Go - Tinfoil Documentation

Go SDK

Go SDK for Tinfoil’s secure AI inference API GitHub: tinfoil-go

Overview

The Tinfoil Go SDK is a wrapper around the OpenAI Go client that provides secure communication with Tinfoil enclaves. It has the same API as the OpenAI SDK with additional security features including automatic verification that the endpoint is running in a secure Tinfoil enclave, TLS certificate pinning, and attestation validation.

Installation

New to Go? Start here - Project Setup

If you don’t have a Go module set up yet, initialize a new one:

# Create a new directory for your project
mkdir my-tinfoil-app
cd my-tinfoil-app

# Initialize a Go module
go mod init my-tinfoil-app

Add the Tinfoil SDK to your project:

go get github.com/tinfoilsh/tinfoil-go

tinfoil-go currently relies on a specific feature in go-sev-guest that hasn’t been upstreamed yet. This requires adding the following line to your go.mod:

replace github.com/google/go-sev-guest => github.com/tinfoilsh/go-sev-guest v0.0.0-20250704193550-c725e6216008

Migration from OpenAI

Migrating from OpenAI to Tinfoil is straightforward. The client is designed to be compatible with the OpenAI Go client:

// Before (OpenAI)
- import (
- 	"github.com/openai/openai-go/v2"
- 	"github.com/openai/openai-go/v2/option"
- )
-
- client := openai.NewClient(
-    option.WithAPIKey("OPENAI_API_KEY")
- )

// After (Tinfoil)
+ import (
+ 	"github.com/openai/openai-go/v2"
+ 	"github.com/openai/openai-go/v2/option"
+ 	"github.com/tinfoilsh/tinfoil-go"
+ )
+
+ client, err := tinfoil.NewClient(
+ 	option.WithAPIKey("TINFOIL_API_KEY")),
+ )

All method signatures remain the same since tinfoil.NewClient() returns a standard OpenAI client with built-in security features.

Usage

// 1. Create a client
client, err := tinfoil.NewClient(
	option.WithAPIKey(os.Getenv("TINFOIL_API_KEY")),
)
if err != nil {
	log.Fatal(err)
}

// 2. Use client as you would openai.Client 
// see https://pkg.go.dev/github.com/openai/openai-go for API documentation

Model Examples

Below are specific examples for each supported model. Click on any model to see its configuration and usage example.

Chat Models

DeepSeek V3.1 Terminus

package main

import (
    "context"
    "fmt"
    "log"
    "os"

    "github.com/openai/openai-go/v2"
    "github.com/openai/openai-go/v2/option"
    "github.com/tinfoilsh/tinfoil-go"
)

func main() {
    // Configure client for DeepSeek V3.1 Terminus
    client, err := tinfoil.NewClient(
        option.WithAPIKey(os.Getenv("TINFOIL_API_KEY")),
    )
    if err != nil {
        log.Fatal(err)
    }

    // Example: Multi-step agentic workflow
    chatCompletion, err := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
        Messages: []openai.ChatCompletionMessageParamUnion{
            openai.UserMessage("Write a Go function to validate email addresses using regex, then test it with several examples and debug any issues."),
        },
        Model: "deepseek-v31-terminus",
    })

    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(chatCompletion.Choices[0].Message.Content)
}

DeepSeek R1

package main

import (
    "context"
    "fmt"
    "log"
    "os"

    "github.com/openai/openai-go/v2"
    "github.com/openai/openai-go/v2/option"
    "github.com/tinfoilsh/tinfoil-go"
)

func main() {
    // Configure client for DeepSeek R1
    client, err := tinfoil.NewClient(
        option.WithAPIKey(os.Getenv("TINFOIL_API_KEY")),
    )
    if err != nil {
        log.Fatal(err)
    }

    // Example: Complex reasoning task
    chatCompletion, err := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
        Messages: []openai.ChatCompletionMessageParamUnion{
            openai.UserMessage("Solve this step by step: If a train travels 120 miles in 2 hours, and then increases its speed by 25% for the next 3 hours, how far does it travel in total?"),
        },
        Model: "deepseek-r1-0528",
    })

