Meta · OpenRouter / Multimodal chat

Muse Wonder

Meta’s multimodal reasoning model for complex questions, coding and working with long documents. Combine text, images, video, audio and PDFs in a conversation and receive a text response.

meta/muse-wonder

Supported inputs: Text inputImage inputVideo inputAudio inputPDF input
Generated output: Text output

Try Muse Wonder API examples

Provider context

1,048,576

Tokens across input and output

Max response

8,192

Output tokens per request on this service

Input

$5.72

USD per million tokens

Output

$28.58

USD per million tokens

Understand mixed media in one conversation

Ask about an image, summarize a video or recording, or reason over a PDF alongside text. Muse Wonder offers a 1,048,576-token provider context window for tasks that need substantial background.

Service limits

This relay accepts up to 40 messages and 256 KiB of text per request. Attach up to 8 files, with 4 MiB per embedded file and 8 MiB combined. The service caps each response at 8192 tokens. Provider context length and service upload limits apply separately.

Input, cache and output pricing

USD and credits per million tokens

Input, cache and output pricing · USD and credits per million tokens
Usage	OpenRouter	Platform price	Platform credits
Input	$4.00	$5.72	57,200
Cache read	$0.20	$0.29	2,900
Output	$20.00	$28.58	285,800

Input, cached input and output are charged at their respective rates. Each chat turn includes the previous messages you send. Credits are reserved before a request and settled against the cost reported by OpenRouter, with a minimum of 1 credit per successful request. 10000 credits = $1.

View published pricing on OpenRouter

Integrate with the chat API

Send requests to /v1/chat/completions with your account API key and model ID meta/muse-wonder. Use a string for text or an array of content parts to combine media. Each example below is a complete request.

Manage API keys

The current relay returns a complete response with stream: false. The examples use a 256-token output limit. Replace YOUR_API_KEY and any sample media URLs or base64 data before calling.

Text input

Send a plain text message with the same model ID used in the playground.

curl https://decisions-api.dev/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "meta/muse-wonder",
  "messages": [
    {
      "role": "user",
      "content": "Summarize the key points of this message."
    }
  ],
  "max_completion_tokens": 256,
  "stream": false
}'

Image input

Use image_url for a public HTTPS image URL or a base64 data URL. Supported embedded images: PNG, JPEG and WebP.

curl https://decisions-api.dev/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "meta/muse-wonder",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Describe this image."
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/image.jpg"
          }
        }
      ]
    }
  ],
  "max_completion_tokens": 256,
  "stream": false
}'

Video input

Use video_url for a public HTTPS video URL or a base64 data URL. Supported embedded video: MP4, MPEG, MOV and WebM.

curl https://decisions-api.dev/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "meta/muse-wonder",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Summarize the events in this clip."
        },
        {
          "type": "video_url",
          "video_url": {
            "url": "https://example.com/video.mp4"
          }
        }
      ]
    }
  ],
  "max_completion_tokens": 256,
  "stream": false
}'

Audio input

Use input_audio with the recording’s base64 data and format. Do not include a data URL prefix in the data field.

curl https://decisions-api.dev/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "meta/muse-wonder",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Summarize this recording."
        },
        {
          "type": "input_audio",
          "input_audio": {
            "data": "BASE64_AUDIO_DATA",
            "format": "wav"
          }
        }
      ]
    }
  ],
  "max_completion_tokens": 256,
  "stream": false
}'

PDF input

Use file with a PDF filename and file_data containing a public HTTPS URL or a data:application/pdf;base64,... URL.

curl https://decisions-api.dev/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "meta/muse-wonder",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Summarize this document."
        },
        {
          "type": "file",
          "file": {
            "filename": "document.pdf",
            "file_data": "https://example.com/document.pdf"
          }
        }
      ]
    }
  ],
  "max_completion_tokens": 256,
  "stream": false
}'

Muse Wonder playground

Muse Wonder

meta/muse-wonder

What would you like to understand?

Ask a question, attach media, or combine them. Muse Wonder accepts text, images, video, audio and PDF files and replies with text.

Max output

PNG, JPEG, WebP, MP4, MPEG, MOV, WebM, WAV, MP3, AIFF, AAC, OGG, FLAC, M4A and PDF · 4 MiB per file · 8 MiB total · 8 files per conversation