Skip to content

Fix model pricing: correct $0 prices for GPT-5.4 and Claude Sonnet 4.6 #531

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rajbos merged 1 commit into from
Mar 30, 2026
Merged

Fix model pricing: correct $0 prices for GPT-5.4 and Claude Sonnet 4.6 #531

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions .github/skills/refresh-json-data/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
14 changes: 9 additions & 5 deletions vscode-extension/src/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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.

Expand Down
69 changes: 52 additions & 17 deletions vscode-extension/src/modelPricing.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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."
Expand Down Expand Up @@ -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,
Expand Down Expand Up @@ -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,
Expand Down Expand Up @@ -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,
Expand Down Expand Up @@ -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,
Expand Down
2 changes: 2 additions & 0 deletions vscode-extension/src/tokenEstimators.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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,
Expand All @@ -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,
Expand Down
Loading