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.

Nova-3Deepgram Remove
GPT-6 Luna ProOpenAI Remove
Claude Sonnet 5.5Anthropic Remove
Perceptron Mk1.5Perceptron Remove

4 is the maximum. Remove one to add another.

nova-3 vs gpt-6-luna-pro vs claude-sonnet-5.5 vs perceptron-mk1.5
Attribute	Nova-3nova-3	GPT-6 Luna Progpt-6-luna-pro	Claude Sonnet 5.5claude-sonnet-5.5	Perceptron Mk1.5perceptron-mk1.5
Pricing
Input	$0 / 1M	$0.10 / 1M	$2.00 / 1M	$0.15 / 1M
Output	$0 / 1M	$0.50 / 1M	$10.00 / 1M	$1.50 / 1M
Cache Write (5m)	Not applicable	$0.10 / 1M	$2.50 / 1M	$0.15 / 1M
Cache Write (1h)	Not applicable	$0.10 / 1M	$4.00 / 1M	$0.15 / 1M
Cache Read	Not applicable	$0.10 / 1M	$0.20 / 1M	$0.15 / 1M
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	N/A	1.1M	1M	36.9K
Max output	N/A	N/A	N/A	N/A
Capabilities
Vision	No	Yes	Yes	No
Function Calling	No	Yes	Yes	No
JSON Mode	No	Yes	Yes	No
Streaming	No	Yes	Yes	Yes
Catalogue
Provider	Deepgram	OpenAI	Anthropic	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	2026-07-15	—	—	2026-09-25
Description
Summary	Deepgram Nova-3 speech-to-text. Billed per second of audio.	GPT-6 Luna Pro uses the same underlying model as GPT-6 Luna, but runs with reasoning.mode set to pro for higher-quality responses on complex tasks. It combines Luna's speed and cost efficiency with deeper reasoning and more reliable multi-step execution, making it well suited for advanced coding, computer use, and agentic workflows where higher solution quality is needed without moving to a larger GPT-6 tier.	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.	Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.