diff --git a/packages/cli/src/commands/media-use/generate.ts b/packages/cli/src/commands/media-use/generate.ts index 7e327b6aa5..60b4b5b489 100644 --- a/packages/cli/src/commands/media-use/generate.ts +++ b/packages/cli/src/commands/media-use/generate.ts @@ -131,7 +131,7 @@ export default defineCommand({ model: { type: "string", description: - "image: nano-banana-2 (default), nano-banana-2.1, gpt-image-2.5, gpt-image-2.6 or gpt-image-2.6-flare", + "image: nano-banana-2 (default), nano-banana-2.1, gpt-image-2.5, gpt-image-2.6, gpt-image-2.6-flare, minimax-h3-image (2K) or minimax-h3-image-4k", }, bpm: { type: "string", description: "music: tempo, 60–180" }, vocals: { @@ -142,7 +142,7 @@ export default defineCommand({ "max-credits": { type: "string", description: - "The person's credit limit, less what earlier calls used: make nothing when this call would cost more. A gpt-image call is charged at the vendor's cost, so it is checked against its estimate plus 10%; that is not a hard ceiling, and an edit with many references can still go over. The project's credit-limit.json follows the same rule", + "The person's credit limit, less what earlier calls used: make nothing when this call would cost more. A gpt-image or minimax-h3-image call is charged on the vendor's bill, so it is checked against its estimate plus 10%; that is not a hard ceiling, and an edit with many references can still go over. The project's credit-limit.json follows the same rule", }, plan: { type: "boolean", diff --git a/packages/cli/src/heygen/generate.test.ts b/packages/cli/src/heygen/generate.test.ts index abf1d13f84..26c9dc8fa5 100644 --- a/packages/cli/src/heygen/generate.test.ts +++ b/packages/cli/src/heygen/generate.test.ts @@ -169,7 +169,7 @@ describe("generate", () => { ); }); - it("keeps 10% headroom under the run's credit limit for an image charged at the vendor's cost", async () => { + it("keeps 10% headroom under the run's credit limit for an image charged on the vendor's bill", async () => { const run = (limit: number) => { const dir = mkdtempSync(join(tmpdir(), "hf-generate-limit-")); writeFileSync(join(dir, "index.html"), ""); @@ -198,10 +198,39 @@ describe("generate", () => { }, }), ); - await expect(run(43)).rejects.toThrow( - "about 40 credits, 44 with 10% headroom because it is charged at the vendor's cost and the run's credit limit of 43 leaves 43", + await expect(run(72)).rejects.toThrow( + "about 66 credits, 73 with 10% headroom because it is charged on the vendor's bill and the run's credit limit of 72 leaves 72", ); - await expect(run(44)).resolves.toMatchObject({ job: "img4" }); + await expect(run(73)).resolves.toMatchObject({ job: "img4" }); + }); + + it("sends a MiniMax H3 image one picture at its aspect, with no seed", async () => { + const sent: Record[] = []; + vi.stubGlobal("fetch", async (url: string, init?: RequestInit) => { + if (init?.body) sent.push(JSON.parse(String(init.body))); + return url === "https://files.test/h3.png" + ? new Response(new Uint8Array([1])) + : json({ + data: { + id: "img6", + status: "completed", + images: [{ url: "https://files.test/h3.png" }], + }, + }); + }); + await generate({ + type: "image", + out: join(project, "assets/h3.png"), + prompt: "a wide desk", + model: "minimax-h3-image-4k", + aspect: "21:9", + }); + expect(sent[0]).toEqual({ + model: "minimax-h3-image-4k", + prompt: "a wide desk", + num_images: 1, + aspect_ratio: "21:9", + }); }); it("reports no charge