Best value GLM 4.7 API providers

30 providers host GLM 4.7. Best value (SWE-bench score divided by blended cost) is DekaLLM at $0.61/MTok blended.

What would GLM 4.7 cost you?

DekaLLM is 74% 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
1DekaLLM203k$0.38$1.74$0.61—fp4
2Chutes203k$0.39$1.75$0.62100.00%bf16
3DeepInfra203k$0.40$1.75$0.63100.00%fp4
4DeepInfra203k$0.40$1.75$0.6399.65%fp4
5Venice198k$0.40$1.93$0.6696.27%fp4
6Nebius203k$0.40$2.00$0.6793.90%fp8
7StreamLake200k$0.48$1.76$0.6991.85%fp8
8StreamLake200k$0.48$1.76$0.6992.04%fp8
9Parasail203k$0.45$2.10$0.7299.10%fp8
10SiliconFlow205k$0.45$2.20$0.74—fp8
11AtlasCloud203k$0.52$1.85$0.7494.48%fp8
12AtlasCloud203k$0.52$1.85$0.7495.05%fp8
13Novita205k$0.54$1.98$0.7895.21%fp8
14Novita205k$0.54$1.98$0.7892.00%fp8
15Fireworks AI—$0.60$2.20$0.87——
16Z Ai203k$0.60$2.20$0.8786.30%fp4
17Google AI Studio200k$0.60$2.20$0.87100.00%—
18Z Ai203k$0.60$2.20$0.8776.99%fp4
19Google AI Studio200k$0.60$2.20$0.87100.00%—
20Venice198k$0.55$2.65$0.90100.00%fp4
21Mancer 2131k$0.65$2.50$0.96100.00%fp4
22Mancer 2131k$0.70$2.50$1.00—fp4
23Amazon Bedrock—$0.72$2.64$1.04——
24Amazon Bedrock—$0.72$2.64$1.04——
25Amazon Bedrock—$0.72$2.64$1.04——
26Amazon Bedrock—$0.72$2.64$1.04——
27Amazon Bedrock—$0.72$2.64$1.04——
28Phala131k$0.85$3.30$1.26——
29Amazon Bedrock—$0.93$3.41$1.34——
30Cerebras131k$2.25$2.75$2.33100.00%fp16

Other rankings for GLM 4.7