Cheapest Gemma 4 31B API providers
33 providers host Gemma 4 31B. The cheapest right now is OpenInference at $0.08/MTok input and $0.35/MTok output. Prices below are pulled live from each provider, updated daily.
What would Gemma 4 31B cost you?
OpenInference is 88% cheaper than Cerebras at this workload.
Input tokens / month150M
Output tokens / month30M
OpenInference
$22.50 /mo
DeepInfra
$23.70 /mo
DeepInfra
$23.70 /mo
CoreWeave
$25.20 /mo
CoreWeave
$25.20 /mo
WandB
$28.50 /mo
Venice
$28.80 /mo
Venice
$28.80 /mo
Chutes
$29.10 /mo
Chutes
$29.10 /mo
SiliconFlow
$31.50 /mo
SiliconFlow
$31.50 /mo
AkashML
$33.00 /mo
Morph
$33.00 /mo
Crusoe
$33.00 /mo
Friendli
$33.00 /mo
Novita
$33.00 /mo
Crusoe
$33.00 /mo
Friendli
$33.00 /mo
Novita
$33.00 /mo
Parasail
$34.50 /mo
Parasail
$34.50 /mo
Phala
$36.30 /mo
Phala
$36.30 /mo
Ambient
$54.00 /mo
Together
$67.80 /mo
Together
$67.80 /mo
SambaNova
$91.50 /mo
SambaNova
$91.50 /mo
ModelRun
$143 /mo
ModelRun
$143 /mo
Cerebras
$193 /mo
Cerebras
$193 /mo
Projected monthly cost = (input price × 150M) + (output price × 30M). Drag the sliders to match your actual workload; the chart re-ranks live.
| # | Host | Context | Input $/MTok | Output $/MTok | Blended | Uptime 30m | Quant |
|---|---|---|---|---|---|---|---|
| 1 | OpenInference | 262k | $0.08 | $0.35 | $0.13 | 98.79% | bf16 |
| 2 | DeepInfra | 262k | $0.09 | $0.34 | $0.13 | 98.90% | fp4 |
| 3 | DeepInfra | 262k | $0.09 | $0.34 | $0.13 | 99.85% | fp4 |
| 4 | CoreWeave | 262k | $0.10 | $0.34 | $0.14 | 98.20% | fp4 |
| 5 | CoreWeave | 262k | $0.10 | $0.34 | $0.14 | 99.21% | fp4 |
| 6 | WandB | 262k | $0.12 | $0.35 | $0.16 | 99.91% | bf16 |
| 7 | Venice | 256k | $0.12 | $0.36 | $0.16 | 99.70% | bf16 |
| 8 | Venice | 256k | $0.12 | $0.36 | $0.16 | 99.37% | bf16 |
| 9 | Chutes | 131k | $0.12 | $0.37 | $0.16 | 99.04% | fp4 |
| 10 | Chutes | 131k | $0.12 | $0.37 | $0.16 | 98.54% | fp4 |
| 11 | SiliconFlow | 262k | $0.13 | $0.40 | $0.17 | 89.45% | fp8 |
| 12 | SiliconFlow | 262k | $0.13 | $0.40 | $0.17 | 90.70% | fp8 |
| 13 | AkashML | 131k | $0.14 | $0.40 | $0.18 | 91.10% | fp8 |
| 14 | Morph | 175k | $0.14 | $0.40 | $0.18 | 92.30% | fp4 |
| 15 | Crusoe | 262k | $0.14 | $0.40 | $0.18 | 99.19% | — |
| 16 | Friendli | 262k | $0.14 | $0.40 | $0.18 | 99.97% | — |
| 17 | Novita | 262k | $0.14 | $0.40 | $0.18 | 98.61% | bf16 |
| 18 | Crusoe | 262k | $0.14 | $0.40 | $0.18 | 99.80% | — |
| 19 | Friendli | 262k | $0.14 | $0.40 | $0.18 | 99.94% | — |
| 20 | Novita | 262k | $0.14 | $0.40 | $0.18 | 99.92% | bf16 |
| 21 | Parasail | 262k | $0.15 | $0.40 | $0.19 | 99.46% | fp8 |
| 22 | Parasail | 262k | $0.15 | $0.40 | $0.19 | 99.92% | fp8 |
| 23 | Phala | 262k | $0.15 | $0.46 | $0.20 | 99.92% | — |
| 24 | Phala | 262k | $0.15 | $0.46 | $0.20 | 98.91% | — |
| 25 | Ambient | 66k | $0.20 | $0.80 | $0.30 | 99.48% | — |
| 26 | Together | 262k | $0.28 | $0.86 | $0.38 | 95.05% | — |
| 27 | Together | 262k | $0.28 | $0.86 | $0.38 | 100.00% | — |
| 28 | SambaNova | 131k | $0.38 | $1.15 | $0.51 | 100.00% | — |
| 29 | SambaNova | 131k | $0.38 | $1.15 | $0.51 | 99.74% | — |
| 30 | ModelRun | 262k | $0.75 | $1.00 | $0.79 | 99.98% | fp4 |
| 31 | ModelRun | 262k | $0.75 | $1.00 | $0.79 | 99.97% | fp4 |
| 32 | Cerebras | 131k | $0.99 | $1.49 | $1.07 | 100.00% | fp16 |
| 33 | Cerebras | 131k | $0.99 | $1.49 | $1.07 | 100.00% | fp16 |