Gemma 4 31B pricing across providers
Across tracked provider offerings, input runs $0.100–$0.750 per million tokens and output $0.250–$1.15 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Consensus Protocol at $0.013 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 11 of 15 offerings publish a cache-read rate; 11 of 15 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to Gemma 4 31B
Is this the right model for your workload? Compare open-weight picks and providers for your use case →
Daily price history
Loading price history…
Daily snapshots are retained for up to 90 days; history begins with the first recorded snapshot.
Provider offerings for Gemma 4 31B
Ranked by effective cost at a typical agentic mix. Quantized and tier variants stay separate rows.
| Provider | Quant | Input $/M | Output $/M | Cache $/M | Blended $/M | Uptime (30m) |
|---|---|---|---|---|---|---|
| Consensusprotocol | — | $0.100 | $0.250 | $0.010 | $0.013 | — |
| Runware | — | $0.102 | $0.297 | $0.012 | $0.016 | — |
| Chutes | fp4 | $0.120 | $0.370 | $0.012 | $0.016 | 100.00% |
| Dekallm | unknown | $0.140 | $0.400 | $0.050 | $0.054 | 100.00% |
| Parasail | fp8 | $0.150 | $0.400 | $0.060 | $0.064 | 100.00% |
| Venice | fp4 | $0.120 | $0.360 | $0.090 | $0.092 | 100.00% |
| Coreweave | fp4 | $0.100 | $0.340 | $0.100 | $0.101 | 100.00% |
| Crusoe | bf16 | $0.140 | $0.400 | $0.140 | $0.141 | 96.67% |
| Friendli | unknown | $0.140 | $0.400 | — | $0.141 | 100.00% |
| Novita | bf16 | $0.140 | $0.400 | — | $0.141 | 100.00% |
| Io Net promo | unknown | $0.361 | $1.09 | $0.181 | $0.190 | 100.00% |
| DeepInfra | — | $0.200 | $0.400 | — | $0.201 | — |
| Modelrun | fp4 | $0.750 | $1.00 | $0.200 | $0.218 | 100.00% |
| SiliconFlow | fp8 | $0.750 | $1.00 | $0.250 | $0.266 | 93.33% |
| SambaNova | — | $0.380 | $1.15 | — | $0.384 | — |
Provider-offering pricing refreshed 2026-10-29. Uptime is the 30-minute endpoint metric where a provider publishes it. Verify rates on the provider's official pricing page before committing spend.