ReferenceAPI reference
Every REST endpoint shares one API key, one model catalog, one balance and one set of limits.
Base URL: https://api.framewharf.com/v1. API keys start with sk-.
Authorization: Bearer sk-your_api_keyMessages also accepts x-api-key: sk-your_api_key.
| Method | Path | Description |
|---|---|---|
| GET | /v1/models | The models, supported endpoints and prices available to your API key |
| POST | /v1/chat/completions | Chat Completions |
| POST | /v1/responses | Responses, tools and streaming |
| POST | /v1/messages | The Anthropic messages protocol |
| POST | /v1/messages/count_tokens | Count tokens for Messages without spending credit |
| POST | /v1/images/generations | Generate images, returned as a temporary download link |
| POST | /v1/images/edits | Edit an existing image from a prompt |
| POST | /v1/videos | Create a video generation job |
| GET | /v1/videos/{id} | Video job status |
| GET | /v1/videos/{id}/content | Download a finished video |
| POST | /v1/interactions | Create or edit Gemini Omni video, returned directly as base64 |
Each request is capped at 32 MB. Limits apply per account and are shared by all of its API keys: standard models get 45 requests per minute and 9 concurrent requests; Claude on a standard API key gets 8 requests per minute and 2 concurrent requests; Claude on the premium plan gets 30 requests per minute and 6 concurrent requests. Keep the x-ltn-request-id header if you need support.