# Connect an LLM provider with one pasted key, checked before saving

> LLM provider setup now offers a one-click grid of common providers, verifies the API key with the provider, and enables models and a default for you.

Source: <https://everruns.com/docs/changelog/2026-09-11-llm-provider-quick-connect/>

Date: 2026-09-11
Products: Platform, Cloud, CLI
Category: Improvement
Available: In 0.26.0
Pull request: everruns/everruns#3526
Pull request: everruns/everruns#3516
Pull request: everruns/everruns#3515
Pull request: everruns/everruns#3517
Pull request: everruns/everruns#3512

**In the UI:** a **Connect** grid offers one tile each for Anthropic, OpenAI, Gemini, OpenRouter and Meta, so connecting one takes a pasted key. Providers that need more than a key stay behind **Another provider**. Keys are checked as you type, and only an outright rejection is shown. Once a key is saved, Everruns discovers the provider’s models, enables a shortlist, stars a few favorites and sets a default model if none exists.

**In the API and CLI:** `POST /v1/providers/check-credentials` checks a key without storing it:

```bash
everruns providers check-credentials check --provider-type openai --api-key "$OPENAI_API_KEY"
```

Disabled models can be re-enabled. See [Providers](https://everruns.com/docs/providers/) and [CLI providers](https://everruns.com/docs/reference/cli/providers/). [#3526](https://github.com/everruns/everruns/pull/3526), [#3516](https://github.com/everruns/everruns/pull/3516), [#3515](https://github.com/everruns/everruns/pull/3515)