Skip to content
Apertis
Get started

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. Llama 3.2 3B InstructMetaRemove
  2. Hy4 previewTencentRemove
  3. GLM 5.3Z.AIRemove
llama-3.2-3b-instruct vs hy4-preview vs glm-5.3
AttributeLlama 3.2 3B Instructllama-3.2-3b-instructHy4 previewhy4-previewGLM 5.3glm-5.3
Pricing
Input$0.324 / 1M$0.834 / 1M$1.40 / 1M
Output$0.324 / 1M$2.50 / 1M$4.40 / 1M
Cache Write (5m)$0.324 / 1M$0.834 / 1M$1.40 / 1M
Cache Write (1h)$0.324 / 1M$0.834 / 1M$1.40 / 1M
Cache Read$0.324 / 1M$0.834 / 1M$1.40 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M
Context
Max context131.1K1M1M
Max outputN/AN/AN/A
Capabilities
VisionNoYesNo
Function CallingNoYesYes
JSON ModeNoYesYes
StreamingNoYesYes
Catalogue
ProviderMetaTencentZ.AI
Categorychatchatchat
Charge typePay As You GoPay As You GoPay As You Go
Released———
Description
Summary—Tencent Hy4 Preview is a Mixture-of-Experts (MoE) model from Tencent, featuring 770B total parameters with 49B activated per token. It is designed for coding agents, complex tool-driven workflows, and professional productivity tasks that require strong planning and reliable execution. Optimized for context continuity and sustained multi-step work, Hy4 Preview is well suited for long-horizon coding, agentic automation, tool orchestration, and complex real-world 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.