Muse Spark 1.2 | EmpirioLabs AI Docs

Meta AI · Text Generation

POST /v1/chat/completions

Meta’s updated frontier reasoning model with a 1,048,576-token context, image, video, audio, and PDF understanding, web search, and tool calling.

At a glance

Field	Value
Model id	`muse-spark-1-2`
Model release date	2026-08-05
Input modalities	Text, Image, Video, Audio, Document
Output modalities	Text
Context window	1M
Weight precision	-
Max output tokens	131,072
Features	reasoning, multimodal, video_understanding, function_calling, structured_output, web_search, cache, audio_input, document_understanding
Native inference	No
New	Yes
Structured output	JSON Schema
Supported endpoints	`POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/muse-spark-1-2:generateContent`
Alternate model ids	`muse-spark-1.2`, `meta/muse-spark-1-2`, `meta/muse-spark-1.2`

Pricing

Charge	Spec	Rate
Input	per 1M prompt tokens	$1.25
Output	per 1M generated tokens	$4.25
Implicit cache read	per 1M cached input tokens	$1.00
Web search	per search query	$0.00825

Example request

$ curl https://api.empiriolabs.ai/v1/chat/completions \
>   -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>   -H 'Content-Type: application/json' \
>   -d '{"model": "muse-spark-1-2", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

Parameter	Type	Required	Default	Description
`max_tokens`	integer	no	`16384`	Maximum number of output tokens to generate. Reasoning tokens count against this budget. · Range: 1 – 131072
`temperature`	number	no	`1`	Controls randomness. Lower values make responses more deterministic. · Range: 0 – 2
`top_p`	number	no	`1`	Nucleus sampling cutoff. · Range: 0.01 – 1
`presence_penalty`	number	no	`0`	Penalizes tokens that already appeared, encouraging new topics. · Range: -2 – 2
`frequency_penalty`	number	no	`0`	Penalizes frequent tokens, reducing repetition. · Range: -2 – 2
`seed`	integer	no	-	Random seed for more reproducible sampling.
`reasoning_effort`	enum	no	`"medium"`	Reasoning is always on; this sets how much effort the model spends before answering. Higher effort uses more reasoning tokens. Reasoning text is not returned in responses. · Allowed: `minimal`, `low`, `medium`, `high`, `xhigh`
`tool_web_search`	boolean	no	false	Enable built-in web search with cited sources. Adds $0.00825 per executed search query; a single request can run more than one search.
`tools`	array	no	`[]`	OpenAI-compatible function and custom tool definitions. On /v1/responses, tool_search and defer_loading can discover deferred tools.
`tool_choice`	object	no	-	OpenAI-compatible tool choice control. This model supports auto and none.
`parallel_tool_calls`	boolean	no	true	Allow the model to request multiple function tools in one response.
`response_format`	enum	no	-	Return structured JSON output. JSON mode returns any valid JSON object; JSON Schema mode enforces an exact schema.

Notes

Reasoning is always on and cannot be disabled. Reasoning stays internal, and reasoning tokens are billed as output tokens and count against max_tokens. reasoning_effort accepts minimal through xhigh. Text, image, MP4 video, MP3/WAV audio, and PDF inputs are supported; up to 50 images can be attached. PDFs use text from the first 100 pages and page images from the first 50 pages. Built-in web search adds $0.00825 per executed search query and reports the count in usage.tool_usage. OpenAI Responses requests also support custom tools and deferred tool search. tool_choice supports auto and none. Prompts and completions sent to this Standard checkpoint are not used by Meta to train its models.

Per-tool billing (usage.tool_usage)

When this model invokes tools inside a single request, the response carries a normalized usage.tool_usage map alongside the token counts. The example below shows the shape. Exact field names, units, and which tools appear can vary by tool:

1 "usage": {
2   "prompt_tokens": 123,
3   "completion_tokens": 456,
4   "cost_usd": 0.0042,
5   "tool_usage": {"web_search": 3}
6 }

The tool counts are already factored into cost_usd and are surfaced so you can audit per-tool billing. The field is omitted when no billed tool was invoked.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/muse-spark-1-2.