Skip to content

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

  1. Muse Spark 1.3MetaRemove
  2. Fugu UltraSakanaRemove
muse-spark-1.3 vs fugu-ultra
AttributeMuse Spark 1.3muse-spark-1.3Fugu Ultrafugu-ultra
Pricing
Input$1.25 / 1M$5.00 / 1M
Output$4.25 / 1M$30.00 / 1M
Cache Write (5m)$1.25 / 1M$5.00 / 1M
Cache Write (1h)$1.25 / 1M$5.00 / 1M
Cache Read$1.25 / 1M$5.00 / 1M
Web Search$0 / 1M$0 / 1M
Context
Max context1M1M
Max outputN/AN/A
Capabilities
VisionYesYes
Function CallingYesYes
JSON ModeYesYes
StreamingYesYes
Catalogue
ProviderMetaSakana
Categorychatchat
Charge typePay As You GoPay As You Go
Released
Description
SummaryMuse Spark 1.3 is Meta's multimodal reasoning model designed for long-running agentic, multi-agent, and coding workflows. It maintains context and information across extended tasks, enabling reliable execution in complex, multi-step environments. The model is optimized to resolve conflicting information, seek clarification or confirmation when necessary, and execute concisely, making it well suited for autonomous agents, collaborative multi-agent systems, and long-horizon software engineering workflows.Fugu Ultra is the high-performance model in Sakana AI's Fugu family, built as a learned multi-agent orchestration system rather than a single monolithic model. It intelligently routes tasks across a pool of underlying models and can recursively invoke itself to solve complex problems more effectively. Optimized for multi-step reasoning, coding, and agentic workflows, Fugu Ultra supports configurable reasoning effort, native tool calling, and built-in web search. Its orchestration-based design makes it well suited for advanced autonomous agents and complex task execution requiring adaptive model coordination.