Flatkey REST API: Endpoints, Auth, and Request Format

The Flatkey API is a REST API that is fully compatible with the OpenAI API specification. API requests go to https://router.flatkey.ai/v1 — the same base URL for all endpoints, providers, and models. Authentication uses a Bearer token in the Authorization header, except for completed video content URLs.

Base URL

https://router.flatkey.ai/v1

Authentication

API requests must include your Flatkey API key as a Bearer token:

Authorization: Bearer sk-fk-your-api-key

Generate your API key in the console. See Authentication for full details. The anonymous GET /v1/videos/{task_id}/content URL is an exception. Treat it as sensitive because possession of the task URL grants access to the completed video.

Request format

All requests use HTTPS
Request bodies must be JSON (Content-Type: application/json)
Responses are JSON, SSE for streaming, or video/mp4 for completed video content

Available endpoints

Endpoint	Method	Description
`/v1/chat/completions`	POST	Chat and text generation (OpenAI-compatible)
`/v1/responses`	POST	OpenAI Responses API (stateful multi-turn)
`/v1/embeddings`	POST	Text embeddings
`/v1/images/generations`	POST	Image generation
`/v1/videos`	POST	Create a Seedance video-generation task
`/v1/videos/{task_id}`	GET	Retrieve Seedance task status and result
`/v1/videos/{task_id}/content`	GET	Download a completed video without Bearer authentication
`/v1/models`	GET	List available models

OpenAI SDK compatibility

Because the API is OpenAI-compatible, you can use the official OpenAI Python or Node.js SDK with no changes to the request code — just set base_url:

from openai import OpenAI

client = OpenAI(
    api_key="sk-fk-your-api-key",
    base_url="https://router.flatkey.ai/v1",
)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-fk-your-api-key",
  baseURL: "https://router.flatkey.ai/v1",
});

Versioning

Flatkey uses the same versioning scheme as the OpenAI API. The /v1 path prefix is stable. When new OpenAI API versions are released, Flatkey adds support while maintaining backward compatibility with /v1.

Rate limits

Rate limits are applied per API key. If you exceed the limit, you receive a 429 Too Many Requests response. Contact support@flatkey.ai if you need higher rate limits for production workloads.

Supported content types

Content type	Used for
`application/json`	JSON request bodies and API responses
`text/event-stream`	Streaming responses (when `stream: true`)
`video/mp4`	Completed video content

​Base URL

​Authentication

​Request format

​Available endpoints

​OpenAI SDK compatibility

​Versioning

​Rate limits

​Supported content types