Text model API
Muse Spark 1.3 API
Muse Spark 1.3 is a multimodal reasoning model from Meta built for long-running agentic, multi-agent, and coding workflows. It is designed to maintain context across extended tasks, reason through conflicting information, and ask for clarification or confirmation when required, while keeping execution concise. With a 1,048,576-token context window, Muse Spark 1.3 is well suited for large codebases, lengthy documents, complex multi-step workflows, and tasks that require sustained reasoning over many interactions. It supports text, images, video, PDFs and other files as inputs and returns tex
- Model id
muse-spark-13- Takes
- Text (required)
- Makes
- Text
- Endpoint
POST /api/v1/chat/completions- Made by
- Meta
- Mode
- Synchronous
Call Muse Spark 1.3
https://payload.rentprompts.com/api/v1. Replace the placeholder with your key.Model muse-spark-13
POST /api/v1/chat/completions
curl https://payload.rentprompts.com/api/v1/chat/completions \
-H "Authorization: Bearer rp_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "muse-spark-13",
"messages": [
{
"role": "user",
"content": "Write a haiku about APIs."
}
],
"max_tokens": 256
}'Replace rp_live_YOUR_KEY with your key, ideally via the RENTPROMPTS_API_KEY environment variable. Keys are shown only once, so they are never filled in here. Get your API key →
What a typical call costs
- 1,000 input + 500 output tokens0.45 Joules
- 10,000 input + 2,000 output tokens3 Joules
Send requests to POST /api/v1/chat/completions. Muse Spark 1.3 answers synchronously: the result comes back in the response to the same request. Token counts come from the model's own usage report, so a real call may use more or fewer tokens than this example.
Settings
This model has no extra settings. Send the standard fields shown in the example.