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. GLM 5.3Z.AIRemove
  2. Kimi K3MoonShot AIRemove
  3. GLM 5.3 FlashZ.AIRemove
glm-5.3 vs kimi-k3 vs glm-5.3-flash
AttributeGLM 5.3glm-5.3Kimi K3kimi-k3GLM 5.3 Flashglm-5.3-flash
Pricing
Input$1.40 / 1M$3.00 / 1M$0.075 / 1M
Output$4.40 / 1M$15.00 / 1M$0.25 / 1M
Cache Write (5m)$1.40 / 1M$3.00 / 1M$0.075 / 1M
Cache Write (1h)$1.40 / 1M$3.00 / 1M$0.075 / 1M
Cache Read$1.40 / 1M$3.00 / 1M$0.075 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M
Context
Max context1M1M1M
Max outputN/AN/AN/A
Capabilities
VisionNoYesYes
Function CallingYesYesYes
JSON ModeYesYesYes
StreamingYesYesYes
Catalogue
ProviderZ.AIMoonShot AIZ.AI
Categorychatchatchat
Charge typePay As You GoPay As You GoPay As You Go
Released
Description
SummaryGLM-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.Kimi K3 is Moonshot AI's 2.8T-parameter open-weight multimodal reasoning model, designed for complex coding, knowledge work, and long-horizon agentic workflows. It excels at repository-scale development, tool use, debugging, and iterative problem solving across text, images, logs, tests, and runtime feedback. Built with KDA and Attention Residuals for improved computational efficiency, Kimi K3 delivers strong performance on advanced engineering and multimodal reasoning tasks, making it well suited for autonomous coding agents and large-scale production workflows.GLM-5.3-Flash is Z.AI's efficient native multimodal model, designed for coding and long-horizon agentic workflows. It combines strong multimodal capabilities with an architecture optimized for responsive, cost-efficient task execution. Built on a hybrid sparse and linear attention architecture, GLM-5.3-Flash maintains accurate long-context behavior while reducing computational overhead, making it well suited for coding agents, extended multi-step tasks, and scalable production workloads.