From 0eedf7c4477cdd2fcba5d89313aea3105b04deb6 Mon Sep 17 00:00:00 2001
From: Krrish Dholakia <krrishdholakia@gmail.com>
Date: Sat, 9 Aug 2025 16:31:41 -0700
Subject: [PATCH] build: update local model cost map

---
 ...odel_prices_and_context_window_backup.json | 124 ++++++++++++++++++
 1 file changed, 124 insertions(+)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 1bd7b460d6..7cfc9dea5a 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -17098,6 +17098,130 @@
         "litellm_provider": "snowflake",
         "mode": "chat"
     },
+    "gradient_ai/anthropic-claude-3.7-sonnet": {
+        "input_cost_per_token": 3e-06,
+        "output_cost_per_token": 15e-06,
+        "litellm_provider": "gradient_ai",
+        "mode": "chat",
+        "max_tokens": 1024,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supported_modalities": ["text"],
+        "supports_tool_choice": false
+    },
+    "gradient_ai/anthropic-claude-3.5-sonnet": {
+        "input_cost_per_token": 3e-06,
+        "output_cost_per_token": 15e-06,
+        "litellm_provider": "gradient_ai",
+        "mode": "chat",
+        "max_tokens": 1024,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supported_modalities": ["text"],
+        "supports_tool_choice": false
+    },
+    "gradient_ai/anthropic-claude-3.5-haiku": {
+        "input_cost_per_token": 8e-07,
+        "output_cost_per_token": 4e-06,
+        "litellm_provider": "gradient_ai",
+        "mode": "chat",
+        "max_tokens": 1024,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supported_modalities": ["text"],
+        "supports_tool_choice": false
+    },
+    "gradient_ai/anthropic-claude-3-opus": {
+        "input_cost_per_token": 15e-06,
+        "output_cost_per_token": 75e-06,
+        "litellm_provider": "gradient_ai",
+        "mode": "chat",
+        "max_tokens": 1024,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supported_modalities": ["text"],
+        "supports_tool_choice": false
+    },
+    "gradient_ai/deepseek-r1-distill-llama-70b": {
+        "input_cost_per_token": 99e-08,
+        "output_cost_per_token": 99e-08,
+        "litellm_provider": "gradient_ai",
+        "mode": "chat",
+        "max_tokens": 8000,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supported_modalities": ["text"],
+        "supports_tool_choice": false
+    },
+    "gradient_ai/llama3.3-70b-instruct": {
+        "input_cost_per_token": 65e-08,
+        "output_cost_per_token": 65e-08,
+        "litellm_provider": "gradient_ai",
+        "mode": "chat",
+        "max_tokens": 2048,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supported_modalities": ["text"],
+        "supports_tool_choice": false
+    },
+    "gradient_ai/llama3-8b-instruct": {
+        "input_cost_per_token": 2e-07,
+        "output_cost_per_token": 2e-07,
+        "litellm_provider": "gradient_ai",
+        "mode": "chat",
+        "max_tokens": 512,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supported_modalities": ["text"],
+        "supports_tool_choice": false
+    },
+    "gradient_ai/mistral-nemo-instruct-2407": {
+        "input_cost_per_token": 3e-07,
+        "output_cost_per_token": 3e-07,
+        "litellm_provider": "gradient_ai",
+        "mode": "chat",
+        "max_tokens": 512,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supported_modalities": ["text"],
+        "supports_tool_choice": false
+    },
+    "gradient_ai/openai-o3": {
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 8e-06,
+        "litellm_provider": "gradient_ai",
+        "mode": "chat",
+        "max_tokens": 100000,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supported_modalities": ["text"],
+        "supports_tool_choice": false
+    },
+    "gradient_ai/openai-o3-mini": {
+        "input_cost_per_token": 11e-07,
+        "output_cost_per_token": 44e-07,
+        "litellm_provider": "gradient_ai",
+        "mode": "chat",
+        "max_tokens": 100000,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supported_modalities": ["text"],
+        "supports_tool_choice": false
+    },
+    "gradient_ai/openai-gpt-4o": {
+        "litellm_provider": "gradient_ai",
+        "mode": "chat",
+        "max_tokens": 16384,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supported_modalities": ["text"],
+        "supports_tool_choice": false
+    },
+    "gradient_ai/openai-gpt-4o-mini": {
+        "litellm_provider": "gradient_ai",
+        "mode": "chat",
+        "max_tokens": 16384,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supported_modalities": ["text"],
+        "supports_tool_choice": false
+    },
+    "gradient_ai/alibaba-qwen3-32b": {
+        "litellm_provider": "gradient_ai",
+        "mode": "chat",
+        "max_tokens": 2048,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supported_modalities": ["text"],
+        "supports_tool_choice": false
+    },
     "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
         "input_cost_per_token": 9e-08,
         "output_cost_per_token": 2.9e-07,