Modal API pricing

Hosted4 language models

As of Oct 19, 2026, Modal lists 4 language models through its API. Its cheapest language model is GLM 5.3 Flash at $0.45 input / $1.50 output per million tokens.

Language models (4)

Prices per million tokens.

Model	Input	Output	Cached input	Context
GLM 5.3 Flash zai-org/GLM-5.3-Flash	$0.45	$1.50	$0.09	1M
Kimi K3 moonshotai/Kimi-K3	$3.00	$15.00	$0.30	1.05M
Qwen3.8 2.4t A95B Qwen/Qwen3.8-2.4T-A95B	$2.00	$6.00	$0.25	1.01M
Inkling Nvfp4 thinkingmachines/Inkling-NVFP4	$1.20	$5.00	$0.27	1.05M

GLM 5.3 Flash
zai-org/GLM-5.3-Flash
Input
$0.45
Output
$1.50
Context
1M
Kimi K3
moonshotai/Kimi-K3
Input
$3.00
Output
$15.00
Context
1.05M
Qwen3.8 2.4t A95B
Qwen/Qwen3.8-2.4T-A95B
Input
$2.00
Output
$6.00
Context
1.01M
Inkling Nvfp4
thinkingmachines/Inkling-NVFP4
Input
$1.20
Output
$5.00
Context
1.05M

Prices in USD from LiteLLM and models.dev, checked daily; confirm on Modal's pricing page before you rely on a number.