Muse Spark 1.3

by meta · family muse-spark

Facts

Release date	2026-09-02
Retired date	—
Knowledge cutoff	—
Context (max)	1,048,576
Max output	—
Modalities	text, image, audio, video → text
Aliases	`muse-spark-1.3`
Open weights	no
Description	Meta's flagship follow-up to Muse Spark 1.2, positioned as its frontier return: 1.05M context tuned for long-context workloads, and audio+video added to the input mix over 1.2's image/PDF. Always-on reasoning. $1.25/$4.25 per Mtok; a Contributor program SKU serves at $0.10/$0.20. Rolling out via Muse Code and the Meta Model API.

Unknown values are shown as —.

Offerings

Provider	Wire ID	Variant	Endpoint	Protocol	Status	Price (USD / Mtok)	Reasoning
OpenCode Go	`muse-spark-1.3-contributor`	contributor	go-chat-completions	openai-chat	preview	—	effort · default on · mandatory · returns reasoning_content
OpenCode Zen	`muse-spark-1.3-contributor-free`	contributor	chat-completions	openai-chat	ga	0.00 / 0.00	effort · default on · mandatory · returns hidden
OpenCode Zen	`muse-spark-1.3`		responses	openai-responses	ga	1.25 / 4.25	effort · default on · mandatory · returns hidden
OpenRouter	`meta/muse-spark-1.3-contributor`	contributor	chat-completions	openai-chat	ga	0.10 / 0.20	effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content
OpenRouter	`meta/muse-spark-1.3`		chat-completions	openai-chat	ga	1.25 / 4.25	effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content

Reasoning controls

OpenCode Go· muse-spark-1.3-contributor· go-chat-completions effort

reasoning_effort lowmedium●highxhighmax

effort · default on · mandatory · returns reasoning_content

OpenCode Zen· muse-spark-1.3-contributor-free· chat-completions effort

reasoning_effort lowmedium●highxhighmax

effort · default on · mandatory · returns hidden

OpenCode Zen· muse-spark-1.3· responses effort

reasoning_effort lowmedium●highxhighmax

effort · default on · mandatory · returns hidden

OpenRouter· meta/muse-spark-1.3-contributor· chat-completions effort

reasoning.effort lowmedium●highxhighmax

effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content

OpenRouter· meta/muse-spark-1.3· chat-completions effort

reasoning.effort lowmedium●highxhighmax

effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content

Example requests

OpenCode Go · openai-chat · muse-spark-1.3-contributor

curl 'https://opencode.ai/zen/go/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "muse-spark-1.3-contributor",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "medium"
}'

Python (requests)

import requests

resp = requests.post(
    "https://opencode.ai/zen/go/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "muse-spark-1.3-contributor",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "medium"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://opencode.ai/zen/go/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "muse-spark-1.3-contributor",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "medium"
  }),
})
console.log(await resp.json())

OpenCode Zen · openai-chat · muse-spark-1.3-contributor-free

curl 'https://opencode.ai/zen/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "muse-spark-1.3-contributor-free",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "medium"
}'

Python (requests)

import requests

resp = requests.post(
    "https://opencode.ai/zen/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "muse-spark-1.3-contributor-free",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "medium"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://opencode.ai/zen/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "muse-spark-1.3-contributor-free",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "medium"
  }),
})
console.log(await resp.json())

OpenCode Zen · openai-responses · muse-spark-1.3

curl 'https://opencode.ai/zen/v1/responses' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "muse-spark-1.3",
  "input": "Tell me about the weather.",
  "reasoning_effort": "medium"
}'

Python (requests)

import requests

resp = requests.post(
    "https://opencode.ai/zen/v1/responses",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "muse-spark-1.3",
      "input": "Tell me about the weather.",
      "reasoning_effort": "medium"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://opencode.ai/zen/v1/responses", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "muse-spark-1.3",
    "input": "Tell me about the weather.",
    "reasoning_effort": "medium"
  }),
})
console.log(await resp.json())

OpenRouter · openai-chat · meta/muse-spark-1.3-contributor

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "meta/muse-spark-1.3-contributor",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "medium"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "meta/muse-spark-1.3-contributor",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "medium"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "meta/muse-spark-1.3-contributor",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "medium"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

OpenRouter · openai-chat · meta/muse-spark-1.3

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "meta/muse-spark-1.3",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "medium"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "meta/muse-spark-1.3",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "medium"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "meta/muse-spark-1.3",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "medium"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).