Z.ai: glm-5.3-flash

GLM-5.3-Flash was released by Z.ai in August 2026. The model is the first natively multimodal model in the GLM-5 series, with 320B total parameters, 18B active parameters, hybrid attention, and support for text, image, and video inputs.

Modetext → text

Input price$0.15 per M tokens

Output price$0.5 per M tokens

Context length

Weekly usage0 tokens

Listed at

Z.ai

Latency—

Throughput—

Upload rate—

Context length—

Max output—

Input price$0.15per 1M tokens

Output price$0.5per 1M tokens

Cache read$0.0045per 1M tokens

Cache write$0per 1M tokens

Performance

Avg TPS—

Avg latency—

Avg success rate—

TPS—

TTFT—

Latency—

Success rate—

Success rate

Speed

Code Example

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST

Supported Parameters

ParameterTypeDefaultDescription

Rate Limits

GroupRPMTPMRPD

RPM = requests per minute, TPM = tokens per minute, RPD = requests per day. Limits apply by token group.

Pricing

GroupBilling typePrice summary