Meta / meta/muse-wonder-1.0
Muse Wonder - access through LLMTR
Muse Wonder is the Muse model Meta offers for its hardest work, and it is in preview. It is built for tasks that need deep reasoning: planning a change across a repository, long-horizon coding and multi-step agent work. It has a 1,048,576-token context window, accepts image, video and PDF alongside text, and returns tool calls, JSON or schema-conforming output. It reasons before every answer and this cannot be turned off; set `reasoning_effort` to minimal, low, medium, high, xhigh or max. Without the field it runs at max; Meta suggests starting agentic coding at `high`. Reasoning tokens are billed as output inside `completion_tokens`. `tool_choice` accepts only `auto`.
Technical specifications
| Canonical ID | meta/muse-wonder-1.0 |
|---|---|
| Provider | Meta |
| Context window | 1,048,576 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text, image, video |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | INPUT_TEXT | PER_1M_TOKENS | $4.00 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.200000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $20.00 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"meta/muse-wonder-1.0","messages":[{"role":"user","content":"Hello"}]}'Related models
- Muse Spark 1.3 meta/muse-spark-1.3
- Muse Ember meta/muse-ember-1.0
- Muse Glimmer 30B meta/muse-glimmer-30b
- Muse Image meta/muse-image-1.0
- Muse Spark 1.2 meta/muse-spark-1.2
- Muse Spark 1.1 meta/muse-spark-1.1
- Muse Spark 1.2 Contributor meta/muse-spark-1.2-contributor
- Muse Spark 1.3 Contributor meta/muse-spark-1.3-contributor