Overview

Base URL: https://api.hinow.ai/v1

Authentication: Bearer token via the Authorization header.

All requests use JSON. All responses return {"success": true, "data": {...}}.

Browse available models at: https://hinow.ai/models/hub

Get your API key at: https://platform.hinow.ai/manage/api-keys

API Endpoints Summary

Chat Completion (Text to Text)

Endpoint: POST https://api.hinow.ai/v1/chat/completions

Categories: text_to_text, chat, code, reasoning

Generate text responses from language models. Supports multi-turn conversations, streaming, and function calling.

cURL Example

curl -X POST https://api.hinow.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "deepseek-ai/deepseek-v4-pro",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Python Example

import requests

response = requests.post(
    "https://api.hinow.ai/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json={
        "model": "deepseek-ai/deepseek-v4-pro",
        "messages": [{"role": "user", "content": "Explain quantum computing"}]
    }
)
print(response.json())

Response Example

{"success": true, "data": {"id": "chatcmpl-abc123", "model": "deepseek-ai/deepseek-v4-pro", "choices": [{"message": {"role": "assistant", "content": "Quantum computing uses qubits..."}}], "cost": {"amount": 0.0003, "currency": "USD"}}}

Vision (Image to Text)

Endpoint: POST https://api.hinow.ai/v1/chat/completions

Categories: image_to_text, vision

Analyze images using vision-capable models. Send images via URL or base64 in the messages content array.

cURL Example

curl -X POST https://api.hinow.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "qwen/qwen-image",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "Describe this image"},
          {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}}
        ]
      }
    ]
  }'

Python Example

import requests

response = requests.post(
    "https://api.hinow.ai/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json={
        "model": "qwen/qwen-image",
        "messages": [{"role": "user", "content": [
            {"type": "text", "text": "Describe this image"},
            {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}}
        ]}]
    }
)
print(response.json())

Response Example

{"success": true, "data": {"id": "chatcmpl-abc123", "model": "qwen/qwen-image", "choices": [{"message": {"role": "assistant", "content": "The image shows..."}}], "cost": {"amount": 0.001, "currency": "USD"}}}

Image Generation (Text to Image)

Endpoint: POST https://api.hinow.ai/v1/images

Categories: text_to_image, image_to_image, image_editing, image_to_3d, text_to_3d

Generate images from text prompts. For image-to-image, include an "images" array with source image URLs or base64.

cURL Example

curl -X POST https://api.hinow.ai/v1/images \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "black-forest-labs/flux-2-pro",
    "prompt": "A futuristic city skyline at sunset, cyberpunk style"
  }'

Python Example

import requests

response = requests.post(
    "https://api.hinow.ai/v1/images",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json={
        "model": "black-forest-labs/flux-2-pro",
        "prompt": "A futuristic city skyline at sunset, cyberpunk style"
    }
)
print(response.json())

Response Example

{"success": true, "data": {"urls": ["https://s3.us1-stlouis.hinow.ai/..."], "model": "black-forest-labs/flux-2-pro", "category": "text_to_image", "cost": {"amount": 0.04, "currency": "USD", "value_type": "per_image"}}}

Embeddings (Text to Embedding)

Endpoint: POST https://api.hinow.ai/v1/embeddings

Categories: text_to_embedding, embeddings

Generate vector embeddings from text for semantic search, RAG, clustering, and classification.

cURL Example

curl -X POST https://api.hinow.ai/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "openai/text-embedding-3-small",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

Python Example

import requests

response = requests.post(
    "https://api.hinow.ai/v1/embeddings",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json={
        "model": "openai/text-embedding-3-small",
        "input": "The quick brown fox jumps over the lazy dog"
    }
)
print(response.json())

Response Example

{"success": true, "data": {"embedding": [0.0023, -0.0091, 0.0152, ...], "model": "openai/text-embedding-3-small", "dimensions": 1536, "cost": {"amount": 0.0001, "currency": "USD", "value_type": "mtoken"}}}

Text to Speech (TTS)

Endpoint: POST https://api.hinow.ai/v1/audio/speech

Categories: text_to_audio, audio_generation, audio_to_audio, audio_to_voice

Convert text to spoken audio. Returns a URL to the generated audio file.

cURL Example

curl -X POST https://api.hinow.ai/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "inworld/tts-1.5-max",
    "prompt": "Hello! Welcome to HiNow AI platform."
  }'

Python Example

import requests

response = requests.post(
    "https://api.hinow.ai/v1/audio/speech",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json={
        "model": "inworld/tts-1.5-max",
        "prompt": "Hello! Welcome to HiNow AI platform."
    }
)
print(response.json())

Response Example

{"success": true, "data": {"url": "https://s3.us1-stlouis.hinow.ai/...", "model": "inworld/tts-1.5-max", "category": "text_to_audio", "cost": {"amount": 0.015, "currency": "USD", "value_type": "tts_hybrid"}}}

Speech to Text (STT / Transcription)

Endpoint: POST https://api.hinow.ai/v1/audio/transcriptions

Categories: audio_to_text, speech_to_text, transcription

Transcribe audio files to text. Provide an audio URL to the file you want transcribed.

cURL Example

curl -X POST https://api.hinow.ai/v1/audio/transcriptions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "openai/whisper-large-v3",
    "audio_url": "https://example.com/audio.mp3"
  }'

Python Example

import requests

response = requests.post(
    "https://api.hinow.ai/v1/audio/transcriptions",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json={
        "model": "openai/whisper-large-v3",
        "audio_url": "https://example.com/audio.mp3"
    }
)
print(response.json())

Response Example

{"success": true, "data": {"text": "Hello, welcome to HiNow AI platform...", "model": "openai/whisper-large-v3", "category": "audio_to_text", "cost": {"amount": 0.006, "currency": "USD", "value_type": "per_minute"}}}

Video Generation

Endpoint: POST https://api.hinow.ai/v1/videos

Categories: text_to_video, image_to_video, video_to_video, video_enhancement, video_upscale

Generate videos from text or image prompts. For image-to-video, include an "images" array. For video processing, include a "video_url".

cURL Example

curl -X POST https://api.hinow.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "wan-ai/wan2.2-t2v-a14b",
    "prompt": "A cat playing with a ball in a sunny garden"
  }'

Python Example

import requests

response = requests.post(
    "https://api.hinow.ai/v1/videos",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json={
        "model": "wan-ai/wan2.2-t2v-a14b",
        "prompt": "A cat playing with a ball in a sunny garden"
    }
)
print(response.json())

Response Example

{"success": true, "data": {"url": "https://s3.us1-stlouis.hinow.ai/...", "model": "wan-ai/wan2.2-t2v-a14b", "category": "text_to_video", "cost": {"amount": 0.50, "currency": "USD", "value_type": "per_second"}}}

Authentication

All API requests require a Bearer token in the Authorization header:

Authorization: Bearer YOUR_HINOW_API_KEY

Get your API key at https://platform.hinow.ai/manage/api-keys

Available SDKs

• Python: pip install hinow-ai
• TypeScript/Node.js: npm install hinow-ai
• Go: go get github.com/hinow-ai/sdk-go
• Java: Maven/Gradle — com.github.hinow-ai:sdk-java
• C#: dotnet add package hinow-ai
• Rust: cargo add hinow-ai
• PHP: composer require hinow-ai/hinow-ai
• Ruby: gem install hinow-ai
• Kotlin: Maven/Gradle — com.github.hinow-ai:sdk-kotlin
• Swift: Swift Package Manager — https://github.com/hinow-ai/sdk-swift.git