# Muse Spark 1.3 Contributor - Core.Today AI API

> The discounted Contributor tier of Meta's Muse Spark 1.3 - same model, about 1/12 of the standard price, on the condition that prompts and responses may be used by Meta to train its models. Do not send personal, confidential or customer data. Shares an upstream limit of 100 requests / 3M tokens per minute.

- **Provider**: Meta
- **Model ID**: muse-spark-1.3-contributor
- **Category**: LLM
- **Credits**: 0.3 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**: 185.8 credits ($0.12)
- **Output Tokens**: 371.6 credits ($0.25)
- **Cached Tokens**: 3.716 credits ($0.00)

## Features
- Same Muse Spark 1.3 model at about 1/12 of the standard price
- Prompts and responses may be used for Meta training (the discount condition)
- 1M-token context, multimodal input (text, image, video, audio, PDF)
- Shared upstream limit: 100 RPM / 3M TPM
- OpenAI-compatible API via /llm/meta/v1

## Use Cases
- Bulk processing of public or synthetic data where cost matters most
- Evaluation and prompt iteration with non-sensitive inputs
- Internal tooling over open documents

## 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. Content may be used by Meta for training - no personal or confidential data.

### 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

### Low-cost batch summarization
Summarize a public article - content may be used for Meta training.
```json
{
  "model": "muse-spark-1.3-contributor",
  "messages": [
    {
      "role": "user",
      "content": "Summarize this public press release in 3 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
- Only send data you are allowed to share for training; otherwise use muse-spark-1.3
- Keep max_tokens >= 2048: reasoning tokens come first and are billed at the output rate
- The 100 RPM / 3M TPM upstream limit is shared across all callers - expect provider_rate_limited under load
- Works with the OpenAI SDK - set base_url to https://api.core.today/llm/meta/v1

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