Skip to content

armgit / cua

Public Imported from GitHub
0

Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.

Merge branch 'study-cua-provider' of https://github.com/trycua/cua into study-cua-provider

f-trycua73bbdc8666f7
diff --cc blog/cua-vlm-router.md
index 1f3da332c1,07b21a8a7f..44be55850e
--- a/blog/cua-vlm-router.md
+++ b/blog/cua-vlm-router.md
@@@ -2,10 -2,9 +2,10 @@@
If you've been building computer-use agents, you know the reality: every model provider has its own specification and deployment process. Anthropic has one API format, OpenAI another, Google something else entirely. Want to try a Hugging Face model? That's a completely different setup. Self-hosting? Even more complexity. Each provider requires learning their specific API, managing their credentials, and adapting your code to their particular requirements.
-Today we're launching the **Cua VLM Router**: a managed inference API that gives you unified access to multiple vision-language model providers through a single API key. We're starting with Anthropic's Claude models (Sonnet 4.5 and Haiku 4.5)—some of the most loved and widely-used computer-use models in the Cua ecosystem—with more providers coming soon.
+Today we're launching the **Cua VLM Router**: a managed inference API that gives you unified access to multiple vision-language model providers through a single API key. We're starting with Anthropic's Claude models (Sonnet 4.5 and Haiku 4.5)—some of the most loved and widely-used computer-use models in the Cua ecosystem - with more providers coming soon.
+
- ![Cua VLM Router Banner](https://github.com/user-attachments/assets/f8358acf-9194-46ee-b9e3-50cfcff5e489)
+ ![Cua VLM Router Banner](https://github.com/user-attachments/assets/1b978f62-2cae-4cf7-932a-55ac8c8f2e06)
## What You Get