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

> ## Agent Instructions
> The Venice API is OpenAI-compatible: use any OpenAI SDK with the base URL `https://api.venice.ai/api/v1` and a Venice API key, or pay per request from a USDC wallet through x402 with no account.
> Read model IDs from `GET /models` or `GET /models/traits` at runtime instead of hardcoding them from memory or from these pages. Models are added and retired often.
> Every model's price is in https://docs.venice.ai/pricing.md. Quote video and audio jobs with `POST /video/quote` or `POST /audio/quote` before you queue them.
> Search these docs from an MCP client at https://docs.venice.ai/mcp. The full agent guide is https://docs.venice.ai/agents.md.

# Muse Spark Open API

> Muse Spark Open API on Venice: 1M context, $1.56 input and $5.31 output per 1M tokens. Private, with zero data retention. Pricing, specs and code examples.



## Muse Spark Open API

Muse Spark Open is a large language model by Meta, available on the Venice API as `muse-spark-open`. This model is private and no prompt data is stored in any capacity.

Muse Spark Open is an open-weight reasoning model from Meta for coding and agentic workflows. It supports tool calling and native image understanding in a single checkpoint, using a sparse Mixture-of-Experts architecture with 816B total / 42B active parameters and a 1M-token context window.

### Muse Spark Open API pricing

| Model ID | Variant | Privacy | Price |
| - | - | - | - |
| `muse-spark-open` | Standard | Private | $1.56 / $5.31 per 1M |

### Muse Spark Open specifications

| Spec | Value |
| - | - |
| Provider | Meta |
| Released | Oct 15, 2026 |
| Privacy | Private |
| Status | Stable |
| Open weights | [meta-models/Muse-Spark-Open-816B-A42B](https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B) |
| Context window | 1M tokens |
| Max output | 128K tokens |
| Reasoning effort | low, medium, high, xhigh |
| [GPQA Diamond](https://docs.venice.ai/models/methodology.md#benchmarks) | 71.7% ±6.3 (95% interval), run by Venice through the API at its default reasoning on Oct 22, 2026 |

### How to use the Muse Spark Open API

Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "muse-spark-open"` and your API key.

```bash theme={"system"}
curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "muse-spark-open",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
    "reasoning_effort": "xhigh"
  }'
```

### Related models

* [DeepSeek V4.1 Flash 1017 Ultrafast API](https://docs.venice.ai/models/deepseek-v4-1-flash-1017-ultrafast.md): $1.50 / $6.00 per 1M
* [DeepSeek V4 Pro 0813 API](https://docs.venice.ai/models/deepseek-v4-pro-0813.md): $1.65 / $4.95 per 1M
* [GLM 5.3 E2EE API](https://docs.venice.ai/models/glm-5-3-e2ee.md): $1.75 / $5.50 per 1M
* [Qwen 4 Max API](https://docs.venice.ai/models/qwen-4-max.md): $1.50 / $4.50 per 1M


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