# Muse: Spark Open 816B a42b:baseten API

Meta's Muse: Spark Open 816B a42b:baseten, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send muse-spark-open-816b-a42b:baseten as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

## Facts

- Model name: muse-spark-open-816b-a42b:baseten
- Maker: Meta
- Context window: 1M tokens
- Input price: $1.251 per million tokens
- Output price: $4.252 per million tokens
- Providers: 1 independent provider
- Regions: us

## Providers

- [Architect](https://liquidinference.ai/providers/805445a7-0e40-4c1b-9baf-7b3b01e30e42.md): us, $1.251 input and $4.252 output per million tokens, $1.251 cache read per million tokens, 1M tokens of context

## Request

```sh
curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "muse-spark-open-816b-a42b:baseten",
    "messages": [{"role":"user","content":"Say hello."}]
  }'
```

## Questions

### What is Muse: Spark Open 816B a42b:baseten?

Muse: Spark Open 816B a42b:baseten is a model from Meta.

### How much does Muse: Spark Open 816B a42b:baseten cost?

Offers now ask $1.251 per million input tokens and $4.252 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.

### What is the context length of Muse: Spark Open 816B a42b:baseten?

The largest offer takes 1,048,576 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.

### What can Muse: Spark Open 816B a42b:baseten do?

Its providers list Vision, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.

### What inputs and outputs does Muse: Spark Open 816B a42b:baseten support?

Text · Images → Text.

### Which providers serve Muse: Spark Open 816B a42b:baseten?

1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.

### How do I call Muse: Spark Open 816B a42b:baseten?

Send "muse-spark-open-816b-a42b:baseten" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.

### When was Muse: Spark Open 816B a42b:baseten listed?

The exchange first listed it on 10/15/2026. This is not its release date.

## Related pages

- [This page in a browser](https://liquidinference.ai/models/muse-spark-open-816b-a42b%3Abaseten)
- [Llama 3.2 3B Instruct](https://liquidinference.ai/models/llama-3.2-3b-instruct.md)
- [Llama 3.1 8B Instruct](https://liquidinference.ai/models/llama-3.1-8b-instruct.md)
- [Meta: Llama 3.1 8B Instruct FP8](https://liquidinference.ai/models/meta-llama-3.1-8b-instruct-fp8.md)
- [Llama: Guard 3 8B](https://liquidinference.ai/models/llama-guard-3-8b.md)
- [Llama 3 8B Instruct](https://liquidinference.ai/models/llama3-8b-instruct.md)
- [Llama: Guard 4 12B](https://liquidinference.ai/models/llama-guard-4-12b.md)
- [Set up a client](https://liquidinference.ai/connect/muse-spark-open-816b-a42b%3Abaseten)
- [All models](https://liquidinference.ai/models)
- [Providers](https://liquidinference.ai/providers.md)
- [Discover the best model for your budget](https://liquidinference.ai/discover)
- [Quickstart](https://liquidinference.ai/docs/quickstart.md)
- [llms.txt: the index of every page, as Markdown](https://liquidinference.ai/llms.txt)
- [llms-full.txt: every page in one file](https://liquidinference.ai/llms-full.txt)