Muse Spark 1.3
by NanoGPT · family muse · listed Sep 2026RTV
Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.
Current rates USD per 1M tokens
Input$1.25
Output$4.25
Cache read$0.15
Cache write—
Against the market
On the record
- Model id
meta/muse-spark-1.3- Context window
- 1.0M tokens
- Max output
- 944K tokens
- Input modalities
- text, image, video, pdf, audio
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-09-02
- Last updated
- 2026-09-02
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- LLM Gateway$1.25 in · $4.25 out
- Kilo Gateway$1.25 in · $4.25 out
- OpenRouter$1.25 in · $4.25 out
- Meta$1.25 in · $4.25 out
- Vercel AI Gateway$1.25 in · $4.25 out
- Opper$1.25 in · $4.25 out
- OpenCode Zen$1.25 in · $4.25 out
- DevPass (LLM Gateway)$1.25 in · $4.25 out
- AIHubMix$1.38 in · $4.67 out