Skip to main content
MIRA supports the OpenAI API for both the RLM and Native Agent engines. You can use any model available on your OpenAI account — not just the suggestions shown in the UI.

​
Setup

1

Get an API key

Log in to platform.openai.com, go to API keys, and create a new secret key.
2

Save the key in MIRA

Press ⌘, to open Settings → API Tokens tab → click Add token.
FieldValue
LabelOpenAI API Key (or any name)
Env varOPENAI_API_KEY
ValueYour sk-… key
Click Save. The key is encrypted with safeStorage and injected as an environment variable each time an engine starts.
3

Select OpenAI in the Engine tab

Press ⌘, → Engine tab → in the Provider & Model section, click the OpenAI button.
4

Enter a model ID

MIRA shows suggestion chips for common models. You can also type any valid OpenAI model ID directly into the Model ID field — any model on your account works.
PurposeSuggested model
General chatgpt-4o
Fast / low costgpt-4o-mini
Strong reasoninggpt-4-turbo
Budget optiongpt-3.5-turbo
5

Save

Click Save & restart bridge. The engine restarts automatically.

​
Suggested models

The following models appear as quick-select chips in the Engine settings. You are not limited to these — type any model ID your account can access.
ModelIDNotes
GPT-4ogpt-4oBest quality, multimodal
GPT-4o Minigpt-4o-miniFast and cost-effective
GPT-4 Turbogpt-4-turboHigh context, strong reasoning
GPT-3.5 Turbogpt-3.5-turboBudget option for simple tasks
OpenAI regularly releases new models (e.g. gpt-4o-2024-11-20, o1, o3-mini). Paste the exact model ID from the OpenAI models page into the Model ID field.

​
Troubleshooting

ErrorFix
401 UnauthorizedAPI key is incorrect or expired — regenerate it on platform.openai.com
429 Too Many RequestsYou are hitting rate limits — reduce concurrency in eval settings
model_not_foundYour account does not have access to this model — check on platform.openai.com
Edit this page — Open a pull request