Build with Ethical AI
Full-featured API access to Thaura's AI capabilities. Image analysis and document parsing - all with privacy by design.

Quick Start Guide
Get up and running with the Thaura Partner API in minutes
Authentication
All requests must include an Authorization header with your API key:
Authorization: Bearer YOUR_API_KEYAPI Access
Create your API key in Settings → API → API Keys to get started with the Thaura API.
Prepaid Billing
Pay only for what you use: $0.50 per million input tokens, $2.00 per million output tokens. Add funds in Settings → API → Billing.
Inference Endpoint
Simplified Attachments
Now supports sending attachments as simple base64 strings! No need for complex object structures.
/v1/chat/completionsRequest Parameters:
messagesMessage array. Can include custom system prompts via system role messages. Default: "You are Thaura, an ethical AI assistant."modelModel to use - only "thaura" is supported (default: "thaura"). Other model names will return an error.streamEnable SSE streaming (default: false)temperatureControl response creativity (0.0-2.0, default: 0.7)attachmentsFile attachments - simple base64 string or array (images, PDFs, audio)max_tokensMaximum tokens to generateresponse_formatControl output format (e.g., JSON-only responses)toolsArray of function/tool definitions with JSON schemas for function callingtool_choiceControl tool usage: "auto" (default), "required", "none", or specific tool nameparallel_tool_callsEnable/disable parallel function calling (boolean)Response Formats
Non-Streaming Response (Thaura Format):
{
"id": "chatcmpl-...",
"object": "chat.completion",
"created": 1234567890,
"model": "thaura",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": "The AI response text..."
},
"finish_reason": "stop"
}],
"usage": {
"prompt_tokens": 52,
"completion_tokens": 18,
"total_tokens": 70
}
}Streaming Response (Thaura SSE Format):
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1234567890,"model":"thaura","choices":[{"index":0,"delta":{"content":"Response "},"finish_reason":null}]}
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1234567890,"model":"thaura","choices":[{"index":0,"delta":{"content":"text..."},"finish_reason":null}]}
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1234567890,"model":"thaura","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
data: [DONE]Streaming with Token Usage:
// Token usage is included in the final streaming chunk
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1234567890,"model":"thaura","choices":[{"index":0,"delta":{"content":"text"},"finish_reason":null}]}
...
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1234567890,"model":"thaura","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":52,"completion_tokens":18,"total_tokens":70}}
data: [DONE]
// To enable usage in streaming, include:
{
"stream": true,
"stream_options": { "include_usage": true }
}Error Response:
{
"error": "Error message"
}
// Status Codes:
// 400: Invalid request
// 401: Invalid API key
// 500: Internal errorCode Examples
Ready-to-use examples for common use cases
curl -X POST https://backend.thaura.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"messages": [
{"role": "system", "content": "You are an ethical AI assistant"},
{"role": "user", "content": "What is 2+2?"}
],
"stream": true
}'Thaura CLI
All API functionalities included in a powerful command-line interface. Available for macOS and Linux.
Install with one command
curl -fsSL https://thaura.ai/downloads/install.sh | bashThe installer automatically detects your platform and architecture (x64/arm64)
Start Building with Ethical AI Today
Create your API keys instantly in Settings and start building with Thaura AI.