in HyperFrames credits for a charge to another pool", async () => { @@ -854,7 +883,7 @@ describe("generate", () => { } as const; await expect( generate(request, undefined, creditsOf(priceOf(request)) ?? undefined), - ).rejects.toThrow("this step needs about 67"); + ).rejects.toThrow("this step needs about 111"); }); it("prices before making", () => { @@ -868,7 +897,7 @@ describe("generate", () => { aspect: "1:1", references: ["a", "b"], }).usd, - ).toBe(0.09); + ).toBe(0.12); expect(priceOf({ type: "voice", out: "a.mp3" }).usd).toBeNull(); expect(creditsOf(priceOf({ type: "voice", out: "a.mp3", script: "今天聊黄金" }))).toBe(1); }); @@ -877,30 +906,129 @@ describe("generate", () => { const edit = (model: string, references: string[]) => creditsOf(priceOf({ type: "image", out: "a.png", model, aspect: "16:9", references })); for (const model of ["gpt-image-2.5", "gpt-image-2.6", "gpt-image-2.6-flare"]) { - expect(edit(model, [])).toBe(40); - expect(edit(model, ["a"])).toBe(53); + expect(edit(model, [])).toBe(66); + expect(edit(model, ["a"])).toBe(87); expect( edit( model, Array.from({ length: 16 }, (_, i) => `r${i}`), ), - ).toBe(240); + ).toBe(397); } expect( creditsOf( priceOf({ type: "image", out: "a.png", model: "nano-banana-2.1", references: ["a", "b"] }), ), - ).toBe(37); + ).toBe(62); expect(priceOf({ type: "image", out: "a.png", model: "some-new-model" }).credits).toBeNull(); }); - it("says a GPT Image price is an estimate charged at vendor cost, and a Nano Banana one is not", () => { + it("says a GPT Image price is an estimate charged on the vendor's bill, and a Nano Banana one is not", () => { expect( priceOf({ type: "image", out: "a.png", model: "gpt-image-2.5", aspect: "16:9" }).basis, ).toBe( - "gpt-image-2.5 at 16:9, about 40 credits (charged at vendor cost), with about $0.0125 a reference", + "gpt-image-2.5 at 16:9, about 66 credits (charged on the vendor's bill), with about $0.0125 a reference; vendor price x1.5 on an API key, x1.6545 in HyperFrames credits", ); - expect(priceOf({ type: "image", out: "a.png" }).basis).toBe("nano-banana-2, $0.067 an image"); + expect(priceOf({ type: "image", out: "a.png" }).basis).toBe( + "nano-banana-2, $0.067 an image; vendor price x1.5 on an API key, x1.6545 in HyperFrames credits", + ); + }); + + it("prices a MiniMax H3 image at 2K and 4K, with references, for an API key and a plan", () => { + const h3 = (model: string, references: number, aspect = "16:9") => + priceOf({ + type: "image", + out: "a.png", + model, + aspect, + references: Array.from({ length: references }, (_, i) => `r${i}`), + }); + // The hf_image rows: 41.3625 a 2K output, 115.815 a 4K output, 24.8175 a reference. + expect(h3("minimax-h3-image", 0).credits).toBeCloseTo(41.3625, 6); + expect(h3("minimax-h3-image-4k", 0).credits).toBeCloseTo(115.815, 6); + expect(h3("minimax-h3-image", 1).credits! - h3("minimax-h3-image", 0).credits!).toBeCloseTo( + 24.8175, + 6, + ); + expect( + h3("minimax-h3-image-4k", 1).credits! - h3("minimax-h3-image-4k", 0).credits!, + ).toBeCloseTo(24.8175, 6); + const both = (p: ReturnType) => [p.list, p.usd, creditsOf(p)]; + expect(both(h3("minimax-h3-image", 0))).toEqual([expect.closeTo(0.0375, 9), 0.05, 42]); + expect(both(h3("minimax-h3-image", 2))).toEqual([expect.closeTo(0.0825, 9), 0.09, 91]); + expect(both(h3("minimax-h3-image-4k", 0))).toEqual([expect.closeTo(0.105, 9), 0.12, 116]); + expect(both(h3("minimax-h3-image-4k", 1))).toEqual([expect.closeTo(0.1275, 