Most reliable Gemma 4 31B API providers

34 providers host Gemma 4 31B. Most reliable over the last 30 minutes is SambaNova at 100.00% uptime.

What would Gemma 4 31B cost you?

OpenInference is 89% cheaper than Cerebras at this workload.
Input tokens / month150M
Output tokens / month30M

Projected monthly cost = (input price × 150M) + (output price × 30M). Drag the sliders to match your actual workload; the chart re-ranks live.

#HostContextInput $/MTokOutput $/MTokBlendedUptime 30mQuant
1SambaNova131k$0.38$1.15$0.51100.00%
2Cerebras131k$0.99$1.49$1.07100.00%fp16
3Cerebras131k$0.99$1.49$1.07100.00%fp16
4ModelRun262k$0.75$1.00$0.7999.98%fp4
5ModelRun262k$0.75$1.00$0.7999.97%fp4
6Friendli262k$0.14$0.40$0.1899.97%
7Friendli262k$0.14$0.40$0.1899.94%
8Novita262k$0.14$0.40$0.1899.92%bf16
9Parasail262k$0.15$0.40$0.1999.92%fp8
10Phala262k$0.15$0.46$0.2099.92%
11WandB262k$0.12$0.35$0.1699.91%bf16
12DeepInfra262k$0.09$0.34$0.1399.85%fp4
13Crusoe262k$0.14$0.40$0.1899.80%
14SambaNova131k$0.38$1.15$0.5199.74%
15OpenInference262k$0.07$0.35$0.1299.73%bf16
16Venice256k$0.12$0.36$0.1699.70%bf16
17Ambient66k$0.20$0.80$0.3099.48%
18Parasail262k$0.15$0.40$0.1999.46%fp8
19Venice256k$0.12$0.36$0.1699.37%bf16
20CoreWeave262k$0.10$0.34$0.1499.21%fp4
21Crusoe262k$0.14$0.40$0.1899.19%
22Chutes131k$0.12$0.37$0.1699.04%fp4
23Phala262k$0.15$0.46$0.2098.91%
24DeepInfra262k$0.09$0.34$0.1398.90%fp4
25OpenInference262k$0.08$0.35$0.1398.79%bf16
26Novita262k$0.14$0.40$0.1898.61%bf16
27Chutes131k$0.12$0.37$0.1698.54%fp4
28CoreWeave262k$0.10$0.34$0.1498.20%fp4
29Together262k$0.39$0.97$0.4996.09%
30Together262k$0.28$0.86$0.3895.05%
31Morph175k$0.14$0.40$0.1892.30%fp4
32AkashML131k$0.14$0.40$0.1891.10%fp8
33SiliconFlow262k$0.13$0.40$0.1790.70%fp8
34SiliconFlow262k$0.13$0.40$0.1789.45%fp8

Other rankings for Gemma 4 31B