    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(chatCompletion.Choices[0].Message.Content)
}

Mistral Small 3.1 24B

package main

import (
    "context"
    "fmt"
    "log"
    "os"

    "github.com/openai/openai-go/v2"
    "github.com/openai/openai-go/v2/option"
    "github.com/tinfoilsh/tinfoil-go"
)

func main() {
    // Configure client for Mistral Small 3.1 24B
    client, err := tinfoil.NewClient(
        option.WithAPIKey(os.Getenv("TINFOIL_API_KEY")),
    )
    if err != nil {
        log.Fatal(err)
    }

    // Example: Multilingual conversation
    chatCompletion, err := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
        Messages: []openai.ChatCompletionMessageParamUnion{
            openai.UserMessage("Explain the concept of machine learning in both English and French."),
        },
        Model: "mistral-small-3-1-24b",
    })

    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(chatCompletion.Choices[0].Message.Content)
}

Llama 3.3 70B

package main

import (
    "context"
    "fmt"
    "log"
    "os"

    "github.com/openai/openai-go/v2"
    "github.com/openai/openai-go/v2/option"
    "github.com/tinfoilsh/tinfoil-go"
)

func main() {
    // Configure client for Llama 3.3 70B
    client, err := tinfoil.NewClient(
        option.WithAPIKey(os.Getenv("TINFOIL_API_KEY")),
    )
    if err != nil {
        log.Fatal(err)
    }

    // Example: Conversational AI
    chatCompletion, err := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
        Messages: []openai.ChatCompletionMessageParamUnion{
            openai.UserMessage("What are the key differences between renewable and non-renewable energy sources?"),
        },
        Model: "llama3-3-70b",
    })

    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(chatCompletion.Choices[0].Message.Content)
}

GPT-OSS 120B

package main

import (
    "context"
    "fmt"
    "log"
    "os"

    "github.com/openai/openai-go/v2"
    "github.com/openai/openai-go/v2/option"
    "github.com/tinfoilsh/tinfoil-go"
)

func main() {
    // Configure client for GPT-OSS 120B
    client, err := tinfoil.NewClient(
        option.WithAPIKey(os.Getenv("TINFOIL_API_KEY")),
    )
    if err != nil {
        log.Fatal(err)
    }

    // Example: Advanced reasoning with configurable effort levels
    chatCompletion, err := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
        Messages: []openai.ChatCompletionMessageParamUnion{
            openai.UserMessage("Analyze the trade-offs between different database architectures for a high-traffic e-commerce platform."),
        },
        Model: "gpt-oss-120b",
    })

    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(chatCompletion.Choices[0].Message.Content)
}

Qwen3 Coder 480B

package main

import (
    "context"
    "fmt"
    "log"
    "os"

    "github.com/openai/openai-go/v2"
    "github.com/openai/openai-go/v2/option"
    "github.com/tinfoilsh/tinfoil-go"
)

func main() {
    // Configure client for Qwen3 Coder 480B
    client, err := tinfoil.NewClient(
        option.WithAPIKey(os.Getenv("TINFOIL_API_KEY")),
    )
    if err != nil {
        log.Fatal(err)
    }

    // Example: Repository-scale code understanding and agentic coding
    chatCompletion, err := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
        Messages: []openai.ChatCompletionMessageParamUnion{
            openai.UserMessage("Review this codebase and suggest architectural improvements for better modularity and testability."),
        },
        Model: "qwen3-coder-480b",
    })

    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(chatCompletion.Choices[0].Message.Content)
}

Qwen 2.5 72B

package main

import (
    "context"
    "fmt"
    "log"
    "os"

    "github.com/openai/openai-go/v2"
    "github.com/openai/openai-go/v2/option"
    "github.com/tinfoilsh/tinfoil-go"
)

func main() {
    // Configure client for Qwen 2.5 72B
    client, err := tinfoil.NewClient(
        option.WithAPIKey(os.Getenv("TINFOIL_API_KEY")),
    )
    if err != nil {
        log.Fatal(err)
    }

