and where failover stops helping.

Breaks down why Kimi K3 is open-weight rather than open-source: Moonshot's custom license lacks OSI approval and adds a Model-as-a-Service revenue gate and UI attribution requirement above certain scale, despite granting broad use and resale rights.

OpenRouter compares Veo 3.1, Seedance, Kling and Grok Imagine Video for image-to-video work. It covers clip length, resolution, frame roles, audio and reference inputs, and shows how to submit a job through the unified video API.

OpenRouter breaks down Qwen 3.8's four variants: which weights are downloadable, their differing licenses (Apache 2.0, Qwen3.8-Max License, Qwen Community License), native versus extended context windows, and per-token pricing by provider.

Dedicated speech and transcription endpoints arrive behind an existing gateway key, with Whisper and GPT-4o Transcribe for speech to text and OpenAI, Google, and Mistral voices for synthesis, plus guidance on when a voice-native audio model is the wrong tool.

A server-side tool lets an orchestrating model delegate self-contained work to a smaller worker model mid-generation. The worker sees only the task description, never the parent conversation, and you pin which model handles it, with the price spread that makes the split worth it.

OpenRouter benchmarked Exa, Parallel, Perplexity and native search across four models and four search depths. Budget mattered most: 1 to 25 turns roughly doubled BrowseComp scores. Model choice moved results ~15 points, engine choice ~10. Incorrect runs averaged 19.7 searches against 10.3 for correc

OpenRouter released an openrouter-decisions skill for coding agents. In its tests across three models and four tasks, decision-model use rose from 4 of 27 runs to 27 of 27, and a grader preferred the skill output every time.

Where should the routing layer run? A comparison of managed versus self-hosted LLM gateways on operational burden, data residency, RBAC and cost, with the spend arithmetic that identifies the point where running your own proxy becomes the cheaper option.

Live leaderboards grading web-search configurations for agents across BrowseComp, DeepSearchQA, WideSearch and HLE. The findings that survive the leaderboard churn: search budget dominates, the querying model outweighs the engine, and cost is governed by how often runs fail.

Grok 4.6 is routable on OpenRouter, with gains over Grok 4.5 claimed on GPDVal-AA V2 and pricing unchanged at $2 per million input tokens and $6 per million output.

An opt-in header that returns identical requests from an edge cache in 80 to 300ms with zero tokens billed, with configurable TTL up to 24 hours, explicit cache busting, hit and miss response headers, and streaming replay. Distinct from provider prompt caching.

OpenRouter presets move model choice, system prompt, provider preferences and sampling parameters to the server. Any app that accepts a model string can reference one with the preset field or model@preset syntax, and version history reverts a change without touching client code.

A week of Ori Eval fixes: failures now report the cause and the serving provider, crashed runs count as failures rather than wrong answers, ori eval --pilot estimates full-run cost within 5%, the tool warns when judge and candidate share a family, and headless runs work without a browser login.

OpenRouter adds a Security Center that groups API keys by risk, filters by owner and inactivity, bulk-disables or caps up to 500 keys, and supports IP allowlists. Available on all plans.

Gateway-level measurement of what a three-week frontier-model discount did to demand: token volumes multiplied several-fold against a flat undiscounted control, most of the share came from competing labs, and roughly a third of new users stayed once list pricing returned.

Sakana AI's Namazu is routable on OpenRouter. Built on Kimi K2.6, it pairs reasoning with integrated web search and code execution and is specialized for Japanese cultural and business context.

An eval generator that reads your codebase, finds every model call, and asks what you actually optimize for before writing runnable eval files. It pins the harness during a run so comparisons isolate the model, and it re-runs against new releases from CI.

A routing update that picks models from what the market actually spends on over the past seven days rather than a task classifier, keeping selections current as models ship. Benchmarks across knowledge, agents, search, research and coding accompany the release, with a cost_tier control.

Workspace-level controls for agent traffic: spend caps that reject with 402, model and provider allowlists, one-click zero data retention, PII redaction, and deterministic regex screening for prompt injection with flag, redact, or block enforcement before the provider call.