Skip to content

feat(providers): price Gemini 4 Argon on Copilot #623

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
Menci merged 1 commit into from
Oct 13, 2026
Merged

feat(providers): price Gemini 4 Argon on Copilot #623

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
2 changes: 1 addition & 1 deletion packages/gateway/src/repo/models-cache-contract.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ import type { UpstreamModelsCache } from '@floway-dev/provider';
// Persisted ProviderModel rows contain code-derived metadata as well as the
// upstream response. Increment this whenever that derived catalog contract or
// its serialization changes so older rows become cold across deployments.
export const MODEL_CATALOG_REVISION = 16;
export const MODEL_CATALOG_REVISION = 17;

const AUTOMATIC_REFRESH_INTERVAL_MS = 10 * 60_000;

Expand Down
10 changes: 10 additions & 0 deletions packages/provider-copilot/__tests__/pricing_test.ts
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

15 changes: 15 additions & 0 deletions packages/provider-copilot/src/pricing.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -184,6 +184,21 @@ const COPILOT_MODEL_PRICING: readonly PricingRule[] = [
// https://github.com/github/docs/blob/f067ad0f9840f1b4afb5a801a77f74ef70951189/data/tables/copilot/model-release-status.yml
// https://cloud.google.com/vertex-ai/generative-ai/pricing
[/^gemini-3\.[678]-flash$/, tokenBasePricing({ input_tokens: '0.75', input_cache_read_tokens: '0.075', output_tokens: '3.75' })],
// Gemini 4 Argon reached Copilot GA on 2026-10-13, billed at Google's list
// price. Google runs the same promotional card in both places — $2.00 input,
// $0.10 cached input, $10.00 output — through 2026-11-30, doubling on
// 2026-12-01; recheck then. GitHub quotes it as a single Default tier and
// models.dev agrees on all three rates. Two properties separate it from the
// 3.x Gemini rows above: Google lists one band for its 1M-token window
// instead of repricing above 200k, and its only caching is implicit, so
// there is no cache-write rate to quote. Google sells Batch/Flex/Priority
// lanes too, but with no published `serviceTier` coordinate for Copilot this
// entry stays Base-only.
// https://github.blog/changelog/2026-10-13-gemini-4-argon-in-github-copilot/
// https://docs.github.com/en/copilot/reference/copilot-billing/models-and-pricing
// https://ai.google.dev/gemini-api/docs/pricing#gemini-4-argon
// https://github.com/anomalyco/models.dev/blob/03312cc3c02d44bac48abd405d181fcc9c85881d/models/google/gemini-4-argon.toml
['gemini-4-argon', tokenBasePricing({ input_tokens: '2', input_cache_read_tokens: '0.1', output_tokens: '10' })],
// xAI reprices the whole request at 2× once the prompt reaches 200k tokens.
// Cached-read is xAI's own published $0.30/$0.60; Copilot's catalog and
// LiteLLM both carry $0.50/$1.00 for that metric, which the vendor contradicts.
Expand Down
Loading