网页
综合
更新时间 2026-11-14 09:41:01
No bad actions | .txt
Does your provider break your tool calls?
Tool calls that parse the first time.
Tool calls that parse, JSON that fits the schema.
Reliability comes from how a model is served. The same open weights, on different providers, break anywhere from 0.1% to 10% of tool calls. Across 48 models on OpenRouter, the worst provider typically fails 30 times as often as the best.
OpenRouter's published tool-call error rates, 3 to 9 November 2026. The chart shows the 25 models with the most providers and the 41 providers serving at least three of them: 366 provider-model pairs with 1,000 or more tool calls a day.
.txt builds structured generation into the inference engine. At every step, the model can only write what your tools and schemas allow. We work with inference providers, model makers and teams that ship models on devices.
Runs inside vLLM, SGLang and TensorRT-LLM, in your cluster. No slowdown. Pilot on one model. Serve it in weeks.
Before release, get a report on where your model breaks its own format, and how often. We run paired benchmarks with and without .lambda, for you to publish. Your result becomes the reference.
Qwen3-0.6B goes from 46.9% to 55.1% on BFCL, with no repair retries. Runs on your hardware and inside your runtime, offline.
We started as two statisticians annoyed that a language model couldn’t reliably fill in a form. In 2023 we wrote a paper on making models follow a grammar without slowing them down, and put the code online as Outlines. People have downloaded it more than 70 million times since, and structured output has gone from a research idea to something every major model API offers.
Serving models in production takes more than an open-source library, so we built .lambda and .json. Building with models? Tell us what you’re working on.
From the Internet, with love.
Read the manifesto →Meet the team →
The Z800 runs mock calls. Tell us your model and your tools, and we'll run the real ones.
What you run, and where it fails.
Within one working day.
Tool calling, agents or on-device.
Tool calls that parse the first time.
Tool calls that parse, JSON that fits the schema.
Reliability comes from how a model is served. The same open weights, on different providers, break anywhere from 0.1% to 10% of tool calls. Across 48 models on OpenRouter, the worst provider typically fails 30 times as often as the best.
OpenRouter's published tool-call error rates, 3 to 9 November 2026. The chart shows the 25 models with the most providers and the 41 providers serving at least three of them: 366 provider-model pairs with 1,000 or more tool calls a day.
.txt builds structured generation into the inference engine. At every step, the model can only write what your tools and schemas allow. We work with inference providers, model makers and teams that ship models on devices.
Runs inside vLLM, SGLang and TensorRT-LLM, in your cluster. No slowdown. Pilot on one model. Serve it in weeks.
Before release, get a report on where your model breaks its own format, and how often. We run paired benchmarks with and without .lambda, for you to publish. Your result becomes the reference.
Qwen3-0.6B goes from 46.9% to 55.1% on BFCL, with no repair retries. Runs on your hardware and inside your runtime, offline.
We started as two statisticians annoyed that a language model couldn’t reliably fill in a form. In 2023 we wrote a paper on making models follow a grammar without slowing them down, and put the code online as Outlines. People have downloaded it more than 70 million times since, and structured output has gone from a research idea to something every major model API offers.
Serving models in production takes more than an open-source library, so we built .lambda and .json. Building with models? Tell us what you’re working on.
From the Internet, with love.
Read the manifesto →Meet the team →
The Z800 runs mock calls. Tell us your model and your tools, and we'll run the real ones.
What you run, and where it fails.
Within one working day.
Tool calling, agents or on-device.
本页为82搜索生成的网页快照，内容来自站内索引；演示数据的原文链接仅作示例。