Skip to content

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.

  1. GPT-6 LunaOpenAIRemove
  2. GPT-5.6 Luna ProOpenAIRemove
  3. Transcribe 1 ProFish AudioRemove
gpt-6-luna vs gpt-5.6-luna-pro vs transcribe-1-pro
AttributeGPT-6 Lunagpt-6-lunaGPT-5.6 Luna Progpt-5.6-luna-proTranscribe 1 Protranscribe-1-pro
Pricing
Input$0.10 / 1M$0.20 / 1M— Not priced per input token
Output$0.50 / 1M$1.20 / 1M— Not priced per output token
Cache Write (5m)$0.10 / 1M$0.20 / 1MNot applicable
Cache Write (1h)$0.10 / 1M$0.20 / 1MNot applicable
Cache Read$0.10 / 1M$0.20 / 1MNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M
Context
Max context1.1M1MN/A
Max outputN/AN/AN/A
Capabilities
VisionYesYesNo
Function CallingYesYesNo
JSON ModeYesYesNo
StreamingYesYesNo
Catalogue
ProviderOpenAIOpenAIFish Audio
Categorychatchatvoice
Charge typePay As You GoPay As You GoPay As You Go
Released——2026-09-24
Description
SummaryGPT-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-5.6 Luna Pro uses the same underlying model as GPT-5.6 Luna, but runs with reasoning.mode set to pro to deliver higher-quality responses on complex tasks. It is optimized for deeper reasoning, advanced coding, and multi-step agentic workflows, offering improved accuracy and solution quality while retaining the efficiency and scalability of the Luna tier.Fish Audio Transcribe 1 Pro speech-to-text with speaker labels; transcripts include speaker tags such as <|speaker:0|>. Billed per second of audio.