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.

Gemini 3.5 TranscribeGoogle Remove
GPT-6 LunaOpenAI Remove
GPT-6 AstraOpenAI Remove
Perceptron Mk1.5Perceptron Remove

4 is the maximum. Remove one to add another.

gemini-3.5-transcribe vs gpt-6-luna vs gpt-6-astra vs perceptron-mk1.5
Attribute	Gemini 3.5 Transcribegemini-3.5-transcribe	GPT-6 Lunagpt-6-luna	GPT-6 Astragpt-6-astra	Perceptron Mk1.5perceptron-mk1.5
Pricing
Input	$0 / 1M	$0.10 / 1M	$10.00 / 1M	$0.15 / 1M
Output	$0 / 1M	$0.50 / 1M	$50.00 / 1M	$1.50 / 1M
Cache Write (5m)	Not applicable	$0.10 / 1M	$10.00 / 1M	$0.15 / 1M
Cache Write (1h)	Not applicable	$0.10 / 1M	$10.00 / 1M	$0.15 / 1M
Cache Read	Not applicable	$0.10 / 1M	$10.00 / 1M	$0.15 / 1M
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	98.3K	1.1M	1M	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	No	Yes	Yes	No
Streaming	No	Yes	Yes	Yes
Catalogue
Provider	Google	OpenAI	OpenAI	Perceptron
Category	voice	chat	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	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.	GPT-6 Astra is OpenAI's flagship model for demanding end-to-end professional work, designed for advanced analysis, software engineering, deep research, scientific tasks, and document creation. It is particularly strong in long-horizon agentic workflows, including tasks that require sustained reasoning, tool orchestration, and computer and browser use, making it well suited for complex autonomous workflows and production-grade knowledge work.	Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.