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 |
|---|---|---|---|
Qwen: Qwen3.8-27BQwen/Qwen3.8-27B | $0.2 | $0.05 | $2 |
Qwen: Qwen3.8-Flash-NextQwen/Qwen3.8-Flash-Next | $0.14 | $0.015 | $0.45 |
Z.AI: GLM-5.3-Flashzai-org/GLM-5.3-Flash | $0.07 | $0.015 | $0.24 |
Z.AI: GLM-5.3zai-org/GLM-5.3 | $1.1 | $0.23 | $3.5 |
DeepSeek: DeepSeek V4 Pro 0813deepseek-ai/DeepSeek-V4-Pro-0813 | $1.1 | $0.043 | $3.3 |
DeepSeek: DeepSeek V4.1 Flashdeepseek-ai/DeepSeek-V4.1-Flash | $0.05 | $0.003 | $0.3 |
Google: Gemma 4 31Bgoogle/gemma-4-31B-it | $0.09 | $0.05 | $0.34 |
Qwen: Qwen3.8-27B
Qwen/Qwen3.8-27BInput $/1M
$0.2
Cached $/1M
$0.05
Output $/1M
$2
Qwen: Qwen3.8-Flash-Next
Qwen/Qwen3.8-Flash-NextInput $/1M
$0.14
Cached $/1M
$0.015
Output $/1M
$0.45
Z.AI: GLM-5.3-Flash
zai-org/GLM-5.3-FlashInput $/1M
$0.07
Cached $/1M
$0.015
Output $/1M
$0.24
Z.AI: GLM-5.3
zai-org/GLM-5.3Input $/1M
$1.1
Cached $/1M
$0.23
Output $/1M
$3.5
DeepSeek: DeepSeek V4 Pro 0813
deepseek-ai/DeepSeek-V4-Pro-0813Input $/1M
$1.1
Cached $/1M
$0.043
Output $/1M
$3.3
DeepSeek: DeepSeek V4.1 Flash
deepseek-ai/DeepSeek-V4.1-FlashInput $/1M
$0.05
Cached $/1M
$0.003
Output $/1M
$0.3
Google: Gemma 4 31B
google/gemma-4-31B-itInput $/1M
$0.09
Cached $/1M
$0.05
Output $/1M
$0.34