OpenAI
OpenAI provides the GPT series of models, including GPT-4o, GPT-4, and GPT-3.5.
Setup
- Get an API key from platform.openai.com/api-keys
- In Alma, go to Settings → Providers → Add Provider
- Select OpenAI as the provider type
- Enter your API key
- Click Save
Available Models
After setup, Alma fetches available models automatically. Common models include:
| Model | Description | Context Window |
|---|---|---|
| gpt-4o-mini | Smaller, faster, cost-effective version of GPT-4o | 128K |
| gpt-4o | Flagship model, multimodal | 128K |
| gpt-4-turbo | Previous generation flagship | 128K |
| gpt-4 | Original GPT-4 | 8K |
| gpt-3.5-turbo | Fast and cost-effective | 16K |
| o1-preview | Reasoning model (extended thinking) | 128K |
| o1-mini | Smaller reasoning model | 128K |
Configuration Options
Base URL
Leave empty for official OpenAI API. Set a custom URL for:
- OpenAI-compatible proxies
- Self-hosted models
- Regional endpoints
Organization ID
If your API key belongs to multiple organizations, specify the organization ID to use.
Features
Vision
GPT-4o and GPT-4-turbo support image inputs. Attach images to your messages for visual analysis.
Tools
OpenAI models fully support Alma's tool system for file operations, web search, and more.
JSON Mode
Request structured JSON output for parsing and automation.
Pricing
See OpenAI Pricing for current rates. Costs are based on:
- Input tokens (your messages)
- Output tokens (AI responses)
- Image inputs (for vision models)
Troubleshooting
"Invalid API Key"
- Verify the key at platform.openai.com
- Check for extra spaces in the key
- Ensure the key has not been revoked
"Rate Limited"
- You've exceeded your usage tier limits
- Wait a few minutes or upgrade your plan
- Consider using a smaller model
"Model Not Found"
- The model may not be available in your region
- Check model availability in your OpenAI dashboard
- Try fetching models again