Gemma 4 26B A4B pricing
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... Below you will find 3 current rows with input and output dollars per million. Right now the lowest input is $0.100 and the lowest output is $0.300.
Pricing across providers
All figures are list prices per million tokens unless a column says otherwise. 3 offers are listed for Gemma 4 26B A4B. Best input in this view: Cloudflare.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
O Openrouter | $0.120 | $0.400 | — | — |
C Cloudflare | $0.100 | $0.300 | — | — |
S Scaleway | $0.250 | $0.500 | — | — |
Input vs output · per provider
Cost calculator
The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how Gemma 4 26B A4B cost scales with traffic.
Provider
0.012000¢ / req
0.020000¢ / req
Model specifications
Quick spec sheet for Gemma 4 26B A4B before you dive back into pricing. Reported under Google.
- Context window
- 262,144 tokens
- Max output
- 262,144 tokens
- Vision (images)
- Yes
- Tool / function calling
- Yes
- Streaming
- Yes
- Released
- Apr 2026
- Primary provider
- Model family
- N/A
Compare Gemma 4 26B A4B
These links open full side by side pages for Gemma 4 26B A4B. We picked pairs that people often shop together. 6 ready to open.
Locked
Compare with
Pick a model on both sides.
Popular Gemma 4 26B A4B comparisons
- Gemma 4 26B A4B vs Gemini 2.0 Flash
Compare pricing side by side
- Gemma 4 26B A4B vs Gemini 1.5 Pro
Compare pricing side by side
- Gemma 4 26B A4B vs Gemini 1.5 Flash
Compare pricing side by side
- Gemma 4 26B A4B vs Writer Palmyra X4 V1 0
Compare pricing side by side
- Gemma 4 26B A4B vs GPT-4o
Compare pricing side by side
- Gemma 4 26B A4B vs GPT-4o mini
Compare pricing side by side
Frequently asked questions
Answers pull from the same numbers you see on this page. The short model note from our index: 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...
Also from Google
Other models by Google with live pricing in our catalog.