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.

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

4 is the maximum. Remove one to add another.

gpt-6-luna vs gemini-3.5-transcribe vs glm-5-turbo vs perceptron-mk1.5
Attribute	GPT-6 Lunagpt-6-luna	Gemini 3.5 Transcribegemini-3.5-transcribe	GLM 5 Turboglm-5-turbo	Perceptron Mk1.5perceptron-mk1.5
Pricing
Input	$0.10 / 1M	— Not priced per input token	$0.96 / 1M	$0.15 / 1M
Output	$0.50 / 1M	— Not priced per output token	$3.20 / 1M	$1.50 / 1M
Cache Write (5m)	$0.10 / 1M	Not applicable	$0.96 / 1M	$0.15 / 1M
Cache Write (1h)	$0.10 / 1M	Not applicable	$0.96 / 1M	$0.15 / 1M
Cache Read	$0.10 / 1M	Not applicable	$0.96 / 1M	$0.15 / 1M
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	1.1M	98.3K	202.8K	36.9K
Max output	N/A	N/A	N/A	N/A
Capabilities
Vision	Yes	Yes	Yes	No
Function Calling	Yes	Yes	Yes	No
JSON Mode	Yes	No	Yes	No
Streaming	Yes	No	Yes	Yes
Catalogue
Provider	OpenAI	Google	Z.AI	Perceptron
Category	chat	voice	chat	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	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.	Google Gemini 3.5 Transcribe speech-to-text. Billed per input and output token.	GLM-5 Turbo is a high-performance model from Z.ai optimized for fast inference and agent-driven workflows. Designed for real-world environments such as OpenClaw scenarios, it delivers strong performance across long execution chains and complex task pipelines. The model features improved instruction decomposition, tool integration, scheduled and persistent execution, and enhanced stability for extended multi-step tasks, making it well suited for autonomous agents and production automation workflows.	Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.