RentGPU RentGPU
Trouver un GPU →
by Zhipu AI

Z.ai: GLM 4.7 Flash.

text open weights 203K ctx
Cheapest input
$0.06/M
on Zhipu BigModel
Cheapest output
$0.4/M
on Zhipu BigModel
Fastest
41 tok/s
on OpenRouter
Hosted equiv.
~$0.14/hr
@ 100 tok/s on Zhipu BigModel

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
Zhipu BigModel api direct $0.06 $0.4 Launch ↗
DeepInfra hosted inference $0.06 $0.4 Launch ↗
OpenRouter api aggregator $0.06 $0.4 Launch ↗
Performance

Speed across providers.

Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.

Provider Tokens/sec TTFT Total
OpenRouter 41.0 — 12197 ms
FAQ

Frequently asked.

How do I run Z.ai: GLM 4.7 Flash?
Z.ai: GLM 4.7 Flash is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Z.ai: GLM 4.7 Flash?
Z.ai: GLM 4.7 Flash is available via Zhipu BigModel, DeepInfra, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Z.ai: GLM 4.7 Flash?
API pricing starts at $0.06/M input tokens and $0.4/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Z.ai: GLM 4.7 Flash open-source or proprietary?
Z.ai: GLM 4.7 Flash is open-weight under the license. You can download and self-host it.