Friendli
99.66%Context256K
Max output131.1K
p50 latency270 ms
Throughput79.5 t/s
Input price$0.14
Output price$0.4
google/gemma-4-31b-it
Gemma 4 31B is engineered to tackle the most demanding enterprise workloads and complex reasoning tasks. With an expansive 256K-token context window, the 31B model can effortlessly ingest entire codebases, and massive sets of images in a single prompt.
USD per one million tokens, using current provider data.
Last-hour p50 in milliseconds; lower is better.
Reported availability over the last 24 hours; not a contractual SLA.
Compare current pricing, performance, and privacy across every available provider.
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Friendli | 256K | 131.1K | 270 ms | 79.5 t/s | 99.662% | $0.14 | $0.4 | |
Gmicloud | 1M | 1M | — | — | 0.000% | $0.14 | $0.4 | |
Novita | 262.1K | 131.1K | 696 ms | 18.0 t/s | 99.997% | $0.14 | $0.4 | |
Parasail | 262.1K | 131.1K | 715 ms | 35.0 t/s | 100.000% | $0.14 | $0.4 | |
Togetherai | 256K | 131.1K | 1,503 ms | 3.0 t/s | 99.892% | $0.39 | $0.97 |
Available modalities and capabilities across inference providers.
google/gemma-4-31b-itMore options from the same creator or model category.