Skip to main content

​
Client Structure

The Dedalus Go SDK provides a unified client for accessing AI models across multiple providers including OpenAI, Anthropic, Google, xAI, Mistral, Groq, Fireworks, and DeepSeek. 
import (
    "github.com/dedalus-labs/dedalus-sdk-go"
    "github.com/dedalus-labs/dedalus-sdk-go/option"
)

client := githubcomdedaluslabsdedalussdkgo.NewClient(
    option.WithAPIKey("your-api-key"),
)

​
Available Services

The SDK is organized into the following service areas:

​
Chat

Generate conversational responses with support for streaming, function calling, and multimodal inputs.
  • Completions - Create chat completions with streaming support

​
Embeddings

Create vector embeddings for text inputs using various embedding models.
  • Create - Generate embeddings for text

​
Audio

Process and generate audio content.
  • Speech - Generate speech audio from text (text-to-speech)
  • Transcriptions - Transcribe audio files to text
  • Translations - Translate audio to English text

​
Images

Generate and manipulate images using AI models.
  • Generate - Create images from text prompts
  • Edit - Edit images using inpainting
  • Variations - Create variations of existing images

​
Models

Retrieve information about available models.
  • List - Get all available models
  • Get - Retrieve details about a specific model

​
Authentication

All API requests require authentication using an API key: 
client := githubcomdedaluslabsdedalussdkgo.NewClient(
    option.WithAPIKey("your-api-key"),
)

​
Error Handling

The SDK returns standard Go errors. Check for errors after each API call: 
response, err := client.Chat.Completions.New(ctx, params)
if err != nil {
    // Handle error
    log.Fatal(err)
}

​
Rate Limits

API endpoints are subject to rate limits based on your account tier. Handle rate limit errors appropriately:
  • 429 Too Many Requests: Rate limit exceeded
  • 402 Payment Required: Quota or balance issue

​
Best Practices

  1. Context Management: Always pass a context to API calls for timeout and cancellation support
  2. Error Handling: Check and handle errors for all API calls
  3. Streaming: Use streaming for real-time responses when appropriate
  4. Resource Cleanup: Close streaming connections properly

Build docs developers (and LLMs) love

Get started for freeTalk to us