From 6adcd79c1aeebab2d0db1b09054e2fc1f769d1d7 Mon Sep 17 00:00:00 2001
From: Kagamine Rin <rin.kagamine@captcouch.xyz>
Date: Sat, 13 Jun 2026 16:21:49 -0400
Subject: [PATCH] feat: add hide_zero_spend parameter to litellm_cost()

Adds optional hide_zero_spend parameter (default False) to filter out
models with bash.00 spend from the per-model breakdown. Useful when
free-tier or subscription models (e.g. Ollama Cloud) dominate the
breakdown with high token counts but zero cost.

- Updated litellm_cost() signature with hide_zero_spend parameter
- Added filtering logic in model line builder
- Added hidden model count summary line
- Updated README with parameter documentation
- Bumped version to 1.2.0
---
 README.md            |  5 +++++
 litellm_dashboard.py | 12 ++++++++++--
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index b631265..4e65030 100644
--- a/README.md
+++ b/README.md
@@ -10,6 +10,11 @@ Check LiteLLM proxy health and authentication status. Returns which models are h
 ### `litellm_cost`
 Get LiteLLM cost breakdown for a date range. Returns per-model and per-day spend, token counts, cache hit rate, and request stats.
 
+**Parameters:**
+- `start_date` (str, required): Start date in YYYY-MM-DD format
+- `end_date` (str, required): End date in YYYY-MM-DD format
+- `hide_zero_spend` (bool, default false): Hide models with $0.00 spend. Useful when free-tier or subscription models (e.g. Ollama Cloud) dominate the breakdown with high token counts but zero cost.
+
 ### `litellm_history`
 Get recent LiteLLM request history. Returns the most recent N requests with model, call type, status, duration, token counts, cache hit %, and per-request cost. Useful for understanding which models are being called and how much individual requests cost.
 
diff --git a/litellm_dashboard.py b/litellm_dashboard.py
index 54776cd..49e5eff 100644
--- a/litellm_dashboard.py
+++ b/litellm_dashboard.py
@@ -5,7 +5,7 @@ author_url: https://rin.captcouch.xyz
 description: Check LiteLLM proxy health + auth status and get cost breakdowns with configurable timerange. Two functions, that's it.
 required_open_webui_version: 0.4.0
 requirements: requests
-version: 1.1.0
+version: 1.2.0
 licence: MIT
 """
 
@@ -119,11 +119,13 @@ class Tools:
         self,
         start_date: str,
         end_date: str,
+        hide_zero_spend: bool = False,
     ) -> str:
         """
         Get LiteLLM cost breakdown for a date range.
         :param start_date: Start date in YYYY-MM-DD format (e.g. "2026-06-01")
         :param end_date: End date in YYYY-MM-DD format (e.g. "2026-06-04")
+        :param hide_zero_spend: Hide models with $0.00 spend (default False). Useful when free-tier or subscription models (e.g. Ollama Cloud) dominate the breakdown with high token counts but zero cost.
         Returns formatted cost report with per-model and per-day breakdowns, token counts, cache hit rate, and request stats.
         """
         if not self.valves.litellm_master_key:
@@ -205,8 +207,12 @@ class Tools:
 
         # Build model lines sorted by spend
         model_lines = []
+        hidden_count = 0
         for model_name in sorted(model_totals, key=lambda k: model_totals[k]["spend"], reverse=True):
             mt = model_totals[model_name]
+            if hide_zero_spend and mt["spend"] == 0:
+                hidden_count += 1
+                continue
             # Strip common provider prefixes for readability
             display = model_name
             for prefix in ("gemini/", "openai/", "anthropic/", "mistral/", "cohere/"):
@@ -237,6 +243,8 @@ class Tools:
         lines.append("By Model:")
         lines.append(f'  {"Model":25s} {"Spend":>7s} | {"Requests":>14s} | {"Tokens":>10s}')
         lines.extend(model_lines)
+        if hidden_count > 0:
+            lines.append(f"  ... ({hidden_count} model(s) with $0.00 spend hidden)")
         lines.append("")
         lines.append("By Date:")
         lines.extend(date_lines)
@@ -406,4 +414,4 @@ class Tools:
                              f"{recent_prompt:,} prompt + {recent_completion:,} completion tokens | "
                              f"{recent_failed} failed")
 
-        return "\n".join(lines)
\ No newline at end of file
+        return "\n".join(lines)