auto model pricing

src/chatlet/model_pricing.py

@@ -1,5 +1,41 @@
 MODEL_PRICING = {}
 
+MODEL_PRICING["meta-llama/llama-3.1-405b"] = {
+    "input_price_per_token": 0.000002,
+    "output_price_per_token": 0.000002,
+    "image_price_per_thousand": 0,
+}
+
+MODEL_PRICING["01-ai/yi-vision"] = {
+    "input_price_per_token": 0.00000019,
+    "output_price_per_token": 0.00000019,
+    "image_price_per_thousand": 0,
+}
+
+MODEL_PRICING["01-ai/yi-large-fc"] = {
+    "input_price_per_token": 0.000003,
+    "output_price_per_token": 0.000003,
+    "image_price_per_thousand": 0,
+}
+
+MODEL_PRICING["01-ai/yi-large-turbo"] = {
+    "input_price_per_token": 0.00000019,
+    "output_price_per_token": 0.00000019,
+    "image_price_per_thousand": 0,
+}
+
+MODEL_PRICING["nothingiisreal/mn-celeste-12b"] = {
+    "input_price_per_token": 0.0000015,
+    "output_price_per_token": 0.0000015,
+    "image_price_per_thousand": 0,
+}
+
+MODEL_PRICING["google/gemini-pro-1.5-exp"] = {
+    "input_price_per_token": 0.0000025,
+    "output_price_per_token": 0.0000075,
+    "image_price_per_thousand": 0.00265,
+}
+
 MODEL_PRICING["perplexity/llama-3.1-sonar-large-128k-online"] = {
     "input_price_per_token": 0.000001,
     "output_price_per_token": 0.000001,
@@ -132,6 +168,12 @@
     "image_price_per_thousand": 0,
 }
 
+MODEL_PRICING["01-ai/yi-large"] = {
+    "input_price_per_token": 0.000003,
+    "output_price_per_token": 0.000003,
+    "image_price_per_thousand": 0,
+}
+
 MODEL_PRICING["anthropic/claude-3.5-sonnet:beta"] = {
     "input_price_per_token": 0.000003,
     "output_price_per_token": 0.000015,
@@ -1068,3 +1110,11 @@
     "image_price_per_thousand": 0,
 }
 
+# ADD PRICING ABOVE THIS LINE, KEEP THIS LINE
+
+def get_model_pricing(model: str):
+    return MODEL_PRICING.get(model, {
+        "input_price_per_token": 0,
+        "output_price_per_token": 0,
+        "image_price_per_thousand": 0,
+    })

src/chatlet/test_chatlet.py

@@ -155,7 +155,7 @@ def test_url_context():
 
         rsps.add_passthru('https://')
 
-        response = chat("Write the title and exact content I provided above", urls=[url], temperature=0.0)
+        response = chat("Write the title and exact content I provided from text above", urls=[url], temperature=0.0)
 
         assert "Test Article" in response.lower() or "test article" in response.lower()
         assert "content" in response.lower()

src/chatlet/update_model_pricing.py

@@ -25,6 +25,15 @@ def main():
                 file.write(f'    "image_price_per_thousand": {pricing["image"]},\n')
                 file.write('}\n\n')
 
+            file.write("# ADD PRICING ABOVE THIS LINE, KEEP THIS LINE\n\n")
+            file.write("")
+            file.write("def get_model_pricing(model: str):\n")
+            file.write("    return MODEL_PRICING.get(model, {\n")
+            file.write("        \"input_price_per_token\": 0,\n")
+            file.write("        \"output_price_per_token\": 0,\n")
+            file.write("        \"image_price_per_thousand\": 0,\n")
+            file.write("    })\n")
+
         print("Model pricing information has been written to model_pricing.py")
     else:
         print(f"Failed to retrieve data. Status code: {response.status_code}")