# Muse Spark Open API Pricing

As of October 21, 2026, Muse Spark Open costs $1.25 per 1M input tokens and $4.25 per 1M output tokens from Baseten, the lowest of 2 providers, with cache reads at $0.15 per 1M tokens. It has a 1,048,576-token context window and returns up to 1,048,576 tokens per response.

- Page: https://models.litellm.ai/models/muse-spark-open
- Lab: Meta
- LiteLLM model name: `baseten/meta-models/muse-spark-open`
- Context window: 1,048,576 tokens
- Max output: 1,048,576 tokens
- Added to LiteLLM: October 15, 2026
- Prices updated: October 21, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Baseten | `baseten/meta-models/muse-spark-open` | $1.25 | $4.25 | $0.15 | – | – | 1M |
| Fireworks AI | `fireworks_ai/accounts/fireworks/models/muse-spark-open` | $1.25 | $4.25 | $0.15 | – | – | 1M |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Baseten: $4.625
- Fireworks AI: $4.625

100 long-document requests with 100,000 input and 2,000 output tokens each:

- Baseten: $13.35
- Fireworks AI: $13.35

## Features

Supported: Function calling, Image input, Audio input, Reasoning, Prompt caching.
Not supported: Structured output.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="baseten/meta-models/muse-spark-open",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## Cost calculator

10,000 requests a day with 1,000 input and 500 output tokens each, at Baseten's price: $0.003375 per request, $33.75 per day, $1,013 per month (30 days). Try other numbers at https://models.litellm.ai/calculator?model=muse-spark-open

## FAQ

### How much does Muse Spark Open cost?

Muse Spark Open costs $1.25 per 1M input tokens and $4.25 per 1M output tokens from Baseten, the lowest of 2 providers, with cache reads at $0.15 per 1M tokens.

### What is the context window of Muse Spark Open?

Muse Spark Open has a 1,048,576-token context window and returns up to 1,048,576 tokens per response.

### Which providers offer Muse Spark Open?

Muse Spark Open is available from 2 providers through LiteLLM: Baseten and Fireworks AI.

### How do I call Muse Spark Open with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="baseten/meta-models/muse-spark-open", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does Muse Spark Open support?

Muse Spark Open supports function calling, image input, audio input, reasoning and prompt caching. It does not support structured output.

### When did LiteLLM add Muse Spark Open?

Muse Spark Open was added to LiteLLM's model price file on October 15, 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change.