9), 0.14, 141]); + expect(creditsOf(h3("minimax-h3-image", 16))).toBe(439); + // One price at every aspect: H3 bills by area tier, not shape. + expect(h3("minimax-h3-image", 0, "21:9").credits).toBe( + h3("minimax-h3-image", 0, "1:1").credits, + ); + expect(h3("minimax-h3-image-4k", 0, "21:9").basis).toBe( + "minimax-h3-image-4k at 21:9, about 116 credits (charged on the vendor's bill), with about $0.015 a reference; vendor price x1.5 on an API key, x1.6545 in HyperFrames credits", + ); + for (const model of ["minimax-h3-image", "minimax-h3-image-4k"]) + expect(isVendorPriced({ type: "image", out: "a.png", model })).toBe(true); + }); + + it("prices every image model at its hf_image row for a plan and 1.5x its vendor price for an API key", () => { + const image = (model: string, aspect: string, references = 0) => + priceOf({ + type: "image", + out: "a.png", + model, + aspect, + references: Array.from({ length: references }, (_, i) => `r${i}`), + }); + const rows: [string, string, number][] = [ + ["gpt-image-2.6", "1:1", 87.15906], + ["gpt-image-2.6-flare", "16:9", 65.5182], + ["gpt-image-2.5", "4:3", 59.76054], + ["nano-banana-2", "21:9", 110.8515], + ["nano-banana-2.1", "3:2", 55.5912], + ]; + for (const [model, aspect, row] of rows) + expect(image(model, aspect).credits).toBeCloseTo(row, 6); + expect( + image("gpt-image-2.6", "16:9", 1).credits! - image("gpt-image-2.6", "16:9").credits!, + ).toBeCloseTo(20.68125, 6); + expect( + image("nano-banana-2.1", "1:1", 1).credits! - image("nano-banana-2.1", "1:1").credits!, + ).toBeCloseTo(2.77956, 6); + expect(image("nano-banana-2", "1:1", 3).credits).toBe(image("nano-banana-2", "1:1").credits); + expect(image("nano-banana-2", "1:1").list).toBeCloseTo(0.1005, 9); + expect(image("nano-banana-2", "1:1").usd).toBe(0.12); + expect(image("gpt-image-2.6", "16:9").list).toBeCloseTo(0.0594, 9); + expect(image("gpt-image-2.6", "16:9").usd).toBe(0.07); + expect(image("nano-banana-2.1", "16:9", 2).list).toBeCloseTo((0.0336 + 2 * 0.00168) * 1.5, 9); + }); + + it("refuses an aspect ratio or a reference count the model does not take", () => { + const check = + (model: string, aspect?: string, references = 0) => + () => + checkRequest({ + type: "image", + out: join(project, "assets/limits.png"), + prompt: "a desk", + model, + ...(aspect ? { aspect } : {}), + references: Array.from({ length: references }, (_, i) => + join(project, `missing-${i}.png`), + ), + }); + for (const model of ["minimax-h3-image", "minimax-h3-image-4k"]) { + for (const aspect of ["1:1", "16:9", "9:16", "4:3", "3:4", "21:9"]) + expect(check(model, aspect)).not.toThrow(); + expect(check(model, "3:2")).toThrow(`${model} does not make 3:2`); + expect(check(model, undefined, 17)).toThrow( + `${model} takes at most 16 --reference pictures, not 17`, + ); + expect(check(model, undefined, 16)).toThrow("no file at"); + } + expect(check("gpt-image-2.6", "21:9")).toThrow("gpt-image-2.6 does not make 21:9"); + expect(check("nano-banana-2.1", "21:9")).not.toThrow(); + expect(check("nano-banana-2", undefined, 15)).toThrow("at most 14 --reference pictures"); + expect(check("some-new-model", "7:5")).not.toThrow(); }); it("prices only a request the real call would accept", () => { @@ -1056,26 +1184,26 @@ describe("generate", () => { it("keeps a call under the person's credit limit, or refuses it before sending", () => { const shot = creditsOf(priceOf({ type: "video", out: "a.mp4", seconds: 6 })); expect(shot).toBe(108); - expect(creditsOf(priceOf({ type: "image", out: "a.png" }))).toBe(67); + expect(creditsOf(priceOf({ type: "image", out: "a.png" }))).toBe(111); expect(() => checkLimit(shot, 108)).not.toThrow(); expect(() => checkLimit(shot, 30)).toThrow("about 108 credits, over --max-credits 30"); expect(() => checkLimit(null, 30)).toThrow("cannot be priced ahead"); expect(() => checkLimit(null, undefined)).not.toThrow(); }); - it("keeps 10% headroom under the limit for an image charged at the vendor's cost", () => { + it("keeps 10% headroom under the limit for an image charged on the vendor's bill", () => { const limited = (request: GenerateRequest, limit: number) => () => checkLimit(creditsOf(priceOf(request)), limit, isVendorPriced(request)); const gpt = { type: "image", out: "a.png", model: "gpt-image-2.5", aspect: "16:9" } as const; - expect(creditsOf(priceOf(gpt))).toBe(40); - expect(limited(gpt, 40)).toThrow( - "about 40 credits, 44 with 10% headroom because it is charged at the vendor's cost, over --max-credits 40", + expect(creditsOf(priceOf(gpt))).toBe(66); + expect(limited(gpt, 66)).toThrow( + "about 66 credits, 73 with 10% headroom because it is charged on the vendor's bill, over --max-credits 66", ); - expect(limited(gpt, 43)).toThrow("44 with 10% headroom"); - expect(limited(gpt, 44)).not.toThrow(); + expect(limited(gpt, 72)).toThrow("73 with 10% headroom"); + expect(limited(gpt, 73)).not.toThrow(); const nano = { type: "image", out: "a.png", model: "nano-banana-2" } as const; expect(isVendorPriced(nano)).toBe(false); - expect(limited(nano, 67)).not.toThrow(); + expect(limited(nano, 111)).not.toThrow(); }); }); diff --git a/packages/cli/src/heygen/generate.ts b/packages/cli/src/heygen/generate.ts index d658d0a841..d5c0821916 100644 --- a/packages/cli/src/heygen/generate.ts +++ b/packages/cli/src/heygen/generate.ts @@ -168,7 +168,22 @@ export const VENDOR_PRICED_IMAGES = new Set([ "gpt-image-2.5", "gpt-image-2.6", "gpt-image-2.6-flare", + "minimax-h3-image", + "minimax-h3-image-4k", ]); +const GPT_ASPECTS = ["1:1", "16:9", "9:16", "4:3", "3:4"]; +const GEMINI_ASPECTS = [...GPT_ASPECTS, "3:2", "2:3", "21:9"]; +const MINIMAX_ASPECTS = [...GPT_ASPECTS, "21:9"]; +/** What /v3/images accepts from each model: its aspect ratios and how many reference pictures. */ +const IMAGE_MODELS: Record = { + "nano-banana-2": { aspects: GEMINI_ASPECTS, references: 14 }, + "nano-banana-2.1": { aspects: GEMINI_ASPECTS, references: 14 }, + "gpt-image-2.5": { aspects: GPT_ASPECTS, references: 16 }, + "gpt-image-2.6": { aspects: GPT_ASPECTS, references: 16 }, + "gpt-image-2.6-flare": { aspects: GPT_ASPECTS, references: 16 }, + "minimax-h3-image": { aspects: MINIMAX_ASPECTS, references: 16 }, + "minimax-h3-image-4k": { aspects: MINIMAX_ASPECTS, references: 16 }, +}; export const isVendorPriced = (r: GenerateRequest): boolean => r.type === "image" && VENDOR_PRICED_IMAGES.has(r.model ?? ""); const VIDEO_RESOLUTION = "768p"; @@ -182,6 +197,21 @@ const need = (value: T | undefined, flag: string, example: string): T => { return value; }; +function imageModel(r: GenerateRequest): string { + const model = r.model ?? DEFAULTS.image; + const spec = IMAGE_MODELS[model]; + if (!spec) return model; + if (r.aspect && !spec.aspects.includes(r.aspect)) + throw new Fix(`${model} does not make ${r.aspect}`, `--aspect ${spec.aspects.join("|")}`); + const refs = r.references?.length ?? 