Qudata
Z.ai logo

Launch GLM-4.7-Flash 30B-A3B

Fast GLM for code and agents
By Z.aiglm-4.7-flash30B parameters32K tokens of contextMIT

An efficient GLM with 30B total and 3B active parameters. Particularly strong at agentic coding, tools and mathematical reasoning.

GPU configurations for GLM-4.7-Flash 30B-A3B

1x RTX5090

Best value
~52 tok/s
$1.78per hour

1x A100

~60 tok/s
$2.50per hour

1x H100

~95 tok/s
$5.20per hour

1x H200

~108 tok/s
$8.26per hour
Pick a GPU
VRAM
—
RAM
—
Storage
—
CPU
—
Get started

GLM-4.7-Flash 30B-A3B benchmarks

as published by the model vendor
GLM-4.7-Flash 30B-A3B scores in public benchmarks
AIME 202591.6
GPQA75.2
SWE-bench Verified59.2

Other models in the private loop

FAQ

Frequently asked about renting GLM-4.7-Flash 30B-A3B

Which GPU does GLM-4.7-Flash 30B-A3B need?

The entry configuration is 1x RTX5090, which delivers around 52 tokens per second. For more parallel requests and headroom on speed, go with 1x H200.

How much does GLM-4.7-Flash 30B-A3B cost?

An hour of GLM-4.7-Flash 30B-A3B runs from $1.78 to $8.26 depending on the GPU configuration. Billing is hourly: you pay for server time, not for tokens.

How do I call GLM-4.7-Flash 30B-A3B from my code?

Once deployed you get an OpenAI-compatible endpoint: point any OpenAI client at the base_url you receive and pass glm-4.7-flash as the model name. Code written against the OpenAI API needs no changes.

Does the data stay private?

Yes. GLM-4.7-Flash 30B-A3B runs on a dedicated GPU server inside a private loop: requests and responses never reach the model vendor and are not used for training.

What context window and license does GLM-4.7-Flash 30B-A3B have?

GLM-4.7-Flash 30B-A3B holds 32K tokens of context per request and ships under the MIT license, so you can use it commercially on your own hosting terms.