google
Google: Gemma 4 26B A4B
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...
Quality Score
100/100
price + capability + benchmarks
Input Price
$0.06
per 1M tokens
Output Price
$0.33
per 1M tokens
Context Window
262,144
tokens
- Model ID
- google/gemma-4-26b-a4b-it
- Vendor
- Tokenizer
- Gemma
- Input Modalities
- image, text, video
- Output Modalities
- text
- Max Output
- default
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
Strong choice for
Similar models
google
Google: Gemini 3.5 Flash
$1.50 in / $9.00 out
1,048,576 ctx
100
google
Google: Gemini 3.1 Flash Lite
$0.25 in / $1.50 out
1,048,576 ctx
100
google
Google: Gemma 4 26B A4B (free)
Free
262,144 ctx
100
google
Google: Gemma 4 31B (free)
Free
262,144 ctx
100
google
Google: Gemma 4 31B
$0.12 in / $0.36 out
262,144 ctx
100
google
Google: Gemini 3.1 Flash Lite Preview
$0.25 in / $1.50 out
1,048,576 ctx
100