Update models.py

models.py

@@ -49,7 +49,7 @@ class OpenAIModelGPT4(BaseTCOModel):
 
     def __init__(self):
         self.set_name("(SaaS) OpenAI GPT4")
-        self.latency = "15s" #Default value for GPT4
+        self.set_latency("15s") #Default value for GPT4
         super().__init__()
 
     def render(self):
@@ -65,16 +65,16 @@ class OpenAIModelGPT4(BaseTCOModel):
         self.context_length = gr.Dropdown(["8K", "32K"], value="8K", interactive=True,
                                           label="Context size",
                                           visible=False, info="Number of tokens the model considers when processing text")
-        self.input_tokens_cost_per_second = gr.Number(0.03, visible=False,
+        self.input_tokens_cost_per_token = gr.Number(0.03, visible=False,
                                            label="($) Price/1K input prompt tokens",
                                            interactive=False
                                            )
-        self.output_tokens_cost_per_second = gr.Number(0.06, visible=False,
+        self.output_tokens_cost_per_token = gr.Number(0.06, visible=False,
                                            label="($) Price/1K output prompt tokens",
                                            interactive=False
                                            )
         self.info = gr.Markdown("The cost per input and output tokens values are from OpenAI's [pricing web page](https://openai.com/pricing)", interactive=False, visible=False)
-        self.context_length.change(define_cost_per_token, inputs=self.context_length, outputs=[self.input_tokens_cost_per_second, self.output_tokens_cost_per_second])
+        self.context_length.change(define_cost_per_token, inputs=self.context_length, outputs=[self.input_tokens_cost_per_token, self.output_tokens_cost_per_token])
         
         self.labor = gr.Number(0, visible=False, 
                                 label="($) Labor cost per month", 
@@ -82,9 +82,9 @@ class OpenAIModelGPT4(BaseTCOModel):
                                 interactive=True
                                 )
 
-    def compute_cost_per_token(self, input_tokens_cost_per_second, output_tokens_cost_per_second, labor):
-        cost_per_input_token = (input_tokens_cost_per_second / 1000) 
-        cost_per_output_token = (output_tokens_cost_per_second / 1000)
+    def compute_cost_per_token(self, input_tokens_cost_per_token, output_tokens_cost_per_token, labor):
+        cost_per_input_token = (input_tokens_cost_per_token / 1000) 
+        cost_per_output_token = (output_tokens_cost_per_token / 1000)
 
         return cost_per_input_token, cost_per_output_token, labor
 
@@ -92,7 +92,7 @@ class OpenAIModelGPT3_5(BaseTCOModel):
 
     def __init__(self):
         self.set_name("(SaaS) OpenAI GPT3.5 Turbo")
-        self.latency = "5s" #Default value for GPT3.5 Turbo
+        self.set_latency("5s") #Default value for GPT3.5 Turbo
         super().__init__()
 
     def render(self):
@@ -108,16 +108,16 @@ class OpenAIModelGPT3_5(BaseTCOModel):
         self.context_length = gr.Dropdown(choices=["4K", "16K"], value="4K", interactive=True,
                                           label="Context size",
                                           visible=False, info="Number of tokens the model considers when processing text")
-        self.input_tokens_cost_per_second = gr.Number(0.0015, visible=False,
+        self.input_tokens_cost_per_token = gr.Number(0.0015, visible=False,
                                            label="($) Price/1K input prompt tokens",
                                            interactive=False
                                            )
-        self.output_tokens_cost_per_second = gr.Number(0.002, visible=False,
+        self.output_tokens_cost_per_token = gr.Number(0.002, visible=False,
                                            label="($) Price/1K output prompt tokens",
                                            interactive=False
                                            )
         self.info = gr.Markdown("The cost per input and output tokens values are from OpenAI's [pricing web page](https://openai.com/pricing)", interactive=False, visible=False)
-        self.context_length.change(define_cost_per_token, inputs=self.context_length, outputs=[self.input_tokens_cost_per_second, self.output_tokens_cost_per_second])
+        self.context_length.change(define_cost_per_token, inputs=self.context_length, outputs=[self.input_tokens_cost_per_token, self.output_tokens_cost_per_token])
         
         self.labor = gr.Number(0, visible=False, 
                                 label="($) Labor cost per month", 
@@ -125,9 +125,9 @@ class OpenAIModelGPT3_5(BaseTCOModel):
                                 interactive=True
                                 )
 
