All Models
Gemma 4 26B A4B IT
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...
Available Providers (9)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 OrcaRouter | google/gemma-4-26b-a4b-it | $0.06/MTok | $0.33/MTok | 262.1K | 32.8K | |
 OpenRouter | google/gemma-4-26b-a4b-it | $0.06/MTok | $0.33/MTok | 262.1K | 262.1K | |
 Deep Infra | google/gemma-4-26B-A4B-it | $0.07/MTok | $0.34/MTok | 262.1K | 32.8K | |
 Cloudflare Workers AI | @cf/google/gemma-4-26b-a4b-it | $0.10/MTok | $0.30/MTok | 256K | 16.4K | |
 SiliconFlow | google/gemma-4-26B-A4B-it | $0.12/MTok | $0.40/MTok | 262.1K | 262.1K | |
 Vercel AI Gateway | google/gemma-4-26b-a4b-it | $0.15/MTok | $0.60/MTok | 262.1K | 131.1K | |
 Scaleway | gemma-4-26b-a4b-it | $0.25/MTok | $0.50/MTok | 256K | 16.4K | |
 Google | gemma-4-26b-a4b-it | —/MTok | —/MTok | 262.1K | 32.8K | |
 Merge Gateway | google/gemma-4-26b-a4b-it | —/MTok | —/MTok | 262.1K | 32.8K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output