Models & Pricing

Model	Model Key	Context Window	Input Modality	Tool Calling	Reasoning	Prompt Caching
DeepSeek-V4.1-Flash-1017	`deepseek-ai/deepseek-v4.1-flash-1017`	1 million tokens	Text, Image	Yes	Yes	Yes
GLM-5.3-Flash	`zai-org/glm-5.3-flash`	1 million tokens	Text, Image, Video	Yes	Yes	Yes

Prices are listed in USD per million tokens. Cached input is charged at the cache read rate instead of the regular input rate.

Deploy servers are located in the United States. Unlike other providers, we do not charge a premium for US-based inference.

Model	Input Tokens	Output Tokens	Cache Read Tokens
DeepSeek-V4.1-Flash-1017	$0.10 / 1M	$0.35 / 1M	$0.003 / 1M
Z.AI GLM-5.3-Flash	$0.05 / 1M	0.17 / 1M	$0.01 / 1M

⌘I