diff --git a/.github/skills/refresh-json-data/SKILL.md b/.github/skills/refresh-json-data/SKILL.md index 0acc0124..9e6423b6 100644 --- a/.github/skills/refresh-json-data/SKILL.md +++ b/.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 diff --git a/vscode-extension/src/README.md b/vscode-extension/src/README.md index ecf40010..178a8054 100644 --- a/vscode-extension/src/README.md +++ b/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 / $1.50 output Note: These are the current GitHub Copilot supported Gemini models. Pricing from direct Google AI API usage applies. diff --git a/vscode-extension/src/modelPricing.json b/vscode-extension/src/modelPricing.json index 0c0f402e..3efceed6 100644 --- a/vscode-extension/src/modelPricing.json +++ b/vscode-extension/src/modelPricing.json @@ -2,29 +2,46 @@ "$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, diff --git a/vscode-extension/src/tokenEstimators.json b/vscode-extension/src/tokenEstimators.json index e4592fb2..3d3d0b14 100644 --- a/vscode-extension/src/tokenEstimators.json +++ b/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,