OpenAI Configuration

Connect Glyph to OpenAI’s API to use the current GPT-5 family, GPT-4.1, and other OpenAI models.

Prerequisites

• OpenAI API account: platform.openai.com
• API key with appropriate permissions
• Sufficient API credits

Setup

Configuration

Provider Settings

• Service: openai
• Base URL: https://api.openai.com/v1 (default)
• Authentication: Bearer token (API key)

Custom Endpoint

To use a custom OpenAI endpoint (proxy, Azure OpenAI, etc.):

1. Set Base URL to your endpoint
2. Add any required headers in Custom Headers
3. Enable Allow Private Hosts if using localhost

Base URL: https://<resource-name>.openai.azure.com/openai/deployments/<deployment-name>
Headers:
[
  { "key": "api-key", "value": "your-azure-api-key" },
  { "key": "api-version", "value": "2024-02-15-preview" }
]

Base URL: https://your-proxy.com/v1
Headers: (if required by proxy)

Model Selection

Glyph fetches the latest model list from OpenAI’s /v1/models endpoint.

Recommended Model Families

Chat Completion Models Only

Glyph uses the /v1/chat/completions endpoint. Ensure your selected model supports chat completions.

Model 'gpt-3.5-turbo-instruct' is not chat-completions compatible.
Select a chat-capable model (for example, a current GPT-5 or GPT-4.1 model).

Features

Chat Mode

Conversational interaction without tools:

• Back-and-forth dialogue
• Faster responses (no tool overhead)
• Best for brainstorming and discussion

Create Mode

AI with workspace access:

• File reading via read_file tool
• Search notes with search_notes tool
• List files with list_dir tool
• Best for research and knowledge retrieval

Context Attachment

Attach files or folders to ground responses:

• Attach via context menu in AI panel
• Mention files with @filename syntax
• Context sent in system message
• Token estimates shown before sending

API Usage and Billing

Glyph makes direct API calls to OpenAI:

• You are billed by OpenAI based on token usage
• No additional fees from Glyph
• Check usage at platform.openai.com/usage

Cost Estimation

Use the context manifest in Glyph to estimate token usage, then compare it with the current pricing on OpenAI’s pricing page .

Rate Limits

OpenAI enforces rate limits based on your usage tier and the specific model you choose.

If you hit rate limits, Glyph displays the error from OpenAI. Wait before retrying or upgrade your tier.

Troubleshooting

”API key not set for this profile”

Solution: Add your OpenAI API key in Settings → AI.

”model list failed (401)”

Solution: Your API key is invalid or expired. Generate a new key from OpenAI Platform.

”model list failed (429)”

Solution: You’ve hit OpenAI’s rate limit. Wait before retrying.

”This model is not chat-completions compatible”

Solution: Select a current chat-capable model like gpt-5, gpt-5-mini, or gpt-4.1.

Model list is empty

Solution: Type the model ID manually (for example, gpt-5 or gpt-4.1). The model can still work even if the list fetch failed.

Responses are slow

Possible causes:

• Large context (10K+ tokens)
• Complex tool usage in create mode
• OpenAI API latency

Solution: Try a faster model like gpt-5-mini or reduce context size.

Security Best Practices

Next Steps