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. mai-ds-r1:freeNot in the catalogueRemove
  2. GPT-6 AstraOpenAIRemove
  3. Perceptron Mk1.5PerceptronRemove
  4. Gemini 4 ArgonGoogleRemove

4 is the maximum. Remove one to add another.

mai-ds-r1:free vs gpt-6-astra vs perceptron-mk1.5 vs gemini-4-argon
Attributemai-ds-r1:freeNot in the catalogueGPT-6 Astragpt-6-astraPerceptron Mk1.5perceptron-mk1.5Gemini 4 Argongemini-4-argon
Pricing
Input—$10.00 / 1M$0.15 / 1M$2.00 / 1M
Output—$50.00 / 1M$1.50 / 1M$10.00 / 1M
Cache Write (5m)—$10.00 / 1M$0.15 / 1M$2.00 / 1M
Cache Write (1h)—$10.00 / 1M$0.15 / 1M$2.00 / 1M
Cache Read—$10.00 / 1M$0.15 / 1M$2.00 / 1M
Web Search—$0 / 1M$0 / 1M$0 / 1M
Context
Max context—1M36.9K1M
Max output—N/AN/AN/A
Capabilities
Vision—YesNoYes
Function Calling—YesNoYes
JSON Mode—YesNoYes
Streaming—YesYesYes
Catalogue
Provider—OpenAIPerceptronGoogle
Category—chatchatchat
Charge type—Pay As You GoPay As You GoPay As You Go
Released——2026-09-25—
Description
Summary—GPT-6 Astra is OpenAI's flagship model for demanding end-to-end professional work, designed for advanced analysis, software engineering, deep research, scientific tasks, and document creation. It is particularly strong in long-horizon agentic workflows, including tasks that require sustained reasoning, tool orchestration, and computer and browser use, making it well suited for complex autonomous workflows and production-grade knowledge work.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.