Meta

Meta: Muse Spark 1.3

Unmapped
Context

1M

Input

text, file, image, video

Output

text

Tool calling

Supported

About this model

Muse Spark 1.3 is Meta's natively multimodal reasoning model optimized for long-horizon agentic workflows, advanced coding, tool use, computer interaction, and complex multi-step tasks. It is designed to sustain multiple workflows within long conversations, generate and manage context across conflicting sources, identify and correct gaps in its plans, and efficiently complete real-world engineering and knowledge-work tasks. Compared with Muse Spark 1.2, it improves coding and agentic performance while using fewer tool calls and fewer tokens.

Input modalities

text

Accepted as model input

file

Accepted as model input

image

Accepted as model input

video

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Available

Input tokens

$1.250 / 1M tokens

Output tokens

$4.250 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$1.250 / 1M tokens
Output tokens$4.250 / 1M tokens
Cached input tokens$0.150 / 1M tokens

Performance

Published evaluation results associated with this model.

Agent

GDPVal-AA v21754
JobBench64.9
OSWorld 2.066.9
DeepSearchQA89.4
Agentic IF Index (Internal)57.8
AutomationBench49.4

Long Context

MRCR 256K-512K98.5
MRCR 512K-1M98.1

Coding

DeepSWE v1.175.4
SWEAtlas CodeBase QnA59.4
Terminal-Bench 2.188.8

API Guide

Refer Documentation
  1. 1

    Generate your access token

    Use your API key to generate the JWT access token required by the Models API.

  2. 2

    Add the JWT token

    Copy the generated JWT token and replace JWT_TOKEN in the example below.

  3. 3

    Check your credits

    If your balance is too low, before calling the model.

  4. 4

    Run the API example

    Choose your preferred language, copy the example, and send your first model request.

    curl https://api.oneinfer.ai/v1/ula/chat/completions \
      -H "Authorization: Bearer $JWT_TOKEN" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "Unmapped",
        "messages": [
          { "role": "user", "content": "Hello!" }
        ]
      }'