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 5.3Z.AIRemove
  3. Nemotron Nano 9B V2 (Free)NVIDIARemove
muse-spark-1.3 vs glm-5.3 vs nemotron-nano-9b-v2
AttributeMuse Spark 1.3muse-spark-1.3GLM 5.3glm-5.3Nemotron Nano 9B V2 (Free)nemotron-nano-9b-v2
Pricing
Input$1.25 / 1M$1.40 / 1M$0 / 1M
Output$4.25 / 1M$4.40 / 1M$0 / 1M
Cache Write (5m)$1.25 / 1M$1.40 / 1M
Cache Write (1h)$1.25 / 1M$1.40 / 1M
Cache Read$1.25 / 1M$1.40 / 1M$0 / 1M
Web Search$0 / 1M$0 / 1M
Cache Write$0 / 1M
Context
Max context1M1M131.1K
Max outputN/AN/AN/A
Capabilities
VisionYesNoNo
Function CallingYesYesYes
JSON ModeYesYesYes
StreamingYesYesYes
Catalogue
ProviderMetaZ.AINVIDIA
Categorychatchatchat
Charge typePay As You GoPay As You GoFree
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-5.3 is Z.ai's large-scale reasoning model designed for complex software engineering and long-horizon agentic workflows. It supports text input and output with a 1M-token context window, enabling sustained reasoning across large codebases and extended multi-step tasks. Building on GLM-5.2, it delivers stronger coding performance while improving the balance between capability and token efficiency, making it well suited for autonomous coding agents, large-scale engineering workflows, and complex task execution.NVIDIA Nemotron Nano 9B v2 is a 9B-parameter language model trained from scratch by NVIDIA, designed to handle both reasoning and non-reasoning tasks. It can generate an internal reasoning trace before producing a final answer, and this behavior is configurable via system prompts—allowing developers to enable or suppress visible reasoning as needed.