Skip to content

feat(cost): add pricing metadata and resolve prefix shadowing #86

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

Open
kesslerio wants to merge 2 commits into
base: main
Choose a base branch
from
Open

feat(cost): add pricing metadata and resolve prefix shadowing #86

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4262300
feat(cost): add pricing metadata for new flagship and cloud models
kesslerio Jun 6, 2026
ed730c3
feat(cost): resolve prefix shadowing and align gpt-5.4-mini pricing
kesslerio Jun 6, 2026
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
18 changes: 15 additions & 3 deletions lib/server/cost-utils.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,14 @@ const kGlobalModelPricing = {
"gemini-3.1-pro-preview": { input: 2.0, output: 12.0 },
"gemini-3-flash-preview": { input: 0.5, output: 3.0 },
"gemini-2.0-flash": { input: 0.1, output: 0.4 },
"gpt-5.5": { input: 5.0, output: 30.0, cacheRead: 0.5, cacheWrite: 5.0 },
"kimi-k2.6:cloud": { input: 0.8, output: 3.0, cacheRead: 0.1, cacheWrite: 0.8 },
"deepseek-v4-flash:cloud": { input: 0.14, output: 0.28, cacheRead: 0.0028, cacheWrite: 0.14 },
"glm-5.1:cloud": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 1.4 },
"grok-4.3": { input: 1.25, output: 2.5, cacheRead: 0.2, cacheWrite: 1.25 },
"qwen3-coder-next": { input: 0.11, output: 0.8, cacheRead: 0.0, cacheWrite: 0.11 },
"gpt-5.4-mini": { input: 0.75, output: 4.5, cacheRead: 0.075, cacheWrite: 0.75 },
"minimax-m3:cloud": { input: 0.6, output: 2.4, cacheRead: 0.06, cacheWrite: 0.6 },
};

const toInt = (value, fallbackValue = 0) => {
Expand Down Expand Up @@ -256,9 +264,13 @@ const resolvePricingFromFallbackMap = (model = "") => {
if (!normalized) return null;
const exact = kGlobalModelPricing[normalized];
if (exact) return exact;
const matchKey = Object.keys(kGlobalModelPricing).find((key) =>
normalized.includes(key),
);
const modelId = normalized.split("/").filter(Boolean).pop();
if (modelId && kGlobalModelPricing[modelId]) {
return kGlobalModelPricing[modelId];
}
const matchKey = Object.keys(kGlobalModelPricing)
.sort((a, b) => b.length - a.length)
.find((key) => normalized.includes(key));
return matchKey ? kGlobalModelPricing[matchKey] : null;
};

Expand Down
27 changes: 27 additions & 0 deletions tests/server/cost-utils.test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,4 +29,31 @@ describe("server/cost-utils", () => {
expect(breakdown.pricingFound).toBe(true);
expect(breakdown.totalCost).toBeCloseTo(5, 8);
});

it("prices provider-qualified GPT-5.5 correctly without gpt-5 shadowing", () => {
const breakdown = deriveCostBreakdown({
provider: "openai",
model: "openai/gpt-5.5",
inputTokens: 1_000_000,
outputTokens: 1_000_000,
});

expect(breakdown.pricingFound).toBe(true);
// GPT-5.5 is input: 5.0, output: 30.0 (total $35.0 per million)
// GPT-5 would be input: 1.25, output: 10.0 (total $11.25 per million)
expect(breakdown.totalCost).toBeCloseTo(35.0, 8);
});

it("prices provider-qualified GPT-5.4-mini correctly without gpt-5 shadowing", () => {
const breakdown = deriveCostBreakdown({
provider: "openai",
model: "openai/gpt-5.4-mini",
inputTokens: 1_000_000,
outputTokens: 1_000_000,
});

expect(breakdown.pricingFound).toBe(true);
// GPT-5.4-mini is input: 0.75, output: 4.5 (total $5.25 per million)
expect(breakdown.totalCost).toBeCloseTo(5.25, 8);
});
});
Loading