added sambanova cloud models (#7187)

Co-authored-by: Rodrigo Maldonado <[email protected]>
BerriAI · Dec 18, 2024 · d214d3c · d214d3c
1 parent 523beed
commit d214d3c
Showing 1 changed file with 70 additions and 0 deletions.
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
@@ -15,6 +15,76 @@
         "supports_prompt_caching": true,
         "supports_response_schema": true
     },
+    "sambanova/Meta-Llama-3.1-8B-Instruct": {
+        "max_tokens": 16000,
+        "max_input_tokens": 16000,
+        "max_output_tokens": 16000, 
+        "input_cost_per_token": 0.0000001,
+        "output_cost_per_token": 0.0000002,
+        "litellm_provider": "sambanova",
+        "supports_function_calling": true,
+        "mode": "chat"
+    },
+    "sambanova/Meta-Llama-3.1-70B-Instruct": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000, 
+        "input_cost_per_token": 0.0000006,
+        "output_cost_per_token": 0.0000012,
+        "litellm_provider": "sambanova",
+        "supports_function_calling": true,
+        "mode": "chat"
+    },
+    "sambanova/Meta-Llama-3.1-405B-Instruct": {
+        "max_tokens": 16000,
+        "max_input_tokens": 16000,
+        "max_output_tokens": 16000, 
+        "input_cost_per_token": 0.000005,
+        "output_cost_per_token": 0.000010,
+        "litellm_provider": "sambanova",
+        "supports_function_calling": true,
+        "mode": "chat"
+    },
+    "sambanova/Meta-Llama-3.2-1B-Instruct": {
+        "max_tokens": 16000,
+        "max_input_tokens": 16000,
+        "max_output_tokens": 16000, 
+        "input_cost_per_token": 0.0000004,
+        "output_cost_per_token": 0.0000008,
+        "litellm_provider": "sambanova",
+        "supports_function_calling": true,
+        "mode": "chat"
+    },
+    "sambanova/Meta-Llama-3.2-3B-Instruct": {
+        "max_tokens": 4000,
+        "max_input_tokens": 4000,
+        "max_output_tokens": 4000, 
+        "input_cost_per_token": 0.0000008,
+        "output_cost_per_token": 0.0000016,
+        "litellm_provider": "sambanova",
+        "supports_function_calling": true,
+        "mode": "chat"
+    },
+    "sambanova/Qwen2.5-Coder-32B-Instruct": {
+        "max_tokens": 8000,
+        "max_input_tokens": 8000,
+        "max_output_tokens": 8000, 
+        "input_cost_per_token": 0.0000015,
+        "output_cost_per_token": 0.000003,
+        "litellm_provider": "sambanova",
+        "supports_function_calling": true,
+        "mode": "chat"
+    },
+    "sambanova/Qwen2.5-72B-Instruct": {
+        "max_tokens": 8000,
+        "max_input_tokens": 8000,
+        "max_output_tokens": 8000, 
+        "input_cost_per_token": 0.000002,
+        "output_cost_per_token": 0.000004,
+        "litellm_provider": "sambanova",
+        "supports_function_calling": true,
+        "mode": "chat"
+    },
     "gpt-4": {
         "max_tokens": 4096, 
         "max_input_tokens": 8192,