Google: Gemma 4 26B A4B google
Bottom Line
Google: Gemma 4 26B A4B : $0.07/1M input, $0.23/1M output, 262K context. Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
API Pricing (per 1M tokens)
| Input | $0.07 |
| Output | $0.23 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.11 |
Specs & Performance
| Context Length | 262K |
| Max Output | 236K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | image, text, video → text |
More from google
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Google: Gemma 4 26B A4B API cost?
Google: Gemma 4 26B A4B costs $0.07/1M input tokens and $0.23/1M output tokens. Blended cost at a 3:1 ratio is about $0.11/1M tokens.
What is the context window of Google: Gemma 4 26B A4B ?
Google: Gemma 4 26B A4B supports a 262K token context window with up to 236K output tokens.
Is Google: Gemma 4 26B A4B worth it?
Google: Gemma 4 26B A4B has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.