Skip to content

Peter/model cache pricing #47

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
pjb157 merged 2 commits into from
Jul 31, 2026
Merged

Peter/model cache pricing #47

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
e1e942b
fix: show cache read multiplier in catalog
pjb157 Jul 31, 2026
5d78ec2
Merge pull request #46 from doublewordai/peter/cache-read-multiplier-…
pjb157 Jul 31, 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
10 changes: 6 additions & 4 deletions src/lib/model-artifacts.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,15 +150,17 @@ describe("buildModelArtifacts", () => {
});

describe("renderModelsIndexMarkdown", () => {
it("shows model-specific cache-read prices and unsupported fallbacks", () => {
it("shows model-specific cache-read multipliers and unsupported fallbacks", () => {
const markdown = renderModelsIndexMarkdown([
{ name: "Enabled", slug: "enabled", id: "enabled", rawName: "Enabled", type: "Generation", capabilities: [], playgroundUrl: "https://example.com/enabled", pricing: [], cacheReadPricePer1M: "\\$0.10", cacheReadMultiplier: 0.1 },
{ name: "Unsupported", slug: "unsupported", id: "unsupported", rawName: "Unsupported", type: "Generation", capabilities: [], playgroundUrl: "https://example.com/unsupported", pricing: [] },
]);

expect(markdown).toContain("| Model | Provider | Type | Realtime | Async | Batch (24h) | Cache read |");
expect(markdown).toContain("| [Enabled](/inference-api/models/enabled) | — | Generation | — | — | — | \\$0.10 / 1M |");
expect(markdown).toContain("| [Unsupported](/inference-api/models/unsupported) | — | Generation | — | — | — | — |");
expect(markdown).toContain("| Model | Provider | Type | Realtime | Async | Batch (24h) | Cache read |");
expect(markdown).toContain("|-------|----------|------|----------|-------|-------------|:----------:|");
expect(markdown).toContain("| [Enabled](/inference-api/models/enabled) | — | Generation | — | — | — | 0.1× |");
expect(markdown).toContain("| [Unsupported](/inference-api/models/unsupported) | — | Generation | — | — | — | ❌ |");
expect(markdown).not.toContain("❌ Prompt caching is not supported for this model.");
expect(markdown).not.toContain("90% discount");
});
});
Expand Down
12 changes: 6 additions & 6 deletions src/lib/model-artifacts.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -211,12 +211,12 @@ export function renderModelsIndexMarkdown(artifacts: ModelArtifact[]): string {
};

const overviewTable = [
"| Model | Provider | Type | Realtime | Async | Batch (24h) | Cache read |",
"|-------|----------|------|----------|-------|-------------|------------|",
"| Model | Provider | Type | Realtime | Async | Batch (24h) | Cache read |",
"|-------|----------|------|----------|-------|-------------|:----------:|",
...artifacts.map((artifact) => {
const cacheRead = artifact.cacheReadPricePer1M
? `${artifact.cacheReadPricePer1M} / 1M`
: "—";
const cacheRead = artifact.cacheReadMultiplier !== undefined
? `${artifact.cacheReadMultiplier}×`
: "❌";
return `| [${artifact.name}](${getModelArtifactPath(artifact.slug)}) | ${renderProvider(artifact.providerName)} | ${artifact.type} | ${formatTierCell(artifact, "Realtime")} | ${formatTierCell(artifact, "Async")} | ${formatTierCell(artifact, "Batch (24h)")} | ${cacheRead} |`;
}),
].join("\n");
Expand All @@ -226,7 +226,7 @@ export function renderModelsIndexMarkdown(artifacts: ModelArtifact[]): string {
The table below outlines the models we have available and their pricing per 1M tokens. If you are interested in understanding pricing for a model not listed below or if you'd like to request a new model - please reach out to support@doubleword.ai.

:::info{title="Prompt caching"}
Prompt-caching availability and rates are model-specific. The **Cache read** column shows the current cache-read price for supported models. See the [prompt caching guide](/inference-api/prompt-caching) for setup, TTLs, and write pricing.
Prompt-caching availability and rates are model-specific. The **Cache read** column shows the current multiplier on the model's standard input price. See the [prompt caching guide](/inference-api/prompt-caching) for setup, TTLs, and write pricing.
Comment on lines 226 to +229
:::

## Model Catalog
Expand Down