Add the RunInfra organization card
Browse files
README.md
CHANGED
|
@@ -1,10 +1,11 @@
|
|
| 1 |
-
-
|
| 2 |
-
title: README
|
| 3 |
-
emoji: 📉
|
| 4 |
-
colorFrom: pink
|
| 5 |
-
colorTo: gray
|
| 6 |
-
sdk: static
|
| 7 |
-
pinned: false
|
| 8 |
-
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Open-weight model APIs on capacity we optimize and operate ourselves, priced per token with no minimum and no subscription.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
+
RunInfra runs open-weight models as hosted APIs.
|
| 4 |
+
|
| 5 |
+
Every model we publish is one we have tuned for the way it is actually served,
|
| 6 |
+
rather than one generic runtime applied to everything. You call it with the
|
| 7 |
+
OpenAI chat completions shape, you pay per token, there is no minimum and no
|
| 8 |
+
subscription, and prefix caching is applied automatically on models that support
|
| 9 |
+
it at a reduced input rate.
|
| 10 |
+
|
| 11 |
+
Models, prices and per model behavior live at https://runinfra.ai.
|