Muse Spark 1.1 API

meta/muse-spark-1.1
Muse Spark 1.1 is a chat model from Meta accepting text, image, and file input with text output. It offers a 1,000,000-token context window plus reasoning, function calling, vision, web search, and structured outputs. Suited to long-document analysis rather than short exchanges.
Context
1M tokens
Input
$1.71925 / 1M tokens
Output
$5.84545 / 1M tokens
Released
Jul 9, 2026

How to use Muse Spark 1.1 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to meta/muse-spark-1.1.

from openai import OpenAI

client = OpenAI(
   base_url="https://api.aimlapi.com/v1",
   api_key="<YOUR_AIMLAPI_KEY>",
)

response = client.chat.completions.create(
   model="meta/muse-spark-1.1",
   messages=[
       {"role": "system", "content": "You are a helpful assistant."},
       {"role": "user", "content": "What can Muse Spark 1.1 do?"},
   ],
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
 baseURL: "https://api.aimlapi.com/v1",
 apiKey: "<YOUR_AIMLAPI_KEY>",
});

const response = await client.chat.completions.create({
 model: "meta/muse-spark-1.1",
 messages: [
   { role: "system", content: "You are a helpful assistant." },
   { role: "user", content: "What can Muse Spark 1.1 do?" },
 ],
});

console.log(response.choices[0].message.content);

curl https://api.aimlapi.com/v1/chat/completions \
 -H "Authorization: Bearer <YOUR_AIMLAPI_KEY>" \
 -H "Content-Type: application/json" \
 -d '{
   "model": "meta/muse-spark-1.1",
   "messages": [
     {"role": "system", "content": "You are a helpful assistant."},
     {"role": "user", "content": "What can Muse Spark 1.1 do?"}
   ]
 }'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Muse Spark 1.1 API Pricing

TypePrice
Input
$1.71925 / 1M tokens
Output
$5.84545 / 1M tokens
Cached input
$0.20631 / 1M tokens

The full 1M token context window is included at standard pricing. Free credits on signup.

Muse Spark 1.1 Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
Intelligence
34.3
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Coding
71.3
Composite score across standardised coding evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

Muse Spark 1.1 vs other models

ModelInputOutputContextBest for
$1.71925 / 1M tokens
$5.84545 / 1M tokens
1M tokens
Agentic tasks, computer use & coding
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

Muse Spark 1.1 has a 1,000,000 tokens context window and can return up to 128,00 tokens.

Muse Spark 1.1 takes text, image, file in as input and returns text out.

Use meta/muse-spark-1.1 as the model id.

Muse Spark 1.1 became available on July 9, 2026.

Muse Spark 1.1 is priced at input $1.71925 / 1M tokens, output $5.84545 / 1M tokens, cached input $0.20631 / 1M tokens.

Yes, Muse Spark 1.1 can stream responses as they are generated.

Yes, Muse Spark 1.1 accepts image input alongside text.

Muse Spark 1.1 was built by Meta.

Yes, computer use is listed among its features.

Yes, it supports parallel tool calling.

Start building with Muse Spark 1.1

Get API Key
1000+ models, one API.