Last refreshed 2026-10-12. Next refresh: weekly.
Why use Muse Wonder on Meta Model API?
Meta Model API offers Muse Wonder with pay-as-you-go pricing at $4.00/1M input tokens. Meta Model API is Meta's developer API for accessing Muse Spark 1.1 in public preview, with OpenAI-compatible and Anthropic-compatible request formats, tool/function calling, structured output, and multimodal agentic workflows.
Compare Muse Wonder across 3 providers to find the best fit for your use caseInput / 1M
$4.00
Output / 1M
$20.00
Cache
read $0.20
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: muse-wonder-1.0Model ID
muse-wonder-1.0Request example
Curated snippets for this provider are not sourced yet. Use Meta Model API documentation with model ID
muse-wonder-1.0.Gotchas
- Use provider model ID "muse-wonder-1.0", not the LLMReference slug "muse-wonder".
Compare Muse Wonder Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Meta Model API | $4.00 | $20.00 |
| OpenRouter | $4.00 | $20.00 |
| Vercel AI Gateway | $4.00 | $20.00 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $4.00 |
| Output tokens | $20.00 |
Capabilities
VisionMultimodalReasoningJSON / Tool usePrompt CachingAudio
About Muse Wonder
Muse Wonder is a Meta Superintelligence Labs model released October 12, 2026, for agentic coding, long-running agents and computer use. Meta says it builds on a larger base model than the Muse Spark models. It takes text, image, video and audio input and returns text, with a 1M-token context window. A larger sibling, Muse Wonder Full, is offered only through a Muse Code subscription.
Get Started
Model Specs
Released2026-10-12
Context1M