Skip to main content

Getting started

The full OpenAPI description that powers this reference lives alongside the docs. You can import it into Postman, Hoppscotch, or your favourite SDK generator to bootstrap a client automatically.

AI Stats Gateway OpenAPI

View the specification file
All production traffic should target https://api.phaseo.app/v1. All endpoint paths in this page are relative to that /v1 base URL.

Authentication

All endpoints require a gateway API key to help mitigate abuse. Supply it as an Authorization: Bearer header. Keys use the format aistats_v1_sk_<kid>_<secret> and map back to the teams you manage inside the dashboard.
Authorization: Bearer aistats_v1_sk_<kid>_<secret>
If authentication fails you will receive a 401 error response.

Endpoint overview

The table below outlines the main endpoints available in the AI Stats Gateway right now:
EndpointDescription
POST /chat/completions, POST /responses, POST /messagesText generation across OpenAI-compatible and Anthropic-compatible surfaces.
POST /embeddings, POST /moderationsEmbeddings and moderation checks.
POST /audio/speech, POST /audio/transcriptions, POST /audio/translationsAudio generation and speech-to-text.
POST /images/generations, POST /images/editsImage generation and editing.
POST /videosCreate a video generation job (asynchronous).
GET /videos/{video_id}Poll the video job status until complete.
GET /videos/{video_id}/content, DELETE /videos/{video_id}Fetch completed video bytes or delete a job.
POST /music/generate, GET /music/generate/{music_id}Create and poll music generation jobs.
POST /ocr, POST /batches, GET /batches/{batch_id}, POST /files, GET /files, GET /files/{file_id}OCR is active; batch and file endpoints are currently placeholders returning 501 not_implemented.
GET /gateway/models, GET /data/models, GET /providers, GET /health, GET /generations?id=..., GET/POST /management/keys, GET/PATCH/DELETE /management/keys/{id}Platform API discovery and management endpoints.
Use the endpoints query parameter on GET /gateway/models to reproduce the per-surface catalogues (chat, moderations, embeddings, images, video, or audio) without bouncing between separate endpoints. The following endpoints are documented, but still under active work:
EndpointDescription
GET /endpoints, GET /keys, POST /keys, GET /keyComing Soon placeholder endpoints.
Responses include an optional usage and meta object with your usage, in both tokens and pricing, broken down into clear lines to see what costs what, as well as detailed timing and performance metadata, such as throughput, latency, and generation time, to support auditing and debugging.

Rate limits & billing

We apply no rate limits directly on our platform. Any rate limits are upstream, applied by providers themselves. We are working to get higher rate limits from upstream providers to ensure that users have a smooth experience. We apply credit checks prior to all requests made, ensuring that you have a minimum of $1.00 of credit in the team wallet. We do this to ensure that users do not accidentally rack up large bills on their accounts. You can top up your team wallet via the dashboard at any time, with payments typically going through within a few minutes.
Last modified on March 2, 2026