Source: https://ailoot.ai/docs/en/integrations/llm-cli/
Canonical: https://ailoot.ai/docs/en/integrations/llm-cli/
Language: en

[Terminal agents](https://ailoot.ai/docs/en/integrations/#agents) 

# LLM

[Markdown](https://ailoot.ai/docs/en/integrations/llm-cli/index.md)

Terminal agent · OpenAI Chat, OpenAI Responses

| Format | Where to set it up |
| --- | --- |
| OpenAI Chat, OpenAI Responses | The extra-openai-models.yaml file in llm's configuration directory; set the key with llm keys set \<name\> |

## [](https://ailoot.ai/docs/en/integrations/llm-cli/#setup)Setup

Copy the configuration and replace `sk-...` with your key from the Ailoot Dashboard. Prefer storing the key in the environment variable `AILOOT_API_KEY`, if the application supports it.

Before starting, request GET /v1/models with your Ailoot key. Choose an exact model ID whose methods include POST /v1/chat/completions, POST /v1/responses, then use that ID in the configuration. For agents, also check tool support and the features required by your client version.

`extra-openai-models.yaml`

```text
- model_id: ailoot-sonnet
  model_name: claude-sonnet-5-5
  api_base: "https://api.ailoot.ai/v1"
  api_key_name: ailoot
  supports_tools: true
  vision: true
- model_id: ailoot-gpt
  model_name: gpt-6.1-sol
  api_base: "https://api.ailoot.ai/v1"
  api_key_name: ailoot
  responses: true
```

```bash
llm keys set ailoot
llm -m ailoot-sonnet 'Hello'
```

Example model: `claude-sonnet-5-5`. Choose any other model from the [catalog](https://ailoot.ai/models/en/) — check that it supports the format you need.

## [](https://ailoot.ai/docs/en/integrations/llm-cli/#notes)Good to know

Chat Completions is the default; responses: true switches the model to /responses. When api\_base is set, the OpenAI key is not sent, so api\_key\_name is required. This is a CLI utility for making requests, not an agent.

## [](https://ailoot.ai/docs/en/integrations/llm-cli/#check)Test

- For the OpenAI format, the URL is `https://api.ailoot.ai/v1` (or the full path if the application asks for a full URL).
- Ask a short question. If you get an error, check the code and Request ID, then consult [Errors and limits](https://ailoot.ai/docs/en/errors/).
- 404 immediately after setup almost always means the URL is wrong: an extra or missing `/v1`.
- 402 — insufficient balance for the reserve. Agents reserve more than chat: [why](https://ailoot.ai/docs/en/billing/reserve/).

Application documentation: [https://llm.datasette.io/en/stable/other-models.html](https://llm.datasette.io/en/stable/other-models.html)

Still have questions? Send your Request ID and a description — we'll help you troubleshoot.[Contact support](mailto:support@ailoot.ai)

## Ailoot · The company and its project portfolio





Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control.





The company and its project portfolio: millions of customers; monthly sales in the billions.





Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.