Meta / meta/muse-spark-open
Muse Spark Open - access through LLMTR
Muse Spark Open is Meta's open-weight mixture-of-experts reasoning model: 816 billion parameters in total, about 42 billion active per token. It is trained for agentic coding: reading a codebase, writing and debugging code, and calling tools in multi-step agent loops. It has a 1,048,576-token context window, accepts image, video and audio alongside text, and returns tool calls, JSON or schema-conforming output. Reasoning runs before every answer and cannot be turned off; set `reasoning_effort` to low, medium, high or xhigh. Without it the model reasons at a high effort, so send `low` or `medium` for shorter, cheaper replies. Reasoning tokens are billed as output inside `completion_tokens`. A repeated prompt prefix can be billed at the cached-input rate.
Technical specifications
| Canonical ID | meta/muse-spark-open |
|---|---|
| Provider | Meta |
| Context window | 1,048,576 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text, image, audio, 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 | $1.25 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.150000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $4.25 |
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-spark-open","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- Muse Spark Open API: OpenAI SDK usage and pricing - On LLMTR, meta/muse-spark-open is called with the OpenAI SDK at https://llmtr.com/v1/chat/completions. The context window is 1,048,576 tokens, and per 1M tokens it costs $1.25 input, $0.15 input read from cache and $4.25 output. The model reasons before every answer; the level is chosen with reasoning_effort as low, medium, high or xhigh.
- Send images, video and audio to Muse Spark Open - On LLMTR, media reaches Muse Spark Open (meta/muse-spark-open) as a content part added to the message's content array in a request to https://llmtr.com/v1/chat/completions: image_url for images, video_url for video, input_audio for audio. Media tokens are billed inside prompt_tokens at the $1.25 per 1M token input price; the answer is text.
- Muse Spark Open reasoning_effort: levels and cost - On LLMTR, Muse Spark Open (meta/muse-spark-open) reasons before every answer; you choose the level in a /v1/chat/completions request with reasoning_effort set to low, medium, high or xhigh. Without the field the model reasons at a high effort. Reasoning tokens are billed inside completion_tokens at the output price of $4.25 per 1M tokens; every 1,000 reasoning tokens cost $0.00425.
- Models added to LLMTR in October 2026: facts and guide - Eight of the models LLMTR added in October 2026 in one table: Glimpse, Muse Spark Open, Nemotron 3.5 Super VL (paid and free rows), Moondream 3.1, EmbeddingMagibu 200M, the two decision models on /v1/systemone and Beam 1.0, free until 22 October 2026, 23:59 (Turkey time). All are called at https://llmtr.com/v1 with the same key; the free Qwen3.8 27B row, added earlier, is listed next to them.
Related models
- Muse Spark 1.3 meta/muse-spark-1.3
- 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
- Llama 3.3 70B Instruct (12K) meta/llama-3.3-70b-instruct-12k