# Asking other models

> Have a run put a question to another model your account has connected, such as a second opinion on its review findings.

A run can ask any model your account has a credential for. Ask in plain words, in [standing instructions](https://pullfrog.com/docs/instructions), an automation's prompt, or a comment:

```text
Before posting a review, send each finding to gpt-sol and grok and ask them to refute it. Drop any finding you cannot re-verify after a refutation.
```

The model you ask works as a helper of the run:

- It has the run's tools, including its shell, and its edits land in the same checkout.
- Pushing, posting to GitHub, and the run's own settings stay with the run that asked.
- Its answer goes back to that run, which decides how to act on it. Nothing posts a finding because another model agreed with it, and nothing drops one because another model disagreed.

A request can name an effort, such as `gpt-sol at high effort`. The level has to be one that model offers, and the console lists them. A model with no effort control, such as one on Bedrock or Vertex, refuses the request.

## Which models a run can ask

The repository console lists them under **Standing instructions → Models a run can ask**, with the effort levels each one takes. The list covers credentials stored in Pullfrog:

- [API keys](https://pullfrog.com/docs/api-keys).
- Connected subscriptions: [Claude](https://pullfrog.com/docs/claude), [ChatGPT](https://pullfrog.com/docs/codex), and [Grok](https://pullfrog.com/docs/grok). A subscription pays before an API key for the same provider, the same order a run uses for its own model.

Other credentials work too:

- A key set as a GitHub Actions secret, which the console cannot see.
- [Amazon Bedrock](https://pullfrog.com/docs/bedrock), [Vertex AI](https://pullfrog.com/docs/vertex), [Azure OpenAI](https://pullfrog.com/docs/azure), and [OpenAI-compatible endpoints](https://pullfrog.com/docs/openai-compatible). Each offers the one model it is set up with, named after it, such as `bedrock/us.anthropic.claude-opus-4-7` or `azure/<deployment>`, and a named endpoint goes by its name. The model is often set in the workflow file, so these appear only once a run starts.

Two kinds of credential cannot be asked:

- A provider reached through a [gateway](https://pullfrog.com/docs/gateways), including [keyless auth](https://pullfrog.com/docs/keyless-auth).
- The OpenRouter key Pullfrog mints for Router, OSS, and trial runs. Those runs can still ask a model you hold your own key for.

## Limits

- A run can ask at most 12 times.
- Each call stops after 9 minutes.
- Each call starts fresh. It cannot see the run's conversation, so the question has to include what the other model needs, such as the finding, the file and the line.
- A subscription at its usage limit is refused at once, with the time it resets. An API key at its provider's limit can take the full 9 minutes to fail.
- Your code goes to the provider of every model you ask, under that provider's terms.
