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.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
The full 1M token context window is included at standard pricing. Free credits on signup.
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 34.3 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Coding | 71.3 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Muse Spark 1.1 This page | Agentic tasks, computer use & coding | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
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.