API
A compatible AI API with visible request paths
Keep a familiar request shape while you select a public model identifier and manage access with platform API keys.
Connect through the interface your tool expects
- Send OpenAI-compatible chat completion requests.
- Use the Anthropic Messages-compatible endpoint.
- List models and inspect usage by request and API key.
Illustrative request lifecycle: a key authenticates a compatible request before the response returns.
curl https://api.provod.ai/v1/chat/completions \
-H "Authorization: Bearer $PROVOD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openai/gpt-5.4","messages":[{"role":"user","content":"Summarize this harmless request."}],"stream":true}'| Interface | Path | Lifecycle |
|---|---|---|
| OpenAI-compatible | /v1/chat/completions | Request and streamed response |
| Anthropic Messages | /v1/messages | Request and response |
From key to request record
Create a key, choose a public model identifier, send a compatible request, then review the resulting usage record.
For developers, tools, and internal integrations
Use the API when an application or coding tool needs a compatible chat, image, or Messages interface.
API setup answers
Keep keys private and choose the interface that matches your client.
Use the setup guide for your client: OpenAI-compatible clients use the API root, while Claude Code uses its Anthropic-compatible root.
Store the key in a trusted server environment. If it is exposed, revoke it and create a replacement; never send the full key to support.
The Responses endpoint is not currently published. Use a documented compatible interface when your tool supports one.
Retry transient failures with bounded backoff only before output begins. Retrying after output starts can duplicate work and confirmed usage.