LiteLLMModels

Muse Spark 1.2 API Pricing

As of October 10, 2026, Muse Spark 1.2 costs $1.25 per 1M input tokens and $4.25 per 1M output tokens from Meta Model API, 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 131,072 tokens per response.

Model ID meta/muse-spark-1.2Prices updated Checked
Input
$1.25 / 1M tokens
Output
$4.25 / 1M tokens
Cache read
$0.15 / 1M tokens
Context window
1,048,576 tokens
Max output
131,072 tokens
Providers
2
Added to LiteLLM
August 13, 2026

Muse Spark 1.2 pricing by provider

2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readContext
Meta Model APImeta/muse-spark-1.2$1.25$4.25$0.151M
AIHubMixaihubmix/muse-spark-1.2$1.375$4.675–1M

Other Muse Spark 1.2 prices on Meta Model API

Web search$2.50 per 1K searches

What Muse Spark 1.2 costs in practice

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

Meta Model API$4.625
AIHubMix$5.088

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

Meta Model API$13.35
AIHubMix$14.69

Muse Spark 1.2 features

Input: text, image, video. Output: text.

Use Muse Spark 1.2 with LiteLLM

Call Muse Spark 1.2 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="meta/muse-spark-1.2",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: muse-spark-1.2
    litellm_params:
      model: meta/muse-spark-1.2
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "muse-spark-1.2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Muse Spark 1.2 FAQ

How much does Muse Spark 1.2 cost?

Muse Spark 1.2 costs $1.25 per 1M input tokens and $4.25 per 1M output tokens from Meta Model API, the lowest of 2 providers, with cache reads at $0.15 per 1M tokens.

What is the context window of Muse Spark 1.2?

Muse Spark 1.2 has a 1,048,576-token context window and returns up to 131,072 tokens per response.

Which providers offer Muse Spark 1.2?

Muse Spark 1.2 is available from 2 providers through LiteLLM: Meta Model API and AIHubMix. The lowest price is on Meta Model API.

How do I call Muse Spark 1.2 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="meta/muse-spark-1.2", 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 1.2 support?

Muse Spark 1.2 supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching and web search.

When did LiteLLM add Muse Spark 1.2?

Muse Spark 1.2 was added to LiteLLM's model price file on August 13, 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Meta Model API, AIHubMix.

Provider pages: Meta Model API, AIHubMix.