Text Generation

Endpoint

POST /v1/generate

Returns the result immediately — no polling needed.

Which endpoint to use for LLM? Check capabilities.endpoint from GET /v1/models:

Standard chat models (GPT-, Gemini-, etc.) have "endpoint": "/v1/chat/completions" — use POST /v1/chat/completions with messages[] (OpenAI-compatible format).
Some LLM models and all non-LLM models (STT, OCR, caption) have "endpoint": "/v1/generate" — use this endpoint with a prompt field.

For image generation use POST /v1/images/generations.

Request

string

required

Bearer <your-token>

string

required

application/json

Body

string

required

Model ID from GET /v1/models. Accepted types: llm, speech-to-text, image-to-text, video-to-text.

string

Text prompt or question. Required for LLM and most models.

string

System prompt for LLM models.

number

Maximum tokens for LLM response. Range: 1–32768.

number

default:"1"

Sampling temperature (0–2). Lower = more deterministic.

boolean

Include reasoning trace in LLM response.

string

Audio file URL for speech-to-text models.

string

Language hint for STT (e.g. vi, en). Pass auto for automatic detection.

string

Image URL for image-to-text, OCR, or vision models.

array

Array of image URLs for vision LLM models.

string

Video URL for video-to-text / captioning models.

string

Output format for OCR models. Values: json, markdown.

Examples

LLM — text generation (dùng id từ GET /v1/models với capabilities.endpoint: "/v1/generate"):

curl -X POST https://hypergate.store/v1/generate \
  -H "Authorization: Bearer your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<llm-model-id>",
    "prompt": "Explain async/await in JavaScript in 2 sentences.",
    "max_tokens": 200
  }'

Speech to text:

curl -X POST https://hypergate.store/v1/generate \
  -H "Authorization: Bearer your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai-whisper-turbo",
    "audio": "https://example.com/recording.mp3",
    "language": "vi"
  }'

OCR:

curl -X POST https://hypergate.store/v1/generate \
  -H "Authorization: Bearer your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "paddle-ocr",
    "image": "https://example.com/document.jpg",
    "output_format": "markdown"
  }'

Video captioning:

curl -X POST https://hypergate.store/v1/generate \
  -H "Authorization: Bearer your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "molmo2/video-captioner",
    "video": "https://example.com/clip.mp4"
  }'

Response `200`

Text / transcription:

{
  "model": "<model-id>",
  "output": "Async/await is syntactic sugar over Promises..."
}

Field	Description
`model`	Model ID used for the request.
`output`	Result — text for LLM/STT/OCR/caption.
`outputs`	Present only when the model returns multiple results.

For image generation use POST /v1/images/generations — it has its own response format.

Getting Started

API Reference

Guides

Endpoint

Request

Body

Examples

Response `200`

​Endpoint

​Request

​Body

​Examples

​Response 200

Endpoint

Request

Body

Examples

Response `200`