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.

Perceptron Mk1.5Perceptron Remove
S2 ProFish Audio Remove
GPT-6 LunaOpenAI Remove
Gemini 3.5 TranscribeGoogle Remove

4 is the maximum. Remove one to add another.

perceptron-mk1.5 vs s2-pro vs gpt-6-luna vs gemini-3.5-transcribe
Attribute	Perceptron Mk1.5perceptron-mk1.5	S2 Pros2-pro	GPT-6 Lunagpt-6-luna	Gemini 3.5 Transcribegemini-3.5-transcribe
Pricing
Input	$0.15 / 1M	$0 / 1M	$0.10 / 1M	$0 / 1M
Output	$1.50 / 1M	$0 / 1M	$0.50 / 1M	$0 / 1M
Cache Write (5m)	$0.15 / 1M	Not applicable	$0.10 / 1M	Not applicable
Cache Write (1h)	$0.15 / 1M	Not applicable	$0.10 / 1M	Not applicable
Cache Read	$0.15 / 1M	Not applicable	$0.10 / 1M	Not applicable
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	36.9K	N/A	1.1M	98.3K
Max output	N/A	N/A	N/A	N/A
Capabilities
Vision	No	No	Yes	Yes
Function Calling	No	No	Yes	Yes
JSON Mode	No	No	Yes	No
Streaming	Yes	No	Yes	No
Catalogue
Provider	Perceptron	Fish Audio	OpenAI	Google
Category	chat	voice	chat	voice
Charge type	Pay As You Go	Pay As You Go	Pay As You Go	Pay As You Go
Released	2026-09-25	2026-07-29	—	2026-09-25
Description
Summary	Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.	Fish Audio S2 Pro text-to-speech. Billed per UTF-8 byte of input text.	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.