How much does Muse Spark 1.2 cost?

Muse Spark 1.2 costs $1.25/M input tokens and $4.25/M output tokens, with separate rates for Cache Read at $0.15/M tokens and Web Search at $2.50/1K calls.

What is the context length of Muse Spark 1.2?

Muse Spark 1.2 has a 1,048,576 token context window.

Does Muse Spark 1.2 support tool calling and structured outputs?

Yes. Muse Spark 1.2 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does Muse Spark 1.2 support?

Muse Spark 1.2 accepts text, images, video, and files such as PDFs as input and returns text.

Which providers serve Muse Spark 1.2?

Muse Spark 1.2 is served by 1 provider on OpenRouter: Meta.

What other text models does Meta have?

Muse Ember, Muse Spark Open, Muse Wonder and 5 more are other text models from Meta.

When was Muse Spark 1.2 released?

Muse Spark 1.2 was released on August 5, 2026.

Meta: Muse Spark 1.2

meta/muse-spark-1.2

Compare

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window.

The model is built to support multi-agent workflows, whether as either a main agent that plans and delegates or as a subagent executing in parallel. It works across multiple coding harnesses and supports structured output, parallel function calling, and configurable reasoning effort. In Meta’s testing, it performs well on multi-file refactors, extended debugging sessions, whole-repository generation, and tasks that stretch well past a single prompt.

Modalities

In / out price

$1.25 / $4.25per 1M

Context

1.0M

Released

Aug 5, 2026

Providers

This model is hosted by one provider. OpenRouter forwards every request without routing.

Latency / throughput


	$1.25	$4.25	$0.15	3.18s	141 tok/s	100.00%

Input $1.25Output $4.25
141 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.4715/M tokens

Output

$4.25/M tokens

Muse Spark 1.2 — Price history

Price history

No effective price data for this selection

		$0.471	$4.25	70.8%	100.0%

Effective in $0.471Effective out $4.25
Token share
100.0%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.74%

Availability over the last 3 days

Last 72 hours

Availability 99.74%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.66%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Meta: Muse Spark 1.2 (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	Muse Spark 1.2 (Xhigh) Coding Index	72.2
Artificial Analysis	Muse Spark 1.2 (Xhigh) Agentic Index	43.2
Artificial Analysis	Muse Spark 1.2 (Xhigh) GPQA Diamond	90.4%
Artificial Analysis	Muse Spark 1.2 (Xhigh) HLE	45.5%
Artificial Analysis	Muse Spark 1.2 (Xhigh) AA-LCR	79.0%
Artificial Analysis	Muse Spark 1.2 (Xhigh) τ-Bench Banking	34.8%
Artificial Analysis	Muse Spark 1.2 (Xhigh) GDPval-AA	49.0%
Artificial Analysis	Muse Spark 1.2 (Xhigh) CritPt	17.7%
Artificial Analysis	Muse Spark 1.2 (Xhigh) SciCode	57.4%
Artificial Analysis	Muse Spark 1.2 (Xhigh) Terminal-Bench 4.0	7.1%
Artificial Analysis	Muse Spark 1.2 (Xhigh) Terminal-Bench 2.1	80.1%
Design Arena	Muse Spark 1.2 Agents Arena Agenticgamedev Elo	1128
Design Arena	Muse Spark 1.2 Agents Arena Androidnative Elo	1210
Design Arena	Muse Spark 1.2 Agents Arena Blender3d Elo	1053
Design Arena	Muse Spark 1.2 Agents Arena Codetovideo Elo	1087
Design Arena	Muse Spark 1.2 Agents Arena Full Stack Elo	1184
Design Arena	Muse Spark 1.2 Agents Arena Htmlslides Elo	1028
Design Arena	Muse Spark 1.2 Agents Arena Mobile Apps Elo	1173
Design Arena	Muse Spark 1.2 Agents Arena Pdf Elo	1117
Design Arena	Muse Spark 1.2 Agents Arena Python-Pptxslides Elo	1158
Design Arena	Muse Spark 1.2 Agents Arena Spreadsheet Elo	1017
Design Arena	Muse Spark 1.2 Agents Arena Webapps Elo	1202
Design Arena	Muse Spark 1.2 Models Arena 3D Elo	1283
Design Arena	Muse Spark 1.2 Models Arena Asciiart Elo	1277
Design Arena	Muse Spark 1.2 Models Arena Code Categories Elo	1306
Design Arena	Muse Spark 1.2 Models Arena Data Visualization Elo	1329
Design Arena	Muse Spark 1.2 Models Arena Game Development Elo	1294
Design Arena	Muse Spark 1.2 Models Arena SVG Elo	1272
Design Arena	Muse Spark 1.2 Models Arena UI Component Elo	1299
Design Arena	Muse Spark 1.2 Models Arena Website Elo	1309
Vals AI	Muse Spark 1.2 BioMysteryBench	64.8%
Vals AI	Muse Spark 1.2 Code Migration	30.0%
Vals AI	Muse Spark 1.2 CorpFin v2	70.9%
Vals AI	Muse Spark 1.2 CyberBench v1.1	69.5%
Vals AI	Muse Spark 1.2 EMB	57.0%
Vals AI	Muse Spark 1.2 Finance Agent (v2)	60.6%
Vals AI	Muse Spark 1.2 Financial Coaching Bench	75.7%
Vals AI	Muse Spark 1.2 Harvey's Legal Agent Benchmark v1	25.4%
Vals AI	Muse Spark 1.2 Immigration	66.5%
Vals AI	Muse Spark 1.2 IOI	21.8%
Vals AI	Muse Spark 1.2 LegalBench	85.3%
Vals AI	Muse Spark 1.2 Legal Research Bench	43.8%
Vals AI	Muse Spark 1.2 MedCode	49.3%
Vals AI	Muse Spark 1.2 MedScribe	90.1%
Vals AI	Muse Spark 1.2 MMLU Pro	88.3%
Vals AI	Muse Spark 1.2 MMMU Pro	86.1%
Vals AI	Muse Spark 1.2 MortgageTax	65.4%
Vals AI	Muse Spark 1.2 ProgramBench	0.5%
Vals AI	Muse Spark 1.2 ProofBench v1.1	43.0%
Vals AI	Muse Spark 1.2 Public Benefits Bench v1.1	68.5%
Vals AI	Muse Spark 1.2 SAGE v1	47.7%
Vals AI	Muse Spark 1.2 SkillsBench	53.0%
Vals AI	Muse Spark 1.2 SRE Bench	0.0%
Vals AI	Muse Spark 1.2 SWE-bench	86.6%
Vals AI	Muse Spark 1.2 Tax Agent Bench	32.8%
Vals AI	Muse Spark 1.2 TaxEval v2	80.4%
Vals AI	Muse Spark 1.2 Terminal-Bench 4.0	6.1%
Vals AI	Muse Spark 1.2 Vals Index	49.3%
Vals AI	Muse Spark 1.2 Vals Multimodal Index	69.8%
Vals AI	Muse Spark 1.2 Vibe Code Bench v1.1	79.1%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

