Compare Google Gemini 4 Argon with other AI models

See how Gemini 4 Argon from Google compares with other AI models on price, context length and features.

Chat with Gemini 4 Argon
1 model
Gemini 4 ArgonGoogle

Google's flagship reasoning model, for complex software engineering, maths and science, autonomous multi-step agents and long decode. Raises the output ceiling to 1M tokens.

Overview

Overview for Gemini 4 Argon
MetricGemini 4 Argon
AuthorGoogle
TypeText
Context length1.05M tokens
Max output66K tokens
ReasoningYes
Input modalitiesTextImageAudioVideoFile
Output modalitiesText
ReleasedSep 30, 2026
Knowledge cutoffMarch 2026
Served byGoogle via Oxyy
APIOpenAI-compatible · Gemini/v1/chat/completions
  • Requests are sent to a healthy provider automatically; if one errors, the gateway retries against another serving the same model.

Pricing

Pricing for Gemini 4 Argon
MetricGemini 4 Argon
Input$0.800 /1M inputStandard $2.00
Output$4.00 /1M outputStandard $10.00
Cached input$0.040 /1M cachedStandard $0.100
Web search$5.60 /1K searchesStandard $14.00
Blended price (3:1 input:output)$1.60 /1M tokens
  • Includes the Launch Promo discount (60% off the standard price).

Performance

Performance for Gemini 4 Argon
MetricGemini 4 Argon
Latency (p50, 7 days)13.03 s
Time to first token (p50)8.21 s
Throughput (p50)75.9 tok/s
Tokens (7 days)3.9M
Visualize performance
Latency, daily median
Throughput, daily median
  • Gemini 4 Argon

Features

Features for Gemini 4 Argon
MetricGemini 4 Argon
Tool useYes
Structured outputsYes
Prompt cachingYes
StreamingYes
Web searchYes
Image inputYes

Activity

Activity for Gemini 4 Argon
MetricGemini 4 Argon
Tokens (30 days)8.1M tokens · last 30 days
Input tokens7.7M
Output tokens (excluding reasoning)466.0K
Reasoning tokens4.0K
Gemini 4 Argon8.1M tokens · last 30 days
  • Input 7.7M
  • Output (excl. reasoning) 466.0K
  • Reasoning 4.0K

Suggested models to compare

How this comparison is built

Prices are what Oxyy charges today; where a discount applies, the standard price is shown beside it. Context window, output limit, modalities and features come from the Oxyy model catalog. Latency, time to first token and throughput are medians measured on Oxyy traffic over the last 7 days (throughput from streaming requests only); a model with too little traffic shows a dash. Benchmark scores appear only with their source and date. Oxyy is an independent API gateway, not affiliated with the model vendors named on this page.