GLM-5.3-Flash

z.ai
glm-5.3-flash
Released Aug 26, 2026
Chat
Providers
13
Context
1.0M
Input
$0.05/M
Output
$0.20/M
BAA-eligible on 3 of 13 providersPHI requires a signed BAA from Concentrate and HIPAA-enabled organization.

Z-AI's first natively multimodal GLM-5 model: image and PDF input on a 1M-token context at flash pricing. Reasoning is always on (low/high/max), with function calling and implicit prompt caching.

Novita

novita/glm-5.3-flashQuantfp8
Input
$0.15/M
Output
$0.50/M
Context
1.0M
Max out
131K
Cache read
$0.03/M
Cache write
$0.15/M
Thinking out
$0.50/M
FlexPriority / Fast

Runware

runware/glm-5.3-flashQuantUnspecified
Input
$0.15/M
Output
$0.50/M
Context
1.0M
Max out
131K
Cache read
$0.03/M
Cache write
$0.15/M
Thinking out
$0.50/M
FlexPriority / Fast

Azure Fireworks

azure-fw/glm-5.3-flashQuantUnspecified
Input
$0.19/M
Output
$0.63/M
Context
1.0M
Max out
131K
Cache read
$0.04/M
Cache write
$0.19/M
Thinking out
$0.63/M
FlexPriority / Fast

Fireworks AI

fireworks/glm-5.3-flashQuantUnspecified
Input
$0.15/M
Output
$0.50/M
Context
1.0M
Max out
131K
Cache read
$0.03/M
Cache write
$0.15/M
Thinking out
$0.50/M
Flex

Baseten

baseten/glm-5.3-flashQuantUnspecified
Input
$0.15/M
Output
$0.50/M
Context
1.0M
Max out
262K
Cache read
$0.03/M
Cache write
$0.15/M
Thinking out
$0.50/M
FlexPriority / Fast

Relace

relace/glm-5.3-flashQuantUnspecified
Input
$0.07/M
Output
$0.50/M
Context
1.0M
Max out
131K
Cache read
$0.01/M
Cache write
$0.07/M
Thinking out
$0.50/M
FlexPriority / Fast

Crusoe

crusoe/glm-5.3-flashQuantUnspecified
Input
$0.15/M
Output
$0.50/M
Context
1.0M
Max out
131K
Cache read
$0.03/M
Cache write
$0.15/M
Thinking out
$0.50/M
FlexPriority / Fast

Wafer

wafer/glm-5.3-flashQuantUnspecified
Input
$0.05/M
Output
$0.20/M
Context
1.0M
Max out
131K
Cache read
$0.03/M
Cache write
$0.05/M
Thinking out
$0.20/M
FlexPriority / Fast

Cloudflare

cloudflare/glm-5.3-flashQuantUnspecified
Input
$0.15/M
Output
$0.50/M
Context
1.0M
Max out
131K
Cache read
$0.03/M
Cache write
$0.15/M
Thinking out
$0.50/M
FlexPriority / Fast

DeepInfra

deepinfra/glm-5.3-flashQuantfp4
Input
$0.15/M
Output
$0.50/M
Context
1.0M
Max out
131K
Cache read
$0.03/M
Cache write
$0.15/M
Thinking out
$0.50/M
FlexPriority / Fast

Modal

modal/glm-5.3-flashQuantUnspecified
Input
$0.45/M
Output
$1.50/M
Context
1.0M
Max out
131K
Cache read
$0.09/M
Cache write
$0.45/M
Thinking out
$1.50/M
FlexPriority / Fast

Nebius

nebius/glm-5.3-flashQuantUnspecified
Input
$0.15/M
Output
$0.50/M
Context
1.0M
Max out
131K
Caching
Not offered
Thinking out
$0.50/M
FlexPriority / Fast

z.ai

zai/glm-5.3-flashQuantUnspecified
Input
$0.15/M
Output
$0.50/M
Context
1.0M
Max out
131K
Cache read
$0.03/M
Cache write
$0.15/M
Thinking out
$0.50/M
FlexPriority / Fast