The Orchestrator › Models › Meta
Meta: Muse Spark Open
Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...
Specifications
| Provider | Meta |
| Model ID | meta/muse-spark-open |
| Context window | 1.0M tokens (1,048,576) |
| Modalities | text + image + file + audio + video → text |
| Tokenizer | Other |
| Router sources | OpenRouter, Vercel AI Gateway, Cloudflare |
| Released | 2026-10-15 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Mandatory |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | meta/muse-spark-open | $1.25 | $4.25 | 1.0M |
| standard | Vercel AI Gateway | meta/muse-spark-open | $1.25 | $4.25 | 1.0M |
| standard | Cloudflare | meta/muse-spark-open | $1.25 | $4.25 | — |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $1.25 | $4.25 | — |
| 2026-11-14 | $1.25 | $4.25 | 1.0M |
| 2026-11-14 | $1.25 | $4.25 | 1.0M |
Capabilities
Vision (image input)Audio inputVideo inputFile inputAgentic tool useStructured outputsReasoning (always on)1M+ context windowControllable reasoningZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p