Text Generation

Use these models to generate text, whether it's to review code, write a story, etc.

Available Models on Sentry Block

Sentry Block currently supports a wide range of cutting-edge generative AI models through our Serverless Endpoints. These models are pre-configured and ready for immediate use in your applications.

---

Available Text Models

• DeepSeek-R1-Distill-Llama-70B – High-quality text generation for complex queries.

• DeepSeek-R1-Distill-Qwen-32B – Efficient text generation with lower resource consumption.

• Llama3.3-70B – Advanced conversational AI with expansive knowledge.

• Llama3.1-8B – Lightweight, general-purpose model ideal for low-cost tasks.

• Qwen2.5-Coder-32B – Specialized in code generation, completions, and developer tools.

---

Using the Models

1. Visit the Sentry Block platform.

2. Log into your account and ensure you have sufficient credit.

3. Go to the "Serverless Endpoints" tab.

4. Choose a model and configure your parameters.

5. Enter your prompt (text or image, if applicable) and hit Enter.

---

Adjustable Parameters

• Messages – The dialogue history between the user and the assistant.

• System Prompt – Contextual instructions guiding the model's behavior.

• Output Length – Max number of tokens the model will generate.

• Temperature – Controls creativity (higher = more varied responses).

• Top P – Controls probability sampling for more or less diverse outputs.

• Stream – Toggle between streaming responses or receiving a full response at once.

---

API Integration

You can also use the models via Sentry Block’s API endpoints to integrate AI directly into your applications. Don’t forget to include your API key. See our [API Reference] for details on authentication.

Using cURL

bashCopyEditcurl -X POST "https://inference.sentryblock.com/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $SENTRY_API_KEY" \
--data-raw '{
    "messages": [
        {"role": "user", "content": "Is Montreal a thriving hub for the AI industry?"}
    ],
    "model": "meta-llama/Llama-3.1-8B-Instruct",
    "max_tokens": null,
    "temperature": 1,
    "top_p": 0.9,
    "stream": false
}'

Using Python

pythonCopyEditimport requests
import os

url = "https://inference.sentryblock.com/v1/chat/completions"
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.environ.get('SENTRY_API_KEY')}"
}
data = {
    "messages": [
        {"role": "user", "content": "Is Montreal a thriving hub for the AI industry?"}
    ],
    "model": "meta-llama/Llama-3.1-8B-Instruct",
    "max_tokens": None,
    "temperature": 1,
    "top_p": 0.9,
    "stream": False
}
response = requests.post(url, headers=headers, json=data)
print(response.json())

Using JavaScript

javascriptCopyEditconst url = "https://inference.sentryblock.com/v1/chat/completions";

const headers = {
  "Content-Type": "application/json",
  "Authorization": `Bearer ${process.env.SENTRY_API_KEY}`
};

const data = {
  messages: [
    { role: "user", content: "Is Montreal a thriving hub for the AI industry?" }
  ],
  model: "meta-llama/Llama-3.1-8B-Instruct",
  max_tokens: null,
  temperature: 1,
  top_p: 0.9,
  stream: false
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
  .then(response => response.json())
  .then(data => {
    console.log(JSON.stringify(data, null, 2));
  })
  .catch(error => console.error('Error:', error));

---

Model Name Mappings

Use these identifiers in the model field of your API request:

• deepseek-ai/DeepSeek-R1-Distill-Llama-70B

• deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

• meta-llama/Llama-3.3-70B-Instruct

• meta-llama/Llama-3.1-8B-Instruct

• Qwen/Qwen2.5-Coder-32B-Instruct

---

Example Response (Non-Streaming)

jsonCopyEdit{
  "id": "chatcmpl-ec0014bc38e2cad1e45d47f7f01f6569",
  "created": 1740432179,
  "model": "meta-llama/Llama-3.1-8B-Instruct",
  "object": "chat.completion",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Yes! Montreal is the home of cutting edge ... research.",
        "role": "assistant"
      }
    }
  ],
  "usage": {
    "completion_tokens": 695,
    "prompt_tokens": 42,
    "total_tokens": 737
  }
}

---

Example Response (Streaming Enabled)

jsonCopyEdit{
  "id": "chatcmpl-289eb1f670a58c5cde47ddb634aad595",
  "created": 1740432271,
  "model": "meta-llama/Llama-3.1-8B-Instruct",
  "object": "chat.completion.chunk",
  "choices": [
    {
      "index": 0,
      "delta": {
        "content": " everyone"
      }
    }
  ]
}

Each chunk of streamed data adds to the full response. This is useful for real-time applications or chat-like experiences.