0; + if (refs > spec.references) + throw new Fix( + `${model} takes at most ${spec.references} --reference pictures, not ${refs}`, + `pass the ${spec.references} that matter most`, + ); + return model; +} + const ROUTES: Record = { image: { path: "/v3/images", @@ -189,7 +219,7 @@ const ROUTES: Record = { c.createImage({ body: body as ImageCreateRequest, idempotencyKey: key, signal }), status: (c, id, signal) => c.getImage({ generation_id: id, signal }), body: (r, media) => ({ - model: r.model ?? DEFAULTS.image, + model: imageModel(r), prompt: need(r.prompt, "--prompt", '--prompt "the same room, empty, no text"'), num_images: 1, ...(r.aspect ? { aspect_ratio: r.aspect } : {}), diff --git a/packages/cli/src/heygen/pricing.ts b/packages/cli/src/heygen/pricing.ts index cd4b30c3da..ef1790ed8e 100644 --- a/packages/cli/src/heygen/pricing.ts +++ b/packages/cli/src/heygen/pricing.ts @@ -35,6 +35,21 @@ const GPT_REFERENCE = 0.0125; const NANO_IMAGE = 0.067; const NANO_2_1_IMAGE = 0.0336; const NANO_2_1_REFERENCE = 0.00168; +const MINIMAX_IMAGE: Record = { + "minimax-h3-image": 0.025, + "minimax-h3-image-4k": 0.07, +}; +const MINIMAX_REFERENCE = 0.015; +// An API key pays 1.5x the vendor price; the price book's hf_image rows charge it x1.103 serving overhead x1.5. +const API_IMAGE_MARKUP = 1.5; +const HF_IMAGE_MARKUP = 1.103 * 1.5; +const MARKUPS = "x1.5 on an API key, x1.6545 in HyperFrames credits"; +const image = (vendorUsd: number, basis: string): Price => + at( + vendorUsd * API_IMAGE_MARKUP, + `${basis}; vendor price ${MARKUPS}`, + vendorUsd * HF_IMAGE_MARKUP * HF_CREDITS_PER_USD, + ); const VIDEO_768P_PER_S = 0.018; // A reference shot (pictures, voice or guide clip) bills more, and its guide clip's seconds bill too: measured // 2026-10-23 from the wallet, 5 s with a picture $0.25, 10 s $0.50, 5 s with a 1 s guide $0.30, with a 3 s guide $0.40. @@ -62,20 +77,23 @@ export function priceOf(r: GenerateRequest): Price { case "image": { const refs = r.references?.length ?? 0; const model = r.model ?? "nano-banana-2"; - if (model === "nano-banana-2") return at(NANO_IMAGE, "nano-banana-2, $0.067 an image"); + if (model === "nano-banana-2") return image(NANO_IMAGE, "nano-banana-2, $0.067 an image"); if (model === "nano-banana-2.1") - return at( + return image( NANO_2_1_IMAGE + refs * NANO_2_1_REFERENCE, "nano-banana-2.1, $0.0336 an image and $0.00168 a reference", ); if (!VENDOR_PRICED_IMAGES.has(model)) return { usd: null, list: null, credits: null, basis: `${model}, not priced ahead` }; - const each = GPT_IMAGE[r.aspect ?? "16:9"] ?? GPT_IMAGE["16:9"]!; - const list = each + refs * GPT_REFERENCE; - const about = Math.ceil(list * HF_CREDITS_PER_USD - 1e-9); - return at( + const aspect = r.aspect ?? "16:9"; + const minimax = MINIMAX_IMAGE[model]; + const each = minimax ?? GPT_IMAGE[aspect] ?? GPT_IMAGE["16:9"]!; + const reference = minimax === undefined ? GPT_REFERENCE : MINIMAX_REFERENCE; + const list = each + refs * reference; + const about = Math.ceil(list * HF_IMAGE_MARKUP * HF_CREDITS_PER_USD - 1e-9); + return image( list, - `${model} at ${r.aspect ?? "16:9"}, about ${about} credits (charged at vendor cost), with about $0.0125 a reference`, + `${model} at ${aspect}, about ${about} credits (charged on the vendor's bill), with about $${reference} a reference`, ); } case "video": { @@ -139,7 +157,7 @@ export function priceOf(r: GenerateRequest): Price { } } -// No HeyGen unit rounding here: a $0.067 image is charged 67 