Host SiliconFlow raised Gemma 4 31B input pricing by 477%
Published 18 September 2026
Price move, per 1M tokens
- SiliconFlow · input↑ 477%$0.13 → $0.75
- SiliconFlow · output↑ 150%$0.40 → $1.00
- SiliconFlow · cache read— → $0.25
| host | rate | was | now | change |
|---|---|---|---|---|
| SiliconFlow | input | $0.13 | $0.75 | ↑ 477% |
| SiliconFlow | output | $0.40 | $1.00 | ↑ 150% |
| SiliconFlow | cache read | — | $0.25 | — |
input: ↑ 477%
If you buy
Budget for a much higher input cost on this model at this host, so re-check your usage and whether a lighter prompt or a different model tier fits before your next top-up.
The model
Gemma 4 31Bopen the model →
Open weights31.3B parameters262K context18 hosts
intelligence48th of 168 writing50th of 168 coding49th of 168 agents55th of 55
Gemma 4 is a 31.3-billion-parameter text, image and video model from Google with a permissive Apache licence and a quarter-million-token request limit. Its measured coding skill outpaces its general text score, though it struggles on agent tasks and its speed varies sharply by provider.
Source
Read on openrouter.ai · we published this on 18 September 2026.
read the original at openrouter.ai ↗