Sage Inference API Reference

Complete API reference for all Sage Inference endpoints. Base URL: https://sage-api.devblocktechnologies.com

Live API Playground

Test Sage Inference API endpoints directly from your browser. Enter your API key, customize the request, and see live responses.

Request

Endpoint

API Key

Request Body (JSON)

{}

Response

⚡

Send a request to see the response here

Authentication

All API requests require authentication via Bearer token. Include your API key in the Authorization header of every request.

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

API keys start with sk-sage- and can be created and managed through the DevBlock Console.

Available Models

Model ID	Description	Cost
deepseek-v4-flash	Fast chat	0.0004 credits/token
deepseek-v4-pro	Advanced reasoning/coding	0.002 credits/token
deepseek-reasoner	Deep reasoning	0.002 credits/token
claude-sonnet-4-20250514	Anthropic's most balanced	0.006 credits/token
claude-haiku-3.5	Fast Claude	0.002 credits/token
o3-mini	OpenAI reasoning	0.004 credits/token
gpt-4o	OpenAI multimodal flagship	0.01 credits/token
gpt-4o-mini	Lightweight OpenAI	0.0008 credits/token

Quality Modes

Mode	Description
auto	Automatically selects quality based on model and task
low	Faster response, lower quality (suitable for simple tasks)
high	Higher quality, slower response (complex reasoning)
ultra	Maximum quality, uses multi-pass refinement

Endpoints

GET/v1/models

List all available models and their capabilities.

Response Format

{
  "object": "list",
  "data": [
    {
      "id": "deepseek-v4-flash",
      "object": "model",
      "created": 1700000000,
      "owned_by": "devblock"
    }
  ]
}

Example Request

curl https://sage-api.devblocktechnologies.com/v1/models \
  -H "Authorization: Bearer sk-sage-your-api-key"

POST/v1/chat/completions

Create a chat completion. Supports streaming, vision, and multi-modal inputs.

Request Parameters

Parameter	Type	Required	Description
model	string	Required	Model ID to use
messages	array	Required	Array of message objects
max_tokens	integer	Optional	Maximum tokens (default: 256)
temperature	number	Optional	Sampling temperature 0-2 (default: 1.0)
stream	boolean	Optional	Enable SSE streaming (default: false)

Response Format

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm doing well, thank you!"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 25,
    "total_tokens": 35
  }
}

Example Request

curl https://sage-api.devblocktechnologies.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-sage-your-api-key" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ],
    "temperature": 0.7,
    "max_tokens": 256
  }'

POST/v1/images/generations

Generate images from text descriptions.

Request Parameters

Parameter	Type	Required	Description
model	string	Required	Model ID to use
prompt	string	Required	Text description of the image
n	integer	Optional	Number of images (default: 1)
size	string	Optional	Image size (e.g. 1024x1024)

Response Format

{
  "created": 1700000000,
  "data": [
    {
      "url": "https://sage-api.devblocktechnologies.com/v1/images/abc123.png"
    }
  ]
}

Example Request

curl https://sage-api.devblocktechnologies.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-sage-your-api-key" \
  -d '{
    "model": "deepseek-v4-flash",
    "prompt": "A serene mountain landscape at sunset",
    "n": 1,
    "size": "1024x1024"
  }'

POST/v1/audio/transcriptions

Transcribe audio files to text using speech-to-text models.

Request Parameters

Parameter	Type	Required	Description
model	string	Required	Model ID to use
file	file	Required	Audio file to transcribe
language	string	Optional	Language code (optional)

Response Format

{
  "text": "The transcript of the audio file."
}

Example Request

curl https://sage-api.devblocktechnologies.com/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-sage-your-api-key" \
  -F "model=deepseek-v4-flash" \
  -F "file=@audio.mp3"

POST/v1/audio/speech

Generate speech from text using text-to-speech models.

Request Parameters

Parameter	Type	Required	Description
model	string	Required	Model ID to use
input	string	Required	Text to convert to speech
voice	string	Optional	Voice ID (default: alloy)

Response Format

Binary audio data (MP3 format)

Example Request

curl https://sage-api.devblocktechnologies.com/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-sage-your-api-key" \
  -d '{
    "model": "deepseek-v4-flash",
    "input": "Hello, welcome to DevBlock Sage Inference.",
    "voice": "alloy"
  }' \
  --output speech.mp3

SDK Examples (Python)

Sage Inference is fully compatible with the OpenAI Python SDK. Simply point the base URL to our endpoint.

from openai import OpenAI

client = OpenAI(
    base_url="https://sage-api.devblocktechnologies.com/v1",
    api_key="sk-sage-your-api-key"
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
    ],
    temperature=0.7,
    max_tokens=256
)

print(response.choices[0].message.content)

Error Codes

Code	Description
400	Bad Request - Invalid request parameters
401	Unauthorized - Missing or invalid API key
402	Payment Required - Insufficient credits
404	Not Found - Invalid endpoint or model
429	Too Many Requests - Rate limit exceeded
500	Internal Server Error - Server-side issue

Interactive Examples

Copy these curl commands to test the API directly from your terminal.

List Models

curl https://sage-api.devblocktechnologies.com/v1/models \
  -H "Authorization: Bearer sk-sage-your-api-key"

Chat Completion (Streaming)

curl https://sage-api.devblocktechnologies.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-sage-your-api-key" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Tell me a joke"}],
    "stream": true
  }'

Chat Completion (Non-Streaming)

curl https://sage-api.devblocktechnologies.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-sage-your-api-key" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [
      {"role": "user", "content": "Write a poem about AI"}
    ],
    "temperature": 0.8,
    "max_tokens": 500
  }'