Serverless Inference

Serverless inference pricing for Pearl Inference Platform models, now available at special launch discounts. Pay only for the tokens you use.

Model	Input $/1M	Cached $/1M	Output $/1M
Z.AI: GLM-5.3-Flash`zai-org/GLM-5.3-Flash`	$0.07	$0.015	$0.24
Z.AI: GLM-5.3`zai-org/GLM-5.3`	$1.1	$0.23	$3.5
DeepSeek: DeepSeek V4 Pro 0813`deepseek-ai/DeepSeek-V4-Pro-0813`	$1.1	$0.043	$3.3
DeepSeek: DeepSeek V4 Flash 0731`deepseek-ai/DeepSeek-V4-Flash-0731`	$0.06	$0.016	$0.17

Z.AI: GLM-5.3-Flash

zai-org/GLM-5.3-Flash

Input $/1M

$0.07

Cached $/1M

$0.015

Output $/1M

$0.24

Z.AI: GLM-5.3

zai-org/GLM-5.3

Input $/1M

$1.1

Cached $/1M

$0.23

Output $/1M

$3.5

DeepSeek: DeepSeek V4 Pro 0813

deepseek-ai/DeepSeek-V4-Pro-0813

Input $/1M

$1.1

Cached $/1M

$0.043

Output $/1M

$3.3

DeepSeek: DeepSeek V4 Flash 0731

deepseek-ai/DeepSeek-V4-Flash-0731

Input $/1M

$0.06

Cached $/1M

$0.016

Output $/1M

$0.17