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. mai-ds-r1:freeNot in the catalogueRemove
  2. GLM 5.3 FlashZ.AIRemove
  3. Gemini 4 ArgonGoogleRemove
  4. Perceptron Mk1.5PerceptronRemove

4 is the maximum. Remove one to add another.

mai-ds-r1:free vs glm-5.3-flash vs gemini-4-argon vs perceptron-mk1.5
Attributemai-ds-r1:freeNot in the catalogueGLM 5.3 Flashglm-5.3-flashGemini 4 Argongemini-4-argonPerceptron Mk1.5perceptron-mk1.5
Pricing
Input—$0.075 / 1M$2.00 / 1M$0.15 / 1M
Output—$0.25 / 1M$10.00 / 1M$1.50 / 1M
Cache Write (5m)—$0.075 / 1M$2.00 / 1M$0.15 / 1M
Cache Write (1h)—$0.075 / 1M$2.00 / 1M$0.15 / 1M
Cache Read—$0.075 / 1M$2.00 / 1M$0.15 / 1M
Web Search—$0 / 1M$0 / 1M$0 / 1M
Context
Max context—1M1M36.9K
Max output—N/AN/AN/A
Capabilities
Vision—YesYesNo
Function Calling—YesYesNo
JSON Mode—YesYesNo
Streaming—YesYesYes
Catalogue
Provider—Z.AIGooglePerceptron
Category—chatchatchat
Charge type—Pay As You GoPay As You GoPay As You Go
Released———2026-09-25
Description
Summary—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.Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.