---
id: "meta/muse-spark-1.3"
also: ["meta/muse-spark-1.3-20260902", "requesty/meta/muse-spark-1.3", "vercel/meta/muse-spark-1.3"]
card_usd_per_m: "1.25 in, 4.25 out, at meta"
cheapest_list_usd_per_m: "1.25 in, 4.25 out, at google-vertex/global on openrouter"
cheapest_effective_usd_per_m: "0.3469 in, 4.2497 out, at meta on openrouter"
context: 1048576
max_output: 943718
input: ["text", "image", "video", "file"]
output: ["text"]
released: "2026-09-02"
reasoning: ["max", "xhigh", "high", "medium", "low", "minimal"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p"]
endpoints: 4
gateways: "openrouter (2), requesty (1), vercel (1)"
no_training: 4
trains: 0
retains_prompts: 2
intelligence: 36.6000
coding: 75.8000
agentic: 55.5000
---
# Meta: Muse Spark 1.3

Muse Spark 1.3 is Meta’s multimodal reasoning model for long-horizon agentic and coding workflows. With a 1M-token context window, reliable tool calling, higher first-attempt accuracy, and native understanding of video, images, and documents, it helps developers build capable coding agents and AI development workflows with fewer unnecessary turns and cleaner output.