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. Gemini 4 ArgonGoogleRemove
  2. Gemma 3 4BGoogleRemove
gemini-4-argon vs gemma-3-4b-it
AttributeGemini 4 Argongemini-4-argonGemma 3 4Bgemma-3-4b-it
Pricing
Input$2.00 / 1M$0.02 / 1M
Output$10.00 / 1M$0.04 / 1M
Cache Write (5m)$2.00 / 1M$0.02 / 1M
Cache Write (1h)$2.00 / 1M$0.02 / 1M
Cache Read$2.00 / 1M$0.02 / 1M
Web Search$0 / 1M$0 / 1M
Context
Max context1M131.1K
Max outputN/AN/A
Capabilities
VisionYesNo
Function CallingYesNo
JSON ModeYesNo
StreamingYesNo
Catalogue
ProviderGoogleGoogle
Categorychatchat
Charge typePay As You GoPay As You Go
Released——
Description
SummaryGemini 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.—