Meta

Muse Wonder 1.0

Meta's model for complex code changes and long-running agents. Give it a task, tools and a clear way to check the result.

meta/muse-wonder-1.0Coding and agentstext inputtext output

Run this model

meta/muse-wonder-1.0

Use an endpoint supported by this model.

Get a key for this setup →
Thinking guide →
const response = await fetch('https://api.minirouter.sh/v1/chat/completions', {  method: 'POST',  headers: {    Authorization: `Bearer ${process.env.MINIROUTER_KEY}`,    'Content-Type': 'application/json',  },  body: JSON.stringify({    model: 'meta/muse-wonder-1.0',    messages: [{ role: 'user', content: 'Why is the sky blue?' }],    max_tokens: 1024,  }),}) const data = await response.json()console.log(data.choices[0].message.content)
Read docs →

Start with a text request and an explicit max_tokens limit. Reasoning consumes the output budget, so leave room for the answer. Meta's native tools and multimodal features require separate route qualification.

Model overview

Input / 1M
$4.2
All-in MiniRouter rate
Output / 1M
$21
All-in MiniRouter rate
Context
1M
1,048,576 tokens
Max output
1M
tokens
Reasoning
Adjustable effort
Minimal through xhigh in the catalog
API edition
Standard
Wonder Full is a separate offering
Announced
12 Oct 2026
publisher release
Coding and agents

Work through the whole task.

Meta positions Wonder for planning, tool use and recovery across longer tasks. Evaluate it on completed work, including retries and total cost.
  1. [ 01 ]

    Change a codebase

    Supply the relevant files, constraints and acceptance checks. Review the diff and run the project's tests.

  2. [ 02 ]

    Coordinate several steps

    Give the agent bounded tools and explicit stopping conditions. Check intermediate results before it continues.

  3. [ 03 ]

    Reason over long inputs

    Keep input and generated output within the shared context window. Ask for references to the supplied material.

Publisher list prices

Budget for reasoning and output.

Meta's Standard API rates below exclude MiniRouter's fee. Current MiniRouter route prices appear above; cache savings depend on cache hits.

Meta Standard · per 1M tokens

Input
$4.00
Cached input
$0.20
Output
$20.00
Meta API pricing ↗, checked October 12, 2026.
View chart data
Muse Wonder publisher prices per million tokens
RateUSD per 1M tokens
Input$4.00
Cached input$0.20
Output$20.00
Choose the right model

Wonder and Wonder Full are distinct.

This page covers meta/muse-wonder-1.0. Meta offers Wonder Full separately through Muse Code subscriptions.
  1. [ 01 ]

    Use the exact API ID

    Select meta/muse-wonder-1.0 in your client. Raising reasoning effort does not switch the request to Wonder Full.

  2. [ 02 ]

    Check supported settings

    Use the effort values published by your route. Native Meta API options may differ from the MiniRouter catalog.

  3. [ 03 ]

    Keep tools in your application

    Computer use, search and agent orchestration need their own integrations. Selecting the model does not install those tools.

Route

One route, standard clients.

Authenticate with a MiniRouter bearer key. Caller-provided upstream credentials are not used on this route.
Base URLhttps://api.minirouter.sh/v1
Model IDmeta/muse-wonder-1.0
Endpoints/v1/chat/completions/v1/messages/v1/responses
Parametersmax_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning
Structured outputNot enforced; a requested format is dropped and the answer is plain text.
ModalitiesInput: text · Output: text

Configured providers. Priority follows the live catalog order.

ProviderPriorityInput / 1MOutput / 1MParametersAccess
vercel
1$4.2$21max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoningMiniRouter balance

Every model, one key.