> ## Documentation Index
> Fetch the complete documentation index at: https://docs.asgcompute.com/llms.txt
> Use this file to discover all available pages before exploring further.

# ASG Inference

> AI completions with 100+ models

# ASG Inference

Access state-of-the-art AI models with per-token pricing and instant access.

## Overview

ASG Inference provides:

* **100+ models** — GPT-5.2, Claude Sonnet 4, Gemini 2.5 Pro, DeepSeek R1 and more
* **OpenAI-compatible** — Drop-in replacement
* **Per-token billing** — Pay exactly for usage
* **Automatic fallback** — Reliability across providers

## Quick Example

<CodeGroup>
  ```bash curl theme={null}
  curl -X POST https://agent.asgcompute.com/mcp \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -d '{
      "jsonrpc": "2.0",
      "id": 1,
      "method": "tools/call",
      "params": {
        "name": "inference_chat",
        "arguments": {
          "model": "openai/gpt-4o-mini",
          "messages": [
            {"role": "user", "content": "Explain quantum computing in one sentence."}
          ]
        }
      }
    }'
  ```

  ```typescript fetch theme={null}
  const response = await fetch('https://agent.asgcompute.com/mcp', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'Authorization': 'Bearer YOUR_API_KEY',
      'X-Payment': paymentProof  // base64url-encoded payment proof
    },
    body: JSON.stringify({
      jsonrpc: '2.0',
      id: 1,
      method: 'tools/call',
      params: {
        name: 'inference_chat',
        arguments: {
          model: 'openai/gpt-4o-mini',
          messages: [
            { role: 'user', content: 'Explain quantum computing in one sentence.' }
          ]
        }
      }
    })
  });
  ```
</CodeGroup>

## Available Models

Pass the full model identifier in the `model` parameter:

| Model | Best For | Cost |
| :- | :- | :- |
| `openai/gpt-4o-mini` | Quick responses, chat | \$ |
| `openai/gpt-4.1` | General purpose | \$\$ |
| `openai/gpt-5.2` | Complex reasoning | \$\$\$ |
| `anthropic/claude-sonnet-4` | Coding, analysis | \$\$\$ |
| `google/gemini-2.5-pro` | Multimodal, long context | \$\$ |
| `deepseek/deepseek-r1` | Math, reasoning | \$\$ |

<Tip>
  Use the **Quote** response to see exact per-token pricing for any model before execution.
</Tip>

## Parameters

| Parameter | Type | Required | Description |
| :- | :- | :- | :- |
| `model` | string | Yes | Model identifier (see table above) |
| `messages` | array | Yes | Conversation messages |
| `max_tokens` | number | No | Max output tokens (default: 1024) |
| `temperature` | number | No | Randomness (0-2, default: 1) |
| `stream` | boolean | No | Enable streaming (default: false) |

## Response

```json theme={null}
{
  "result": {
    "content": "Quantum computing uses quantum bits...",
    "usage": {
      "prompt_tokens": 12,
      "completion_tokens": 45,
      "total_tokens": 57
    },
    "_meta": {
      "receipt_id": "rcpt_abc123",
      "debited_usdc_microusd": 2400
    }
  }
}
```

## Streaming

For real-time responses, set `stream: true` in arguments. Streaming responses use Server-Sent Events.

## Pricing

See [Pricing](/billing/pricing) for current rates.

<Tip>
  **Cost Optimization:** Use lightweight models like `openai/gpt-4o-mini` for simple tasks and reserve frontier models for complex reasoning.
</Tip>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.