Muse Wonder 1.0
muse-wonder-1.0Pricing
List prices at Meta Model API, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $4.00 | $20.00 | |
| Cached input 95% off input | $0.20 | 95% off input | |
| Web search $2.50 per 1,000 searches | $2.50 per 1,000 searches |
What it costs a month
At Meta Model API list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$2,358
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$1,728
- Coding agent1,000 requests a day, 40K in / 2K out, cached$2,808
- Overnight batch20,000 requests a day, 4K in / 0.4K out$14,400
Where to run it
1 host serve Muse Wonder 1.0. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Meta Model APILab API muse-wonder-1.0 | $4.00 / $20.00 | muse-wonder-1.0 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- ImagesTextVideoPDFs
- Produces
- Text
- Effort settings the source lists
- minimalxhighmax
- Features
- Parallel tool callsPDF inputPrompt cachingBuilt-in web search
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Meta Model API.
Smaller Meta models
- 75% less
- 98% less
- 98% less
Other frontier labs
- 25% less
- 40% less
- 50% less
- 63% less
Open-weight picks
- 50% less
- 73% less
- 78% less
- 93% less
Call it
Using Meta Model API's API.
from litellm import completion
response = completion(
model="meta/muse-wonder-1.0",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Muse Wonder 1.0 cost?
On Meta Model API, Muse Wonder 1.0 costs $4.00 per million input tokens and $20.00 per million output tokens. Cached input costs $0.20 per million tokens.
Which APIs offer Muse Wonder 1.0?
Muse Wonder 1.0 runs on 1 API: Meta Model API.
What is Muse Wonder 1.0's context window?
1M tokens, with up to 131K tokens in one reply.
Is Muse Wonder 1.0 being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Muse Wonder 1.0?
Models that cost less and keep most of what it can do: Muse Spark 1.3 on Meta Model API (75% less), Gemini 4 Neon on Google AI Studio (25% less), GPT-5.3 Codex on OpenAI (40% less) and Kimi K3.1 Pro on Databricks (50% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Muse Wonder 1.0's API model id?
Use muse-wonder-1.0 with Meta Model API.
Sources
Raw catalog entry for muse-wonder-1.0 on Meta Model API
{
"cache_read_input_token_cost": 2e-7,
"input_cost_per_token": 0.000004,
"litellm_provider": "meta",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 0.00002,
"search_context_cost_per_query": {
"search_context_size_high": 0.0025,
"search_context_size_low": 0.0025,
"search_context_size_medium": 0.0025
},
"source": "https://dev.meta.ai/docs/pricing-rate-limits",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses",
"/v1/messages"
],
"supported_modalities": [
"text",
"image",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": true,
"supports_none_reasoning_effort": false,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
}