Skip to content
Apertis

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. o4 Mini Deep ResearchOpenAIRemove
  2. Claude Sonnet 5.5AnthropicRemove
  3. GPT-6 Luna ProOpenAIRemove
o4-mini-deep-research vs claude-sonnet-5.5 vs gpt-6-luna-pro
Attributeo4 Mini Deep Researcho4-mini-deep-researchClaude Sonnet 5.5claude-sonnet-5.5GPT-6 Luna Progpt-6-luna-pro
Pricing
Input$2.00 / 1M$2.00 / 1M$0.10 / 1M
Output$8.00 / 1M$10.00 / 1M$0.50 / 1M
Cache Write (5m)$2.00 / 1M$2.50 / 1M$0.10 / 1M
Cache Write (1h)$2.00 / 1M$4.00 / 1M$0.10 / 1M
Cache Read$2.00 / 1M$0.20 / 1M$0.10 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M
Context
Max context200K1M1.1M
Max outputN/AN/AN/A
Capabilities
VisionYesYesYes
Function CallingYesYesYes
JSON ModeYesYesYes
StreamingYesYesYes
Catalogue
ProviderOpenAIAnthropicOpenAI
Categorychatchatchat
Charge typePay As You GoPay As You GoPay As You Go
Released———
Description
Summaryo4-mini-deep-research is a faster, lower-cost version of OpenAI's deep-research model, designed for complex, multi-step investigations. It automatically relies on web_search for information gathering, which always adds extra usage cost.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.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.