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 Luna ProOpenAI Remove
Transcribe 1Fish Audio Remove
Claude Sonnet 5.5Anthropic Remove
S2 ProFish Audio Remove

4 is the maximum. Remove one to add another.

gpt-6-luna-pro vs transcribe-1 vs claude-sonnet-5.5 vs s2-pro
Attribute	GPT-6 Luna Progpt-6-luna-pro	Transcribe 1transcribe-1	Claude Sonnet 5.5claude-sonnet-5.5	S2 Pros2-pro
Pricing
Input	$0.10 / 1M	$0 / 1M	$2.00 / 1M	$0 / 1M
Output	$0.50 / 1M	$0 / 1M	$10.00 / 1M	$0 / 1M
Cache Write (5m)	$0.10 / 1M	Not applicable	$2.50 / 1M	Not applicable
Cache Write (1h)	$0.10 / 1M	Not applicable	$4.00 / 1M	Not applicable
Cache Read	$0.10 / 1M	Not applicable	$0.20 / 1M	Not applicable
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	1.1M	N/A	1M	N/A
Max output	N/A	N/A	N/A	N/A
Capabilities
Vision	Yes	No	Yes	No
Function Calling	Yes	No	Yes	No
JSON Mode	Yes	No	Yes	No
Streaming	Yes	No	Yes	No
Catalogue
Provider	OpenAI	Fish Audio	Anthropic	Fish Audio
Category	chat	voice	chat	voice
Charge type	Pay As You Go	Pay As You Go	Pay As You Go	Pay As You Go
Released	—	2026-07-29	—	2026-07-29
Description
Summary	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.	Fish Audio Transcribe 1 speech-to-text. Billed per second of audio.	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.	Fish Audio S2 Pro text-to-speech. Billed per UTF-8 byte of input text.