Most reliable Gemma 4 31B API providers

36 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
3SiliconFlow262k$0.75$1.00$0.79100.00%fp8
4Cerebras131k$0.99$1.49$1.07100.00%fp16
5ModelRun262k$0.75$1.00$0.7999.98%fp4
6ModelRun262k$0.75$1.00$0.7999.97%fp4
7Friendli262k$0.14$0.40$0.1899.97%
8Friendli262k$0.14$0.40$0.1899.94%
9Novita262k$0.14$0.40$0.1899.92%bf16
10Parasail262k$0.15$0.40$0.1999.92%fp8
11Phala262k$0.15$0.46$0.2099.92%
12WandB262k$0.12$0.35$0.1699.91%bf16
13DeepInfra262k$0.09$0.34$0.1399.85%fp4
14Crusoe262k$0.14$0.40$0.1899.80%
15SambaNova131k$0.38$1.15$0.5199.74%
16OpenInference262k$0.07$0.35$0.1299.73%bf16
17Venice256k$0.12$0.36$0.1699.70%bf16
18Crusoe262k$0.14$0.40$0.1899.64%bf16
19Ambient66k$0.20$0.80$0.3099.48%
20Parasail262k$0.15$0.40$0.1999.46%fp8
21Venice256k$0.12$0.36$0.1699.37%bf16
22CoreWeave262k$0.10$0.34$0.1499.21%fp4
23Crusoe262k$0.14$0.40$0.1899.19%
24Venice256k$0.12$0.36$0.1699.10%fp4
25Chutes131k$0.12$0.37$0.1699.04%fp4
26Phala262k$0.15$0.46$0.2098.91%
27DeepInfra262k$0.09$0.34$0.1398.90%fp4
28OpenInference262k$0.08$0.35$0.1398.79%bf16
29Novita262k$0.14$0.40$0.1898.61%bf16
30Chutes131k$0.12$0.37$0.1698.54%fp4
31CoreWeave262k$0.10$0.34$0.1498.20%fp4
32Together262k$0.39$0.97$0.4996.09%
33Together262k$0.28$0.86$0.3895.05%
34Morph175k$0.14$0.40$0.1892.30%fp4
35AkashML131k$0.14$0.40$0.1891.10%fp8
36SiliconFlow262k$0.13$0.40$0.1789.45%fp8

Other rankings for Gemma 4 31B