ARCANAOpenAI
OpenAI provides GPT-4o, o1, o3, and other frontier models. Set one environment variable and Arcana detects it automatically.
Setup
# 1. Get your API key from https://platform.openai.com/api-keys
export OPENAI_API_KEY=sk-...
# 2. Verify detection
arcana doctor
# 3. Run
arcana run "hello"Available Models
| Model | Context | Best For |
|---|---|---|
gpt-4o | 128K | General purpose, tool use, coding |
gpt-4o-mini | 128K | Fast, cheap, good for extraction |
o1 | 128K | Deep reasoning, math, complex analysis |
o3 | 200K | Advanced reasoning, coding challenges |
o3-mini | 200K | Fast reasoning, cost-effective |
Config File
You can also set the provider in ~/.arcana/config.json:
{
"provider": "openai",
"model": "gpt-4o",
"utilityModel": "gpt-4o-mini"
}Environment Variables
| Variable | Description |
|---|---|
OPENAI_API_KEY | Your OpenAI API key (required) |
OPENAI_BASE_URL | Custom base URL for compatible proxies |
OPENAI_ORG_ID | Organization ID for billing (optional) |
Pricing Notes
OpenAI charges per token. Approximate costs per 1M tokens:
| Model | Input | Output |
|---|---|---|
| gpt-4o | $2.50 | $10.00 |
| gpt-4o-mini | $0.15 | $0.60 |
| o1 | $15.00 | $60.00 |
| o3 | $10.00 | $40.00 |
Prices may change. Check openai.com/pricing for current rates.
Tips
- Use
gpt-4o-minias theutilityModelfor extraction and compaction tasks to save costs o1ando3are slower but excel at complex reasoning- Set
OPENAI_BASE_URLto use OpenAI-compatible APIs (e.g., Azure, local proxies) - Run
arcana doctorto verify your key is detected