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. Perceptron Mk1.5PerceptronRemove
  3. Gemini 3.5 TranscribeGoogleRemove
o4-mini-deep-research vs perceptron-mk1.5 vs gemini-3.5-transcribe
Attributeo4 Mini Deep Researcho4-mini-deep-researchPerceptron Mk1.5perceptron-mk1.5Gemini 3.5 Transcribegemini-3.5-transcribe
Pricing
Input$2.00 / 1M$0.15 / 1M$0 / 1M
Output$8.00 / 1M$1.50 / 1M$0 / 1M
Cache Write (5m)$2.00 / 1M$0.15 / 1MNot applicable
Cache Write (1h)$2.00 / 1M$0.15 / 1MNot applicable
Cache Read$2.00 / 1M$0.15 / 1MNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M
Context
Max context200K36.9K98.3K
Max outputN/AN/AN/A
Capabilities
VisionYesNoYes
Function CallingYesNoYes
JSON ModeYesNoNo
StreamingYesYesNo
Catalogue
ProviderOpenAIPerceptronGoogle
Categorychatchatvoice
Charge typePay As You GoPay As You GoPay As You Go
Released—2026-09-252026-09-25
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.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.Google Gemini 3.5 Transcribe speech-to-text. Billed per input and output token.