Back to models
available
GLM-5.3 Flash (Inference.net)
inference-net/glm-5-3-flashPrices
- Input
$0.09 per 1M tokens
low- Input (cached read)
$0.02 per 1M tokens
low- Output
$0.28 per 1M tokens
low
Specifications
- Provider
- inference-net
- Context window
- 1,048,576
- Max output tokens
- 128,000
- Open weights
- yes
- Released
- 08/26/2026
- Retires
- no date announced
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 0.09 per 1M tokens, unchanged since 09/29/2026
- Output
- 0.28 per 1M tokens, unchanged since 09/29/2026
- Input (cached read)
- 0.02 per 1M tokens, unchanged since 09/29/2026