nmaistro-prod-worker

new

5.64Btokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

1.78Btokens

bias_execution

new

307Mtokens

There are many coding agents, but this one is yours.

286Mtokens

StartupHub.ai

new

136Mtokens

Rest of OpenRouter

80.9M

Top 5 Apps

4.61M

Not currently available through EU in-region routing. In-region routing docs

More models from Meta

Muse Ember

Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing, extraction, and long document parsing.

Muse Ember accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.

Text1.0M context$0.10 / $0.50

Muse Spark Open

Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers actually work in.

Text1.0M context$1.25 / $4.25

Muse Wonder

Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.

The model handles long-horizon work: it plans, delegates to sub-agents, calls tools in parallel, and recovers from errors, so multi-step tasks run to completion without step-by-step direction. It can also operate browsers and desktop and mobile applications, and works across many files in existing repositories to make and verify changes. Muse Wonder carries important context across conversations and retrieves the details relevant to the task at hand. And it's trained for Active Focus, so it works toward your goal even when a task gets challenging.

In Meta's testing, it performs well on complex engineering tasks, extended agentic sessions, and multi-file refactors to tackle developers' most demanding work.

Text1.0M context$4 / $20

Muse Voice Transcribe 1.0

Muse Voice Transcribe 1.0 is a synchronous speech-to-text model from Meta. It is suited for push-to-talk, endpointing, and speaker-aware transcription, with keyword biasing for domain terms and language biasing through language-name hints. It accepts mono 16-bit PCM WAV audio at 16 kHz or 24 kHz for recordings up to 10 minutes. It does not provide word-level timestamps or confidence scores, and other audio formats must be converted to WAV before upload.

Transcription$0.00005/second

Muse Spark 1.3 Contributor

Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information across extended tasks, work through conflicting inputs, and request clarification or confirmation when needed. Prompts and outputs may be used to improve Meta’s products.

Text1.0M context$0.10 / $0.20

Muse Spark 1.3

Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through conflicting inputs, and request clarification or confirmation when needed, with an emphasis on concise execution.

Text1.0M context$1.25 / $4.25

Muse Image

Muse Image is an agentic image generation model from Meta that generates and edits images from text and reference images. Unlike single-pass image models, it reasons before it renders, breaking down multi-part prompts and refining its output within the chain of thought, and invokes web search for factual accuracy on knowledge-intensive prompts.

The model supports text-to-image generation, targeted image editing, multi-image composition, reference-image conditioning for style and subject consistency across a series, and precise text rendering within generated images. Iterative editing works by passing the previous output image back with a new instruction.

Image$0.01/image

Muse Spark 1.2 Contributor

Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark 1.2. Your prompts and outputs may be used to improve Meta’s products, making it ideal for experimentation, learning, and early-stage projects without worry about spend.

It is a reasoning model from Meta, tailored for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window. The model is built to support multi-agent workflows, whether as either a main agent that plans and delegates or as a subagent executing in parallel. It works across multiple coding harnesses and supports structured output, parallel function calling, and configurable reasoning effort. In Meta’s testing, it performs well on multi-file refactors, extended debugging sessions, whole-repository generation, and tasks that stretch well past a single prompt.

Text1.0M context$0.10 / $0.20

Muse Glimmer 30B

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon agentic and coding workflows, with multi-step reasoning, reliable tool use, failure recovery, image understanding, and multilingual support across more than 100 languages.

Text131K context$0.30 / $1.20

Muse Glimmer 30B (batch)

Text131K context$0.24 / $0.96

Muse Spark 1.1

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window.

The model is designed to orchestrate multi-agent workflows, acting as either a main agent that plans and delegates or as a subagent, and generalizes zero-shot to new tools, MCP servers, and custom skills. It supports structured output, parallel function calling, built-in search with citations, and configurable reasoning effort. Meta reports strong performance on real-world coding across large codebases, computer-use workflows, and visual-to-code generation.

Text1.0M context$1.25 / $4.25

Meta: Muse Spark 1.2

Providers