---
title: "Aider setup: OPENAI_API_BASE and model id — AI Creator API"
description: "How to connect Aider to AI Creator API: the OPENAI_API_BASE and OPENAI_API_KEY variables and a model id with the openai/ prefix."
url: https://llm.aicreator.app/en/docs/aider/
lang: en
updated: 2026-11-10
---

# Aider

Aider talks to us over OpenAI Chat Completions. It takes the address and the key from environment variables and the model from a launch flag.

> **What is verified.** We have not yet verified this setup with a live run of Aider against our API. Our notes cite no Aider documentation page; they (November 9, 2026) hold only `OPENAI_API_BASE`, `OPENAI_API_KEY`. Not checked against the documentation: the openai/ prefix of the model id and the launch command. If something does not match, [tell support](https://t.me/let_support).

## Setup

```bash
export OPENAI_API_BASE=https://api.aicreator.app/v1
export OPENAI_API_KEY=sk-aic-…
aider --model openai/gpt-6-astra
```

- `OPENAI_API_BASE` — `https://api.aicreator.app/v1`, with `/v1` at the end.
- `OPENAI_API_KEY` — your `sk-aic-…` key from the [Keys page](https://llm.aicreator.app/en/app/keys/).
- `--model` — the model’s id from our list with the `openai/` prefix, as in the example.

## Models

Any model on the Chat protocol will do; they are listed in [Models and prices](https://llm.aicreator.app/en/docs/models/). The API itself gives the list for your key:

```bash
curl "https://api.aicreator.app/v1/models?surface=chat" \
  -H "Authorization: Bearer $AIC_API_KEY"
```

An id that is not on the list returns 400 `model_not_available`.

## Things to know

- One key runs up to 4 requests at a time; the next one gets 429 `concurrent_requests` with a `retry-after` header.
- A Chat Completions stream of ours always ends with a chunk that has an empty `choices: []` and the token usage; that is how we charge by actual tokens.
- From Russia, if `https://api.aicreator.app` is unreachable, set `OPENAI_API_BASE` to `https://api-ru.aicreator.app/v1`: the key and the balance are the same.

If a request fails, see [Troubleshooting](https://llm.aicreator.app/en/docs/troubleshooting/).