# Google: Gemma 4 31B — price and measured latency by host

Updated July 25, 2026. Served by 18 providers; 7 of them measured here.

Latency and uptime are measured by llmlatency.dev probes. Prices are published by the providers and read via OpenRouter on 2026-07-25 — not measured.

| Host | Input $/M | Output $/M | Context | Fastest p50 | From | Uptime |
| --- | --- | --- | --- | --- | --- | --- |
| deepinfra | $0.120 | $0.370 | 262,144 | 226 ms | us-central | 99.9% |
| siliconflow | $0.130 | $0.400 | 262,144 | 82 ms | us-central | 100% |
| novita | $0.140 | $0.400 | 262,144 | 71 ms | us-central | 100% |
| friendli | $0.140 | $0.400 | 262,144 | 185 ms | us-central | 100% |
| together | $0.280 | $0.860 | 262,144 | 111 ms | us-central | 100% |
| sambanova | $0.380 | $1.150 | 131,072 | 24 ms | ap-tokyo | 99.8% |
| cerebras | $0.990 | $1.490 | 131,072 | 69 ms | us-central | 100% |

Source: https://llmlatency.dev/model/google-gemma-4-31b-it · CC BY 4.0