Star OS
Models and pricing

Rate limits

Default request and token limits for the text generation models available through Star OS.

Rate limits are evaluated per minute. RPM is requests per minute; TPM is the combined total of input and output tokens per minute. Short bursts can also be limited at approximately RPM / 60 or TPM / 60, even when the one-minute total has not been reached.

The limits below are the default Star OS limits. Star OS may apply lower project-level limits, so the Console remains the source of truth for the limits available to your project.

Qwen

Model IDRPMTPM
qwen3.7-max6001,000,000
qwen3.7-plus15,0005,000,000
qwen3.6-plus15,0005,000,000
qwen-plus6001,500,000
qwen3.6-flash15,0005,000,000
qwen3.5-flash15,0005,000,000
qwen-flash6005,000,000
qwen3-coder-next6001,000,000

GLM

Model IDRPMTPM
glm-5.2Not publishedNot published
glm-5.2-fast-previewNot publishedNot published
glm-5.15001,000,000

Rate limits are not yet available for glm-5.2 or glm-5.2-fast-preview. Check the Console before planning production capacity for either model.

DeepSeek

Model IDRPMTPM
deepseek-v4-pro10,0001,200,000
deepseek-v4-flash10,0001,200,000
deepseek-v3.210,0001,200,000

If you receive a rate-limit response, smooth requests with a queue and retry with exponential backoff.

On this page