Fix model pricing: correct prices for GPT-5.4 and Claude Sonnet 4.6 (#531)

Critical fixes:
- GPT-5.4: .00/.00 -> .50/.00 (was released after last update)
- Claude Sonnet 4.6: .00/.00 -> .00/.00 (was released after last update)
- o3-mini: .00/.00 -> .10/.40 (was 3.6x too high)
- o4-mini: .00/.00 -> .10/.40 (was 3.6x too high)

New models added:
- gpt-5.4-mini (.25/.00)
- gemini-3.1-flash-lite (.25/.50)

New pricing sources added:
- xAI Grok API (https://x.ai/api)
- GitHub Copilot Premium Requests docs (multiplier validation)
- OpenRouter (cross-provider pricing verification)
- Anthropic platform.claude.com docs

Updated all source retrieval dates to 2026-03-30.
Updated README and refresh-json-data skill with new source URLs.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: rajbos

.github/skills/refresh-json-data/SKILL.md

@@ -106,9 +106,12 @@ Before updating these files, ensure you have:
 
 1. **Check official pricing pages**:
    - OpenAI: https://openai.com/api/pricing/
-   - Anthropic: https://www.anthropic.com/pricing
-   - Google Gemini: https://ai.google.dev/pricing
+   - Anthropic: https://www.anthropic.com/pricing (also https://platform.claude.com/docs/en/about-claude/pricing)
+   - Google Gemini: https://ai.google.dev/gemini-api/docs/pricing
+   - xAI Grok: https://x.ai/api
    - GitHub Copilot Models: https://docs.github.com/en/copilot/reference/ai-models/supported-models
+   - GitHub Copilot Premium Requests: https://docs.github.com/en/copilot/managing-copilot/monitoring-usage-and-entitlements/about-premium-requests
+   - OpenRouter (cross-provider verification): https://openrouter.ai
 
 2. **Update pricing entries** in the `pricing` object:
    ```json

vscode-extension/src/README.md

@@ -53,21 +53,25 @@ Contains pricing information for AI models, including input and output token cos
 **How to update:**
 1. Check official pricing pages:
    - OpenAI: https://openai.com/api/pricing/
-   - Anthropic: https://www.anthropic.com/pricing
-   - Google Gemini: https://ai.google.dev/pricing
+   - Anthropic: https://www.anthropic.com/pricing (also https://platform.claude.com/docs/en/about-claude/pricing)
+   - Google Gemini: https://ai.google.dev/gemini-api/docs/pricing
+   - xAI Grok: https://x.ai/api
    - GitHub Copilot Supported Models: https://docs.github.com/en/copilot/reference/ai-models/supported-models
+   - GitHub Copilot Premium Requests: https://docs.github.com/en/copilot/managing-copilot/monitoring-usage-and-entitlements/about-premium-requests
+   - OpenRouter (cross-provider verification): https://openrouter.ai
 2. Update the `pricing` object with new rates
 3. Update `metadata.lastUpdated` with current date
 4. Update source URLs and dates if needed
-5. Rebuild the extension after making changes
+5. Rebuild the extension after making changes (`npm run compile`)
 
 ### Current Gemini Model Pricing (per million tokens)
 
-Based on Google AI pricing (retrieved December 27, 2025):
+Based on Google AI pricing (retrieved March 30, 2026):
 
 - **Gemini 2.5 Pro**: $1.25 input / $10.00 output
-- **Gemini 3 Flash**: $0.50 input / $3.00 output  
+- **Gemini 3 Flash**: $0.50 input / $3.00 output
 - **Gemini 3 Pro**: $2.00 input / $12.00 output (for prompts ≤ 200k tokens)
+- **Gemini 3.1 Flash Lite**: $0.25 input / $1.50 output
 
 Note: These are the current GitHub Copilot supported Gemini models. Pricing from direct Google AI API usage applies.
 

