Google: Gemma 4 31B
google/gemma-4-31b-it
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Modalities
In / Out Price
$0.09 / $0.34 per 1M
Context
262K
Released
Apr 2, 2026
Knowledge Cutoff
—
Providers
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
 DeepInfrafp4 | 262K | $0.09 | $0.34 | $0.05 | — | — | 100.00% |
 CoreWeavefp4 | 262K | $0.10 | $0.34 | $0.10 | — | — | 100.00% |
 Venicefp4 | 256K | $0.12 | $0.36 | $0.09 | — | — | 100.00% |
 Chutesfp4 | 131K | $0.12 | $0.37 | $0.012 | — | — | 80.00% |
 Crusoebf16 | 262K | $0.14 | $0.40 | $0.14 | — | — | 96.67% |
 Friendli | 262K | $0.14 | $0.40 | — | — | — | 100.00% |
 Novitabf16 | 262K | $0.14 | $0.40 | — | — | — | 63.33% |
 Parasailfp8 | 262K | $0.15 | $0.40 | $0.06 | — | — | 100.00% |
| DeepInfrafp8 | 262K | $0.20 | $0.40 | — | — | — | 100.00% |
 Io Net | 262K | $0.361 | $1.09 | $0.181 | — | — | 100.00% |
 SambaNova | 262K | $0.38 | $1.15 | — | — | — | 96.55% |
 ModelRunfp4 | 262K | $0.75 | $1 | $0.20 | — | — | 100.00% |
 SiliconFlowfp8 | 262K | $0.75 | $1 | $0.25 | — | — | 96.67% |