Merge pull request BerriAI#4087 from BerriAI/litellm_update_together_…

…ai_pricing Update together ai pricing
rick-github · Jun 9, 2024 · 90ae7f0 · 90ae7f0
2 parents 78dbb15 + f3a845e
commit 90ae7f0
Show file tree

Hide file tree

Showing 4 changed files with 41 additions and 30 deletions.
diff --git a/litellm/cost_calculator.py b/litellm/cost_calculator.py
@@ -42,16 +42,18 @@ def get_model_params_and_category(model_name) -> str:
         else:
             return model_name
         # Determine the category based on the number of parameters
-        if params_billion <= 3.0:
-            category = "together-ai-up-to-3b"
-        elif params_billion <= 7.0:
-            category = "together-ai-3.1b-7b"
-        elif params_billion <= 20.0:
-            category = "together-ai-7.1b-20b"
-        elif params_billion <= 40.0:
-            category = "together-ai-20.1b-40b"
-        elif params_billion <= 70.0:
-            category = "together-ai-40.1b-70b"
+        if params_billion <= 4.0:
+            category = "together-ai-up-to-4b"
+        elif params_billion <= 8.0:
+            category = "together-ai-4.1b-8b"
+        elif params_billion <= 21.0:
+            category = "together-ai-8.1b-21b"
+        elif params_billion <= 41.0:
+            category = "together-ai-21.1b-41b"
+        elif params_billion <= 80.0:
+            category = "together-ai-41.1b-80b"
+        elif params_billion <= 110.0:
+            category = "together-ai-81.1b-110b"
         if category is not None:
             return category
 

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
@@ -3009,32 +3009,37 @@
         "litellm_provider": "sagemaker",
         "mode": "chat"
     },
-    "together-ai-up-to-3b": {
+    "together-ai-up-to-4b": {
         "input_cost_per_token": 0.0000001,
         "output_cost_per_token": 0.0000001,
         "litellm_provider": "together_ai"
     },
-    "together-ai-3.1b-7b": {
+    "together-ai-4.1b-8b": {
         "input_cost_per_token": 0.0000002,
         "output_cost_per_token": 0.0000002,
         "litellm_provider": "together_ai"
     },
-    "together-ai-7.1b-20b": {
+    "together-ai-8.1b-21b": {
         "max_tokens": 1000,
-        "input_cost_per_token": 0.0000004,
-        "output_cost_per_token": 0.0000004,
+        "input_cost_per_token": 0.0000003,
+        "output_cost_per_token": 0.0000003,
         "litellm_provider": "together_ai"
     },
-    "together-ai-20.1b-40b": {
+    "together-ai-21.1b-41b": {
         "input_cost_per_token": 0.0000008,
         "output_cost_per_token": 0.0000008,
         "litellm_provider": "together_ai"
     },
-    "together-ai-40.1b-70b": {
+    "together-ai-41.1b-80b": {
         "input_cost_per_token": 0.0000009,
         "output_cost_per_token": 0.0000009,
         "litellm_provider": "together_ai"
     },
+    "together-ai-81.1b-110b": {
+        "input_cost_per_token": 0.0000018,
+        "output_cost_per_token": 0.0000018,
+        "litellm_provider": "together_ai"
+    },
     "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": {
         "input_cost_per_token": 0.0000006,
         "output_cost_per_token": 0.0000006,

diff --git a/litellm/tests/test_completion_cost.py b/litellm/tests/test_completion_cost.py
@@ -560,9 +560,8 @@ def test_together_ai_qwen_completion_cost():
         "custom_cost_per_second": None,
     }
 
-    try:
-        litellm.completion_cost(**input_kwargs)
-    except litellm.NotFoundError:
-        pass
-    except Exception:
-        pytest.fail("This should have returned a 'not found error'")
+    response = litellm.cost_calculator.get_model_params_and_category(
+        model_name="qwen/Qwen2-72B-Instruct"
+    )
+
+    assert response == "together-ai-41.1b-80b"
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
@@ -3009,32 +3009,37 @@
         "litellm_provider": "sagemaker",
         "mode": "chat"
     },
-    "together-ai-up-to-3b": {
+    "together-ai-up-to-4b": {
         "input_cost_per_token": 0.0000001,
         "output_cost_per_token": 0.0000001,
         "litellm_provider": "together_ai"
     },
-    "together-ai-3.1b-7b": {
+    "together-ai-4.1b-8b": {
         "input_cost_per_token": 0.0000002,
         "output_cost_per_token": 0.0000002,
         "litellm_provider": "together_ai"
     },
-    "together-ai-7.1b-20b": {
+    "together-ai-8.1b-21b": {
         "max_tokens": 1000,
-        "input_cost_per_token": 0.0000004,
-        "output_cost_per_token": 0.0000004,
+        "input_cost_per_token": 0.0000003,
+        "output_cost_per_token": 0.0000003,
         "litellm_provider": "together_ai"
     },
-    "together-ai-20.1b-40b": {
+    "together-ai-21.1b-41b": {
         "input_cost_per_token": 0.0000008,
         "output_cost_per_token": 0.0000008,
         "litellm_provider": "together_ai"
     },
-    "together-ai-40.1b-70b": {
+    "together-ai-41.1b-80b": {
         "input_cost_per_token": 0.0000009,
         "output_cost_per_token": 0.0000009,
         "litellm_provider": "together_ai"
     },
+    "together-ai-81.1b-110b": {
+        "input_cost_per_token": 0.0000018,
+        "output_cost_per_token": 0.0000018,
+        "litellm_provider": "together_ai"
+    },
     "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": {
         "input_cost_per_token": 0.0000006,
         "output_cost_per_token": 0.0000006,