vscode-extension/src/modelPricing.json

@@ -2,29 +2,46 @@
   "$schema": "http://json-schema.org/draft-07/schema#",
   "description": "Model pricing data - costs per million tokens for input and output",
   "metadata": {
-    "lastUpdated": "2026-03-09",
+    "lastUpdated": "2026-03-30",
     "sources": [
       {
         "name": "OpenAI API Pricing",
         "url": "https://openai.com/api/pricing/",
-        "retrievedDate": "2026-01-16"
+        "retrievedDate": "2026-03-30"
       },
       {
         "name": "Anthropic Claude Pricing",
         "url": "https://www.anthropic.com/pricing",
-        "note": "Standard rates",
-        "retrievedDate": "2026-01-16"
+        "note": "Standard rates; also see https://platform.claude.com/docs/en/about-claude/pricing",
+        "retrievedDate": "2026-03-30"
       },
       {
         "name": "Google AI Gemini API Pricing",
-        "url": "https://ai.google.dev/pricing",
-        "retrievedDate": "2026-01-16"
+        "url": "https://ai.google.dev/gemini-api/docs/pricing",
+        "retrievedDate": "2026-03-30"
+      },
+      {
+        "name": "xAI Grok API Pricing",
+        "url": "https://x.ai/api",
+        "retrievedDate": "2026-03-30"
       },
       {
         "name": "GitHub Copilot Supported Models",
         "url": "https://docs.github.com/en/copilot/reference/ai-models/supported-models",
-        "retrievedDate": "2026-01-30",
+        "retrievedDate": "2026-03-30",
         "note": "Source for tier/multiplier data"
+      },
+      {
+        "name": "GitHub Copilot Premium Requests",
+        "url": "https://docs.github.com/en/copilot/managing-copilot/monitoring-usage-and-entitlements/about-premium-requests",
+        "retrievedDate": "2026-03-30",
+        "note": "Source for premium request multiplier values"
+      },
+      {
+        "name": "OpenRouter Model Pricing",
+        "url": "https://openrouter.ai",
+        "retrievedDate": "2026-03-30",
+        "note": "Cross-provider pricing aggregator used for verification"
       }
     ],
     "disclaimer": "GitHub Copilot uses these models but pricing may differ from direct API usage. These are reference prices for cost estimation purposes only."
@@ -109,11 +126,20 @@
       "multiplier": 1
     },
     "gpt-5.4": {
-      "inputCostPerMillion": 0.00,
-      "outputCostPerMillion": 0.00,
+      "inputCostPerMillion": 2.50,
+      "outputCostPerMillion": 15.0,
       "category": "GPT-5 models",
       "tier": "premium",
-      "multiplier": 1
+      "multiplier": 1,
+      "displayNames": ["GPT-5.4"]
+    },
+    "gpt-5.4-mini": {
+      "inputCostPerMillion": 0.25,
+      "outputCostPerMillion": 2.0,
+      "category": "GPT-5 models",
+      "tier": "standard",
+      "multiplier": 0,
+      "displayNames": ["GPT-5.4 mini"]
     },
     "gpt-4": {
       "inputCostPerMillion": 3.0,
@@ -201,11 +227,12 @@
       "multiplier": 1
     },
     "claude-sonnet-4.6": {
-      "inputCostPerMillion": 0.00,
-      "outputCostPerMillion": 0.00,
+      "inputCostPerMillion": 3.0,
+      "outputCostPerMillion": 15.0,
       "category": "Claude models (Anthropic)",
       "tier": "premium",
-      "multiplier": 3
+      "multiplier": 3,
+      "displayNames": ["Claude Sonnet 4.6"]
     },
     "claude-haiku": {
       "inputCostPerMillion": 0.25,
@@ -257,16 +284,16 @@
       "multiplier": 30
     },
     "o3-mini": {
-      "inputCostPerMillion": 4.0,
-      "outputCostPerMillion": 16.0,
+      "inputCostPerMillion": 1.10,
+      "outputCostPerMillion": 4.40,
       "category": "OpenAI reasoning models",
       "tier": "premium",
       "multiplier": 1,
       "displayNames": ["o3-mini"]
     },
     "o4-mini": {
-      "inputCostPerMillion": 4.0,
-      "outputCostPerMillion": 16.0,
+      "inputCostPerMillion": 1.10,
+      "outputCostPerMillion": 4.40,
       "category": "OpenAI reasoning models",
       "tier": "premium",
       "multiplier": 1,
@@ -363,6 +390,14 @@
       "multiplier": 1,
       "displayNames": ["Gemini 3.1 Pro", "Gemini 3.1 Pro (Preview)"]
     },
+    "gemini-3.1-flash-lite": {
+      "inputCostPerMillion": 0.25,
+      "outputCostPerMillion": 1.50,
+      "category": "Google Gemini models",
+      "tier": "unknown",
+      "multiplier": 0.33,
+      "displayNames": ["Gemini 3.1 Flash Lite"]
+    },
     "grok-code-fast-1": {
       "inputCostPerMillion": 0.20,
       "outputCostPerMillion": 1.50,

vscode-extension/src/tokenEstimators.json

@@ -21,6 +21,7 @@
     "gpt-5.2-pro": 0.25,
     "gpt-5.3-codex": 0.25,
     "gpt-5.4": 0.25,
+    "gpt-5.4-mini": 0.25,
     "gpt-4.1-nano": 0.25,
     "gemini-2.0-flash": 0.25,
     "gemini-2.0-flash-lite": 0.25,
@@ -43,6 +44,7 @@
     "gemini-3-pro": 0.25,
     "gemini-3-pro-preview": 0.25,
     "gemini-3.1-pro": 0.25,
+    "gemini-3.1-flash-lite": 0.25,
     "grok-code-fast-1": 0.25,
     "raptor-mini": 0.25,
     "goldeneye": 0.25,