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. GLM 4.6 (Thinking)Z.AIRemove
muse-spark-1.3 vs glm-4.6-thinking
AttributeMuse Spark 1.3muse-spark-1.3GLM 4.6 (Thinking)glm-4.6-thinking
Pricing
Input$1.25 / 1M$0.40 / 1M
Output$4.25 / 1M$1.50 / 1M
Cache Write (5m)$1.25 / 1M$0.40 / 1M
Cache Write (1h)$1.25 / 1M$0.40 / 1M
Cache Read$1.25 / 1M$0.40 / 1M
Web Search$0 / 1M$0 / 1M
Context
Max context1M202.8K
Max outputN/AN/A
Capabilities
VisionYesYes
Function CallingYesYes
JSON ModeYesYes
StreamingYesYes
Catalogue
ProviderMetaZ.AI
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.GLM-4.6 improves on GLM-4.5 with a larger 200K context window, stronger coding performance (including better real-world agent tools like Claude Code and Cline), and clearer gains in reasoning with built-in tool use. It delivers more capable agent behavior, integrates better into agent frameworks, and produces more natural, readable writing — especially in role-playing scenarios.