Skip to content
Apertis

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. Perceptron Mk1.5PerceptronRemove
  2. Claude Sonnet 5.5AnthropicRemove
  3. Gemini 3.5 TranscribeGoogleRemove
  4. GLM 5V TurboZ.AIRemove

4 is the maximum. Remove one to add another.

perceptron-mk1.5 vs claude-sonnet-5.5 vs gemini-3.5-transcribe vs glm-5v-turbo
AttributePerceptron Mk1.5perceptron-mk1.5Claude Sonnet 5.5claude-sonnet-5.5Gemini 3.5 Transcribegemini-3.5-transcribeGLM 5V Turboglm-5v-turbo
Pricing
Input$0.15 / 1M$2.00 / 1M— Not priced per input token$1.20 / 1M
Output$1.50 / 1M$10.00 / 1M— Not priced per output token$4.00 / 1M
Cache Write (5m)$0.15 / 1M$2.50 / 1MNot applicable$1.20 / 1M
Cache Write (1h)$0.15 / 1M$4.00 / 1MNot applicable$1.20 / 1M
Cache Read$0.15 / 1M$0.20 / 1MNot applicable$1.20 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max context36.9K1M98.3K202.8K
Max outputN/AN/AN/AN/A
Capabilities
VisionNoYesYesYes
Function CallingNoYesYesYes
JSON ModeNoYesNoYes
StreamingYesYesNoYes
Catalogue
ProviderPerceptronAnthropicGoogleZ.AI
Categorychatchatvoicechat
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-09-25—2026-09-25—
Description
SummaryPerceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, serving as a direct upgrade to Sonnet 5. It excels at feature development, bug fixing, and creating polished documents, presentations, and spreadsheets, while offering clearer writing and communication than its predecessor.Google Gemini 3.5 Transcribe speech-to-text. Billed per input and output token.GLM-5V-Turbo is Z.ai's first native multimodal agent foundation model, designed for vision-based coding and agent-driven workflows. It natively supports image, video, and text inputs, enabling integrated multimodal reasoning and execution. The model excels at long-horizon planning, complex coding, and multi-step task execution, and works seamlessly with agents to complete the full loop of “perceive → plan → execute”, making it well suited for advanced multimodal automation and real-world agent systems.