OpenAI
Connect Sythoria to OpenAI's API to chat with GPT-4o, GPT-4o Mini, o1, and more. OpenAI offers the most widely-used commercial language models with strong general-purpose performance.
Prerequisites
- An OpenAI account with billing enabled
- An API key from the OpenAI dashboard
Setup
- Go to platform.openai.com/api-keys
- Click Create new secret key and copy it
- In Sythoria, open Settings from the sidebar
- Select OpenAI from the Provider Preset dropdown — the API base URL and default model fill in automatically
- Paste your API key into the API Key field
- The connection indicator should turn green within a few seconds
Your API key is stored only in the application's local storage. It is never sent to Sythoria's servers. See Privacy & Security.
Default configuration
| Setting | Value |
|---|---|
| API Base | https://api.openai.com/v1/chat/completions |
| Default Model | gpt-4o |
| API Format | OpenAI Chat Completions |
| Streaming | Supported |
Available models
The model dropdown auto-populates with models available to your API key. Common options:
| Model ID | Best for | Context window |
|---|---|---|
gpt-4o | General-purpose tasks, multi-step reasoning | 128K |
gpt-4o-mini | Fast, cost-effective everyday use | 128K |
o1 | Complex reasoning, math, coding | 200K |
o1-mini | Lightweight reasoning tasks | 128K |
gpt-4-turbo | High-performance instruction following | 128K |
o3-mini | High-speed reasoning and coding | 200K |
Check platform.openai.com/models for the full list and current availability.
Pricing
OpenAI charges per token. Rates vary by model. Check openai.com/pricing for current rates.
Switching models mid-conversation
You can switch to a different OpenAI model at any time using the model dropdown in the chat input bar. Each new message uses the currently selected model, so you can start with GPT-4o and switch to o1 for a harder question — all within the same conversation.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
| 401 Unauthorized | API key is invalid or expired | Generate a new key at platform.openai.com/api-keys |
| 429 Rate Limit | Exceeded your usage tier's rate limit | Wait a moment, or upgrade your OpenAI plan at platform.openai.com/account/billing |
| Model not found | Model name is incorrect or unavailable to your account | Verify the model ID at platform.openai.com/models |
| 402 Payment required | No billing method on file | Add a payment method at platform.openai.com/account/billing |
| Connection indicator red | Network issue or invalid API base | Check that the API base URL is https://api.openai.com/v1/chat/completions and try clicking Refresh |
