Gemma 4 26B A4B cut across 2 hosts, by up to 25% at NextBit (all rates)
Published 25 September 2026
Price move, per 1M tokens
- NextBit · input↓ 25%$0.0900 → $0.0675
- NextBit · output↓ 25%$0.300 → $0.225
- NextBit · cache read↓ 25%$0.0500 → $0.0375
- Makora · input↓ 20%$0.100 → $0.080
- Makora · output↓ 6%$0.34 → $0.32
- Makora · cache read↓ 6%$0.034 → $0.032
| host | rate | was | now | change |
|---|---|---|---|---|
| NextBit | input | $0.0900 | $0.0675 | ↓ 25% |
| NextBit | output | $0.300 | $0.225 | ↓ 25% |
| NextBit | cache read | $0.0500 | $0.0375 | ↓ 25% |
| Makora | input | $0.100 | $0.080 | ↓ 20% |
| Makora | output | $0.34 | $0.32 | ↓ 6% |
| Makora | cache read | $0.034 | $0.032 | ↓ 6% |
NextBit all rates: ↓ 25%Makora input: ↓ 20%
The model
Gemma 4 26B A4Bopen the model →
Open weights25.8B parameters262K context16 hosts
intelligence64th of 168 writing70th of 168 coding66th of 168
Google's Gemma is a mid-size downloadable language model with a permissive Apache licence. It uses an efficient mixture-of-experts design that activates only a few billion parameters per token, making it the efficiency pick of the mid-size class.
Source
Read from the hosts' own published rates · we published this on 25 September 2026.