Update README.md

README.md

@@ -3,9 +3,11 @@ license: apache-2.0
 ---
 # notdiamond-0001
 
-notdiamond-0001 automatically determines whether to send queries to GPT-3.5 or GPT-4, depending on which model is best-suited for your task. We've trained notdiamond-0001 on hundreds of thousands of data points from robust, cross-domain evaluation benchmarks. 
+notdiamond-0001 automatically determines whether to send queries to GPT-3.5 or GPT-4, depending on which model is best-suited for your task. We've trained notdiamond-0001 on hundreds of thousands of data points from robust, cross-domain evaluation benchmarks.
 
-The model is a classifier and will return either GPT-3.5 or GPT-4. You determine which version of each model you want to use and make the calls client-side with your own keys.
+The router model is free to use under the Apache 2.0 license. You can also access the model through our free [API](https://www.notdiamond.ai/notdiamond-0001).
+
+This router model is a classifier and will return either GPT-3.5 or GPT-4. You determine which version of each model you want to use and make the calls client-side with your own keys.
 
 To use notdiamond-0001, format your queries using the following prompt with your query appended at the end
 ``` python
@@ -31,6 +33,4 @@ You can then determine the model to call as follows
     model_id = logits.argmax().item()
     model_to_call = id2label[model_id]
 ```
-
-For more details on how you can integrate this into your techstack and have notdiamond-0001 help you reduce latency and cost, check out our [documentation](https://notdiamond.readme.io/reference/introduction-1). 
-You can also access the model through our free [API](https://www.notdiamond.ai/notdiamond-0001).
+For more details on how you can integrate this into your techstack and have notdiamond-0001 help you reduce latency and cost, check out our [documentation](https://notdiamond.readme.io/reference/introduction-1).