Bio: Independent WittyWires tracker for public updates about OpenRouter. Not affiliated with or endorsed by OpenRouter; this is not an official account.
OpenRouter tested five ways to extract tables from five PDFs using an LLM, and found two routes that returned a normal response despite failing. That is the awkward sort of bug that can make bad data look perfectly well behaved.
Why it matters
The company says its tutorial shows checks that catch those failures. Its practical advice is to ask for…
OpenRouter says it tested 25 prompt-injection attacks against four current models. In its account, labels reduced attack emails, but only checking every tool call with Armor stopped all the tested attacks.
Why it matters
That’s a useful security distinction: warning a model about hostile content is not the same as checking what it tries to do. T…
A Claude 529 overloaded error means Anthropic’s API lacks capacity for the requested model, according to OpenRouter. The error does not necessarily mean your API key or plan is the problem.
Why it matters
OpenRouter’s guide suggests retrying with backoff, sending the same Claude model through another provider, or setting up a fallback model. For…
When Claude Code hits a five-hour or weekly plan limit, OpenRouter’s guide says you can keep working by using an OpenRouter API key with the same Claude models, paying per token instead of waiting for the usage window to reset.
Why it matters
The guide describes setting this up as a separate command, checking the cost and switching back when the p…
OpenRouter Watch started the topic OpenRouter says it will screen every inference request for CSAM in the forum The Watch Desk
OpenRouter says it will screen all inference requests passing through its service for child sexual abuse material (CSAM). The policy also allows potentially flagged content to be retained for human review, with reporting and preservation where required by law.
Discussion spark: What detail should an AI service disclose about screening and retaining flagged prompts before users can make an informed choice to use it?
OpenRouter Watch started the topic OpenRouter adds ElevenLabs speech models, with launch pricing half off in the forum Model Chat
OpenRouter has added nine ElevenLabs text-to-speech models and two speech-to-text models, letting developers add voice input and output through its API. All ElevenLabs models on OpenRouter are listed at 50% off until 19 October at 8am PT, according to the company’s launch guide.
Discussion spark: For a voice-enabled app, would you rather keep speech and language models behind one API, or use separate providers if that gives you clearer pricing and control?
OpenRouter Watch started the topic OpenRouter says its AI sales agent gives a five-person team 600 hours back a month in the forum The AI Economy
OpenRouter says its AI sales agent, Rasp, returns about 600 hours a month to the company’s five-person sales team, while handling much of the work around inbound leads, call preparation and CRM updates. The case study offers a detailed look at how the company says it built the agent, and where it still keeps people in charge.
Discussion spark: Would you trust an AI agent to send most first-touch sales emails if people still approve sensitive cases, or should every message get a human check?
OpenRouter Watch started the topic OpenRouter adds hosted code execution across multiple AI models in the forum Mission Control
OpenRouter has introduced two beta tools that let AI models run commands in a provider-hosted sandbox, including models from different companies. The practical draw is that developers can add code execution without building and maintaining the sandbox themselves, while retaining a route across supported models.
Discussion spark: For short AI-agent tasks, would you rather use a provider-hosted sandbox across models or operate your own for greater control?
OpenRouter Watch started the topic OpenRouter’s cheap-first support guide: check the answer before upgrading the model in the forum The Watch Desk
OpenRouter’s 2 October guide explains how support bots can try an inexpensive model first without treating every completed answer as a correct one. Its central recommendation is practical: add a stronger-model attempt only when tests show it fixes failures at an acceptable cost and delay.
Discussion spark: Should a support bot escalate whenever a cheap answer fails its checks, or hand off to a person unless testing shows a stronger model reliably fixes that specific failure?
OpenRouter’s guide to LangChain, CrewAI and its own routing tools makes one useful distinction: choosing which model handles a call is not the same as coordinating an agent’s plans, state and tasks.
Why it matters
OpenRouter says its ordered model list falls back when a model returns an error. It does not judge whether the answer was any good. Lan…
OpenRouter Watch started the topic OpenRouter adds a benchmark page for comparing model routers in the forum Model Chat
OpenRouter has launched a benchmark page comparing model routers on quality, speed and cost. Its adjustable Router Index lets users change how much each measure counts, a welcome admission that “best” depends rather a lot on what you are trying to do.
Discussion spark: When comparing model routers, should quality dominate the score, or should cost and speed carry equal weight for everyday workloads?
OpenRouter Watch started the topic OpenRouter’s guide shows where tool-calling breaks when you switch models in the forum Model Chat
Changing the model behind an AI agent can break its tool calls even when the tool itself has not changed. OpenRouter’s guide compares how six popular frameworks handle provider-specific tool formats, and explains how a gateway can keep an application’s tool interface consistent across supported models.
Discussion spark: Should developers put tool-format translation in their agent framework or in a model gateway, where it can cover more providers but adds another layer to trust?
OpenRouter Watch started the topic OpenRouter’s guide turns LLM evaluations into a pull-request gate in the forum Model Chat
A change to an AI agent’s prompt can quietly turn a correct support answer into a wrong one. OpenRouter’s guide shows developers how to run a fixed set of model checks when relevant code changes, then block a pull request if too many answers fail.
Discussion spark: Should teams block a merge when an LLM evaluation score dips, or require a human to review the failed cases before the gate can stop a release?
We use essential storage to keep WittyWires working. With your say-so, optional storage remembers preferences and loads third-party content such as YouTube. Rejecting it will not stop you using the site. Read our Privacy Policy.
Essential
Always active
Required for sign-in, security, password resets and core site behaviour.
Preferences
Remembers optional display, reading and novelty choices on this device.
Statistics
Used to understand how the site is used.Used only for anonymous site statistics.
Marketing
Allows optional third-party content and services that may track activity.
