OpenClaw supports Prompt Caching (https://docs.openclaw.ai/reference/prompt-caching). Gradient AI supports Prompt Caching (https://docs.digitalocean.com/products/gradient-ai-platform/details/features/#prompt-caching). How do I configure OpenClaw to use Gradient AI’s prompt caching?
This textbox defaults to using Markdown to format your answer.
You can type !ref in this text area to quickly search our full set of tutorials, documentation & marketplace offerings and insert the link!
Hi there,
I’m not entirely sure if there’s any specific configuration needed on the Gradient side.
Since prompt caching is supported by the Gradient AI platform, it may work automatically if the model/provider supports it, but the exact integration with OpenClaw might depend on how OpenClaw handles provider-specific features.
It might be worth reaching out to DigitalOcean support or the Gradient team to confirm whether any additional configuration is required when using OpenClaw:
Heya,
One thing I noticed though — there’s an open issue (#19279) on the OpenClaw repo where it looks like cache injection currently only activates when the provider is explicitly anthropic. So if you’re routing through Gradient AI’s endpoint, it might silently skip the caching even if the underlying model supports it. Not 100% sure how Gradient AI presents itself to OpenClaw in terms of provider detection.
Enabling cacheTrace in your OpenClaw diagnostics config should tell you pretty quickly if cache reads/writes are actually happening or not.
Hopefully someone with a working Gradient + OpenClaw setup can confirm.
Hope that this helps!
Become a contributor for community
Get paid to write technical tutorials and select a tech-focused charity to receive a matching donation.
DigitalOcean Documentation
Full documentation for every DigitalOcean product.
Resources for startups and AI-native businesses
The Wave has everything you need to know about building a business, from raising funding to marketing your product.
The developer cloud
Scale up as you grow — whether you're running one virtual machine or ten thousand.
Start building today
From GPU-powered inference and Kubernetes to managed databases and storage, get everything you need to build, scale, and deploy intelligent applications.
