Skip to content

Free LLM API errors · OpenRouter · checked 2026-11-13

OpenRouter: no endpoints match your data policy

HTTP 404 · No endpoints found matching your data policy (Free model training)

Every provider that serves this model may store or train on prompts, and your privacy settings (or the request's data_collection) exclude such providers. So nothing is left to route to.

Our own router has received this error from OpenRouter in production.

Why it happens

  • OpenRouter has separate privacy settings for paid and free models. With training turned off for free models, any free model served only by providers that may train becomes unavailable to you.
  • The same happens per request if you send provider.data_collection = "deny".
  • A model's provider can change, so a model that worked last week can start failing this way.

How to fix it

  1. Pick another free model whose provider does not train on prompts. That keeps your prompts out of training.
  2. Or allow training for free models in openrouter.ai/settings/privacy, knowing the provider serving that model may then train on what you send.
  3. Check before you choose: OpenRouter publishes, per provider, whether it may train and how long it keeps prompts.

Questions

Should I turn on training to fix this OpenRouter error?
Only if you are fine with that provider using your prompts. Otherwise choose a free model served by a provider that does not train.
Which OpenRouter providers may train on prompts?
OpenRouter's provider logging page lists them; on 2026-10-10 it marked four of 93 providers that way: DeepSeek, Liquid, NVIDIA and Thinking Machines.

Sources

Read on 2026-11-13. Providers change limits and messages often; the linked pages are what applies.

Limits and fine print of OpenRouter's free tier: OpenRouter free API. Tired of handling these by hand? ZeroLimitAI is one OpenAI-compatible endpoint that moves to the next free model when one of these comes back, and can run on your own Groq or OpenRouter key.

Other OpenRouter errors

Stop paying per token.

One endpoint. $0 inference.

Free 7-day API key in a minute · no card. Then $99 once on your own key, or $99 a year.