Gemini 4 Argon vs Gemma 4 26B A4B
API pricing, context, and independently measured performance, side by side. Gemma 4 26B A4B starts 98% cheaper on input than Gemini 4 Argon at list prices.
Gemini 4 Argon
Google · released Oct 13, 2026
Best input$2.00 / MTok
Best output$10.00 / MTok
Context1.05M
Providers5
Fastest measured2.2s° TTFT · 105 tok/s
VisionToolsReasoningStructured outputPrompt caching
Gemma 4 26B A4B
Google · released Apr 3, 2026
Best input$0.042 / MTok
Best output$0.22 / MTok
Context262K
Providers13
Fastest measured0.28s° TTFT · 87 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Gemini 4 Argon |  Google | $2.00 | $10.00 | 2.2s° | 105° tok/s | — |
| Gemini 4 Argon |  Google AI Studio | $2.00 | $10.00 | — | — | — |
| Gemma 4 26B A4B |  Darkbloom | $0.042 | $0.22 | — | — | 5/5 |
| Gemma 4 26B A4B | DEDekaLLM | $0.06 | $0.33 | 1.7s° | 78° tok/s | — |
| Gemma 4 26B A4B |  DeepInfra | $0.07 | $0.34 | 0.67s° | 35° tok/s | 5/5 |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) · chat10k profile (~10K in / 200 out) · ° = measured via OpenRouter routing (adds a hop) · SMOKE: of 5 programmatic capability probes passed · methodology v1.1 — full details on each model page