    // Example: Code generation and analysis
    chatCompletion, err := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
        Messages: []openai.ChatCompletionMessageParamUnion{
            openai.UserMessage("Write a Go function to calculate the Fibonacci sequence up to n terms, then explain how it works."),
        },
        Model: "qwen2-5-72b",
    })

    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(chatCompletion.Choices[0].Message.Content)
}

Audio Models

Whisper Large V3 Turbo

package main

import (
    "context"
    "fmt"
    "log"
    "os"

    "github.com/openai/openai-go/v2"
    "github.com/openai/openai-go/v2/option"
    "github.com/tinfoilsh/tinfoil-go"
)

func main() {
    // Configure client for Whisper Large V3 Turbo
    client, err := tinfoil.NewClient(
        option.WithAPIKey(os.Getenv("TINFOIL_API_KEY")),
    )
    if err != nil {
        log.Fatal(err)
    }

    // Example: Audio transcription
    audioFile, err := os.Open("meeting_recording.mp3")
    if err != nil {
        log.Fatal(err)
    }
    defer audioFile.Close()

    transcription, err := client.Audio.Transcriptions.New(context.TODO(), openai.AudioTranscriptionNewParams{
        Model:    "whisper-large-v3-turbo",
        File:     openai.File(audioFile, "meeting_recording.mp3", "audio/mpeg"),
        Language: openai.String("en"), // Optional: specify language for better accuracy
        Prompt:   openai.String("This is a business meeting discussing quarterly results"), // Optional: provide context
    })
    if err != nil {
        log.Fatal(err)
    }

    fmt.Println("Transcription:", transcription.Text)
}

Kokoro

package main

import (
    "context"
    "fmt"
    "io"
    "log"
    "os"

    "github.com/openai/openai-go/v2"
    "github.com/openai/openai-go/v2/option"
    "github.com/tinfoilsh/tinfoil-go"
)

func main() {
    // Configure client for Kokoro TTS
    client, err := tinfoil.NewClient(
        option.WithAPIKey(os.Getenv("TINFOIL_API_KEY")),
    )
    if err != nil {
        log.Fatalf("Error creating client: %v", err)
    }

    textToSpeak := "Welcome to Tinfoil's secure AI platform. Your data remains private and protected."

    // Example: Text-to-speech with different voices
    // Single voice
    response1, err := client.Audio.Speech.New(
        context.Background(),
        openai.AudioSpeechNewParams{
            Model:          "kokoro",
            Voice:          "af_sky",
            Input:          textToSpeak,
            ResponseFormat: openai.AudioSpeechNewParamsResponseFormatMp3,
        },
    )
    if err != nil {
        log.Fatalf("Error creating speech: %v", err)
    }
    defer response1.Body.Close()

    out1, err := os.Create("speech_single.mp3")
    if err != nil {
        log.Fatalf("Error creating output file: %v", err)
    }
    defer out1.Close()

    _, err = io.Copy(out1, response1.Body)
    if err != nil {
        log.Fatalf("Error writing audio file: %v", err)
    }

    // Combined voices for richer sound
    response2, err := client.Audio.Speech.New(
        context.Background(),
        openai.AudioSpeechNewParams{
            Model:          "kokoro",
            Voice:          "af_sky+af_bella",
            Input:          textToSpeak,
            ResponseFormat: openai.AudioSpeechNewParamsResponseFormatMp3,
        },
    )
    if err != nil {
        log.Fatalf("Error creating speech: %v", err)
    }
    defer response2.Body.Close()

    out2, err := os.Create("speech_combined.mp3")
    if err != nil {
        log.Fatalf("Error creating output file: %v", err)
    }
    defer out2.Close()

    _, err = io.Copy(out2, response2.Body)
    if err != nil {
        log.Fatalf("Error writing audio file: %v", err)
    }

    fmt.Println("Speech files generated successfully!")
}

Embedding Models

Nomic Embed Text

package main

import (
    "context"
    "fmt"
    "log"
    "math"
    "os"

