DeepInfra Logo

DeepInfra

Serverless GPU platform for AI inference.

Available Models (5)

llama-3.1-70b-instruct

95
Context
128K
Input
$0.001/1k
Output
$0.001/1k

llama-3.1-8b-instruct

66
Context
128K
Input
$0.000/1k
Output
$0.000/1k

llama-3-70b-instruct

88
Context
8K
Cutoff
2023-12
Input
$0.001/1k
Output
$0.001/1k

llama-3-8b-instruct

58
Context
8K
Cutoff
2023-12
Input
$0.000/1k
Output
$0.000/1k

gemma-7b-it

59
Context
8K
Cutoff
2024-02
Input
$0.000/1k
Output
$0.000/1k