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.

GLM 5V TurboZ.AI Remove
Perceptron Mk1.5Perceptron Remove
Gemini 3.5 TranscribeGoogle Remove
GPT-6 LunaOpenAI Remove

4 is the maximum. Remove one to add another.

glm-5v-turbo vs perceptron-mk1.5 vs gemini-3.5-transcribe vs gpt-6-luna
Attribute	GLM 5V Turboglm-5v-turbo	Perceptron Mk1.5perceptron-mk1.5	Gemini 3.5 Transcribegemini-3.5-transcribe	GPT-6 Lunagpt-6-luna
Pricing
Input	$1.20 / 1M	$0.15 / 1M	— Not priced per input token	$0.10 / 1M
Output	$4.00 / 1M	$1.50 / 1M	— Not priced per output token	$0.50 / 1M
Cache Write (5m)	$1.20 / 1M	$0.15 / 1M	Not applicable	$0.10 / 1M
Cache Write (1h)	$1.20 / 1M	$0.15 / 1M	Not applicable	$0.10 / 1M
Cache Read	$1.20 / 1M	$0.15 / 1M	Not applicable	$0.10 / 1M
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	202.8K	36.9K	98.3K	1.1M
Max output	N/A	N/A	N/A	N/A
Capabilities
Vision	Yes	No	Yes	Yes
Function Calling	Yes	No	Yes	Yes
JSON Mode	Yes	No	No	Yes
Streaming	Yes	Yes	No	Yes
Catalogue
Provider	Z.AI	Perceptron	Google	OpenAI
Category	chat	chat	voice	chat
Charge type	Pay As You Go	Pay As You Go	Pay As You Go	Pay As You Go
Released	—	2026-09-25	2026-09-25	—
Description
Summary	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.	Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.	Google Gemini 3.5 Transcribe speech-to-text. Billed per input and output token.	GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, optimized for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks. It combines low-cost, responsive inference with the GPT-6 family’s improvements in factual reliability and clear, concise communication. At higher reasoning effort, GPT-6 Luna can also handle complex software engineering and computer-use workflows that previously required a Sol-tier model, making it a versatile choice for scalable production applications that need to balance speed, cost, and capability.