    "github.com/openai/openai-go/v2"
    "github.com/openai/openai-go/v2/option"
    "github.com/tinfoilsh/tinfoil-go"
)

func main() {
    // Configure client for Nomic Embed Text
    client, err := tinfoil.NewClient(
        option.WithAPIKey(os.Getenv("TINFOIL_API_KEY")),
    )
    if err != nil {
        log.Fatal(err)
    }

    // Example: Generate embeddings for similarity search
    documents := []string{
        "Artificial intelligence is transforming modern technology.",
        "Machine learning enables computers to learn from data.",
        "The weather today is sunny and warm.",
        "Deep learning uses neural networks with multiple layers.",
    }

    // Generate embeddings for all documents
    var embeddings [][]float64
    for _, doc := range documents {
        response, err := client.Embeddings.New(context.TODO(), openai.EmbeddingNewParams{
            Model: "nomic-embed-text",
            Input: openai.EmbeddingNewParamsInputArrayString([]string{doc}),
        })
        if err != nil {
            log.Fatal(err)
        }
        embeddings = append(embeddings, response.Data[0].Embedding)
    }

    // Calculate similarity between first two documents
    similarity := cosineSimilarity(embeddings[0], embeddings[1])

    fmt.Printf("Similarity between first two AI-related documents: %.3f\n", similarity)
    fmt.Printf("Embedding dimension: %d\n", len(embeddings[0]))
}

func cosineSimilarity(a, b []float64) float64 {
    dotProduct := 0.0
    normA := 0.0
    normB := 0.0

    for i := 0; i < len(a); i++ {
        dotProduct += a[i] * b[i]
        normA += a[i] * a[i]
        normB += b[i] * b[i]
    }

    return dotProduct / (math.Sqrt(normA) * math.Sqrt(normB))
}

Advanced Functionality

For advanced use cases requiring manual verification or direct HTTP access, use the SecureClient from the verifier package:

import (
	"fmt"
	"github.com/tinfoilsh/tinfoil-go"
	"github.com/tinfoilsh/verifier/client"
)

// Create a secure client for manual verification and HTTP access
secureClient := client.NewSecureClient(
	"inference.tinfoil.sh",
	"tinfoilsh/confidential-inference-proxy",
)

// Verify the enclave attestation
groundTruth, err := secureClient.Verify()
if err != nil {
	return fmt.Errorf("verification failed: %w", err)
}

// Get the verified HTTP client for custom requests
httpClient, err := secureClient.HTTPClient()
if err != nil {
	return fmt.Errorf("failed to get HTTP client: %w", err)
}

// Access enclave and repository information
fmt.Printf("Enclave: %s\n", secureClient.Enclave())
fmt.Printf("Repository: %s\n", secureClient.Repo())

API Documentation

This library is a drop-in replacement for the official OpenAI Go client that can be used with Tinfoil. All methods and types are identical. See the OpenAI Go client documentation for complete API usage and documentation.

Guides

Tool Calling

Learn how to use function calling capabilities with AI models.

Structured Outputs

Use JSON schema validation for reliable data extraction.

Image Processing

Process images with multimodal AI models.

Document Processing

Upload and process documents securely.

Getting Started

Models

SDKs

Guides

Privacy Verification

Tutorials

Admin API

Confidential Computing

Resources

Go

Go SDK

Overview

Installation

Migration from OpenAI

Usage

Model Examples

Chat Models

Audio Models

Embedding Models

Advanced Functionality

API Documentation

Guides

Tool Calling

Structured Outputs

Image Processing

Document Processing

Getting Started

Models

SDKs

Guides

Privacy Verification

Tutorials

Admin API

Confidential Computing

Resources

Go SDK

​Overview

​Installation

​Migration from OpenAI

​Usage

​Model Examples

​Chat Models

​Audio Models

​Embedding Models

​Advanced Functionality

​API Documentation

​Guides

Tool Calling

Structured Outputs

Image Processing

Document Processing

Overview

Installation

Migration from OpenAI

Usage

Model Examples

Chat Models

Audio Models

Embedding Models

Advanced Functionality

API Documentation

Guides