# Muse Spark 1.3 - Core.Today AI API

> Meta's Muse Spark 1.3 over the direct Meta API - a multimodal reasoning model for agentic work that accepts text, images, video, audio and PDF documents and returns text, with a 1M-token context window and cached-input pricing. Answers are generated after reasoning tokens, so keep max_tokens at 2,048 or more.

- **Provider**: Meta
- **Model ID**: muse-spark-1.3
- **Category**: LLM
- **Credits**: 5 per 1K tokens (avg)
- **Speed**: Medium
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 1.0M tokens
- **Max Output**: 33K tokens
- **Training Cutoff**: Not published
- **Supported Formats**: text, json, markdown
- **Compatible SDK**: OpenAI

### Capabilities
- Vision (image input)
- Function Calling
- Streaming
- JSON Mode
- System Prompt

### Token Pricing (per 1M tokens)
- **Input Tokens**: 2,322.5 credits ($1.55)
- **Output Tokens**: 7,896.5 credits ($5.26)
- **Cached Tokens**: 278.7 credits ($0.19)

## Features
- 1M-token context window
- Multimodal input - text, image, video, audio, PDF
- Reasoning model built for agentic tasks
- Cached input pricing (~88% discount)
- OpenAI-compatible API (chat completions) via /llm/meta/v1
- Billed exactly at the listed rates (direct route, not an aggregator)

## Use Cases
- Agentic workflows over mixed media (documents, screenshots, recordings)
- Video and audio understanding with text answers
- Long-context reasoning across large PDF collections

## API Endpoint

Base URL: https://api.core.today
Endpoint: POST /llm/meta/v1/chat/completions

## Authentication
Header: Authorization: Bearer YOUR_API_KEY

Note: LLM endpoints use OpenAI-compatible format with Authorization Bearer token.

## Input Parameters

### Required
- **messages**: array - Chat messages in OpenAI format (system/user/assistant roles).

### Optional
- **max_tokens**: integer (default: 2048) - Maximum completion tokens including reasoning. Keep >= 2048 or the answer may be cut off before any content is produced.
- **temperature**: number (default: 0.7) - Sampling temperature (0-2).
- **stream**: boolean (default: false) - Stream the response as server-sent events.

## Examples

### Chat completion
OpenAI-compatible chat completion over the direct Meta route
```json
{
  "model": "muse-spark-1.3",
  "messages": [
    {
      "role": "user",
      "content": "Summarize the attached report in 5 bullets."
    }
  ],
  "max_tokens": 4096
}
```

## Response Format
```json
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Response text here"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 100,
    "completion_tokens": 50,
    "total_tokens": 150
  }
}
```

## Tips
- Works with the OpenAI SDK - set base_url to https://api.core.today/llm/meta/v1
- Keep max_tokens >= 2048: reasoning tokens come first and are billed at the output rate
- For discounted pricing where prompts may be used for Meta training, see muse-spark-1.3-contributor
- Repeated system prompts and documents benefit from the cached-input rate

## Documentation
https://dev.meta.ai/docs/models