Muse Spark 1.2
Muse Spark 1.2 is Meta's coding-focused reasoning model for complex agentic tasks, reading text, images, video, audio, and PDFs across a context window of 1.0M tokens.
View API reference- Input and output price
- Input $1.25, Output $4.25, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'meta/muse-spark-1.2', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Muse Spark 1.2 by Meta. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Muse Spark 1.2
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Muse Spark 1.2 through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'meta/muse-spark-1.2', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Muse Spark 1.2 request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'meta/muse-spark-1.2', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. meta/muse-spark-1.2. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Muse Spark 1.2 supports up to 1,048,576 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 1M-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
| — | URL, base64, Uint8Array | — | — | Sent as file parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'meta/muse-spark-1.2', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['meta'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'meta/muse-spark-1.2', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'meta/muse-spark-1.2', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);PDF input
Attach PDFs as file parts. Their contents count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'meta/muse-spark-1.2', messages: [ { role: 'user', content: [ { type: 'text', text: 'Summarize this document.' }, { type: 'file', mediaType: 'application/pdf', data: 'https://example.com/document.pdf', }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'meta/muse-spark-1.2', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingAbout Muse Spark 1.2
Muse Spark 1.2 is Meta's reasoning model for complex agentic tasks, and the coding-focused successor to Muse Spark 1.1. It accepts text, images, video, audio, and PDF documents, returns text, and works within a context window of 1.0M tokens.
Multi-agent work is the design centre. Muse Spark 1.2 runs either as a main agent that plans and delegates, or as a subagent executing in parallel, and it was built around harness patterns like context compaction, whole-repository work, and long-running tasks. That shows up as durability across long sessions rather than as a single benchmark number.
Support covers structured output, parallel function calling, and configurable reasoning effort, and the model works across multiple coding harnesses rather than assuming one.
A second slug, muse-spark-1.2-contributor, serves these same weights at a much lower rate in exchange for Meta training on your inputs and outputs. Choose between them on data governance first and price second. See the comparison on that model's page.
You can integrate Muse Spark 1.2 through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: The cheaper
muse-spark-1.2-contributorslug is not a different model. It is the same weights on a data-sharing arrangement, so if cost is pushing you toward it, read what that arrangement covers before switching. - Configuration: A context window of 1.0M tokens invites large prompts, and cost follows what you actually send. In an agent loop most input becomes cache reads, so measure your cached-versus-fresh ratio against the pricing panel on this page rather than sizing from the headline input rate.
- Configuration: Muse Spark 1.2 is built for multi-step agentic work. On single-turn questions or short completions, a smaller model in the family will usually be the better economic fit.
- Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Muse Spark 1.2
Best for
- Multi-Agent Workflows: Planning main agent or parallel subagent roles
- Whole-Repository Work: Long sessions with context compaction as a design target
- Multimodal Engineering Input: Text, images, video, audio, and PDFs
- Parallel Function Calling: Multiple tools within one reasoning pass
- Harness Portability: Not tied to a single coding harness
Consider alternatives when
- Cost-Driven Workloads: The contributor tier serves the same weights for far less, with data sharing
- Single-Turn Prompts: A smaller model in the family fits the economics better
- Strict Data Control: Confirm retention terms before choosing either tier
- Open Weights Requirement: Muse Glimmer 30B is the Apache 2.0 option
Copy link to headingConclusion
Muse Spark 1.2 is Meta's coding-focused agentic model, built for multi-agent workflows across a 1.0M tokens multimodal window. Point meta/muse-spark-1.2 at AI Gateway to route requests behind one API key, and treat the cheaper contributor slug as a data-governance decision rather than a pricing one.
Copy link to headingFrequently Asked Questions
What is Muse Spark 1.2 built for?
Complex agentic tasks with a coding focus. It runs as a main agent that plans and delegates, or as a subagent executing in parallel.
What input types does Muse Spark 1.2 accept?
Text, images, video, audio, and PDF documents. It returns text.
What is the context window for Muse Spark 1.2?
The context window is 1.0M tokens, with up to 1.0M tokens per response.
How is Muse Spark 1.2 different from muse-spark-1.2-contributor?
Same weights and same capabilities. The contributor slug bills far less in exchange for Meta using your inputs and outputs to train its models. Decide on data governance first.
How does Muse Spark 1.2 compare to Muse Spark 1.1?
It is the coding-focused successor, built around harness patterns including context compaction, subagents, whole-repository work, and long-running tasks.
Does Muse Spark 1.2 support parallel tool calls?
Yes, along with structured output and configurable reasoning effort.
Does Muse Spark 1.2 support Zero Data Retention?
Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.