-    def compute_cost_per_token(self, input_tokens_cost_per_second, output_tokens_cost_per_second, labor):
-        cost_per_input_token = (input_tokens_cost_per_second / 1000) 
-        cost_per_output_token = (output_tokens_cost_per_second / 1000)
+    def compute_cost_per_token(self, input_tokens_cost_per_token, output_tokens_cost_per_token, labor):
+        cost_per_input_token = (input_tokens_cost_per_token / 1000) 
+        cost_per_output_token = (output_tokens_cost_per_token / 1000)
 
         return cost_per_input_token, cost_per_output_token, labor
 
@@ -147,11 +147,11 @@ class OpenSourceLlama2Model(BaseTCOModel):
         self.vm_cost_per_hour = gr.Number(4.42, label="Instance cost ($) per hour",
                                       interactive=False, visible=False)
         self.info_vm = gr.Markdown("This price above is from [CoreWeave's pricing web page](https://www.coreweave.com/gpu-cloud-pricing)", interactive=False, visible=False)
-        self.input_tokens_cost_per_second = gr.Number(0.00052, visible=False,
+        self.input_tokens_cost_per_token = gr.Number(0.00052, visible=False,
                                            label="($) Price/1K input prompt tokens",
                                            interactive=False
                                            )
-        self.output_tokens_cost_per_second = gr.Number(0.06656, visible=False,
+        self.output_tokens_cost_per_token = gr.Number(0.06656, visible=False,
                                            label="($) Price/1K output prompt tokens",
                                            interactive=False
                                            )
@@ -167,9 +167,9 @@ class OpenSourceLlama2Model(BaseTCOModel):
                                 interactive=True
                                 )
 
-    def compute_cost_per_token(self, input_tokens_cost_per_second, output_tokens_cost_per_second, labor):
-        cost_per_input_token = (input_tokens_cost_per_second / 1000) 
-        cost_per_output_token = (output_tokens_cost_per_second / 1000)
+    def compute_cost_per_token(self, input_tokens_cost_per_token, output_tokens_cost_per_token, labor):
+        cost_per_input_token = (input_tokens_cost_per_token / 1000) 
+        cost_per_output_token = (output_tokens_cost_per_token / 1000)
         return cost_per_input_token,  cost_per_output_token, labor
 
 class CohereModel(BaseTCOModel):
@@ -190,26 +190,26 @@ class CohereModel(BaseTCOModel):
         self.model = gr.Dropdown(["Default", "Custom"], value="Default",
                                  label="Model",
                                  interactive=True, visible=False)
-        self.input_tokens_cost_per_second = gr.Number(0.015, visible=False,
+        self.input_tokens_cost_per_token = gr.Number(0.015, visible=False,
                                            label="($) Price/1K input prompt tokens",
                                            interactive=False
                                            )
-        self.output_tokens_cost_per_second = gr.Number(0.015, visible=False,
+        self.output_tokens_cost_per_token = gr.Number(0.015, visible=False,
                                            label="($) Price/1K output prompt tokens",
                                            interactive=False
                                            )
         self.info = gr.Markdown("The cost per input and output tokens value is from Cohere's [pricing web page](https://cohere.com/pricing?utm_term=&utm_campaign=Cohere+Brand+%26+Industry+Terms&utm_source=adwords&utm_medium=ppc&hsa_acc=4946693046&hsa_cam=20368816223&hsa_grp=154209120409&hsa_ad=666081801359&hsa_src=g&hsa_tgt=dsa-19959388920&hsa_kw=&hsa_mt=&hsa_net=adwords&hsa_ver=3&gad=1&gclid=CjwKCAjww7KmBhAyEiwA5-PUSlyO7pq0zxeVrhViXMd8WuILW6uY-cfP1-SVuUfs-leUAz14xHlOHxoCmfkQAvD_BwE)", interactive=False, visible=False)
-        self.model.change(on_model_change, inputs=self.model, outputs=[self.input_tokens_cost_per_second, self.output_tokens_cost_per_second])
+        self.model.change(on_model_change, inputs=self.model, outputs=[self.input_tokens_cost_per_token, self.output_tokens_cost_per_token])
         self.labor = gr.Number(0, visible=False, 
                                 label="($) Labor cost per month", 
                                 info="This is an estimate of the labor cost of the AI engineer in charge of deploying the model",
                                 interactive=True
                                 )
 
-    def compute_cost_per_token(self, input_tokens_cost_per_second, output_tokens_cost_per_second, labor):
+    def compute_cost_per_token(self, input_tokens_cost_per_token, output_tokens_cost_per_token, labor):
         
-        cost_per_input_token = input_tokens_cost_per_second / 1000
-        cost_per_output_token = output_tokens_cost_per_second / 1000
+        cost_per_input_token = input_tokens_cost_per_token / 1000
+        cost_per_output_token = output_tokens_cost_per_token / 1000
 
         return cost_per_input_token, cost_per_output_token, labor