credits, measured on dev 2026-10-29. Still an estimate. +// No HeyGen unit rounding here, only up to a whole credit: the price book rounds a call's lines once. Still an estimate. export const creditsOf = (p: Price): number | null => p.credits === null ? null : Math.ceil(p.credits - 1e-9); diff --git a/packages/cli/src/heygen/v3.ts b/packages/cli/src/heygen/v3.ts index ea7b30cb15..9b995ec21f 100644 --- a/packages/cli/src/heygen/v3.ts +++ b/packages/cli/src/heygen/v3.ts @@ -40,7 +40,7 @@ export function limitCheck(credits: number, vendorPriced = false) { return { checked, about: vendorPriced - ? `about ${credits} credits, ${checked} with 10% headroom because it is charged at the vendor's cost` + ? `about ${credits} credits, ${checked} with 10% headroom because it is charged on the vendor's bill` : `about ${credits} credits`, }; } diff --git a/skills-manifest.json b/skills-manifest.json index d59d04f78d..939fa7fa28 100644 --- a/skills-manifest.json +++ b/skills-manifest.json @@ -18,7 +18,7 @@ "files": 13 }, "media-use": { - "hash": "457c93b8b5216c0f", + "hash": "61f2d9d424f6576a", "files": 125 }, "remotion-to-hyperframes": { diff --git a/skills/media-use/SKILL.md b/skills/media-use/SKILL.md index 33cd49a5a3..d9cbb02fbb 100644 --- a/skills/media-use/SKILL.md +++ b/skills/media-use/SKILL.md @@ -37,7 +37,7 @@ It prints one line, `resolved → (, )`. List reusab **HeyGen.** `npx hyperframes media-use generate` makes images, shots, talking photos, voices and music on the sign-in alone. Helpers and direct recipes need the [`heygen` CLI](https://developers.heygen.com/cli); if it is missing, give the link and wait until they say it is installed. Direct `heygen` recipes bill that CLI's own login: use them only when that payer is selected. -**Credits.** Plan for the best result: no cheaper or free swaps, no dropped items, unless asked to save cost. Don't volunteer prices, estimates or usage; `--plan` is for you. A credit limit the person sets: write it once to `.hyperframes/credit-limit.json` as `{"credits": N}`; every paid call then refuses what would go past it, GPT Image only at estimate +10% (`references/heygen.md`) (`--max-credits` only tightens). A step that won't fit (a `--plan` over what is left, or a refused call): say what doesn't, ask before dropping or shrinking it. A refused call names a `billing` command: say why, ask them to run it, then retry. +**Credits.** Plan for the best result: no cheaper or free swaps, no dropped items, unless asked to save cost. Don't volunteer prices, estimates or usage; `--plan` is for you. A credit limit the person sets: write it once to `.hyperframes/credit-limit.json` as `{"credits": N}`; every paid call then refuses what would go past it, GPT Image and H3 at estimate +10% (`references/heygen.md`) (`--max-credits` only tightens). A step that won't fit (a `--plan` over what is left, or a refused call): say what doesn't, ask before dropping or shrinking it. A refused call names a `billing` command: say why, ask them to run it, then retry. ## Looks on real footage diff --git a/skills/media-use/references/heygen.md b/skills/media-use/references/heygen.md index 48544a30e9..185ac9aec2 100644 --- a/skills/media-use/references/heygen.md +++ b/skills/media-use/references/heygen.md @@ -16,7 +16,7 @@ A refusal names its fix: `api_key_required` needs an API key, `402` or `insuffic ## Making media: `media-use generate` -Make it without quoting a price or asking for a budget; `--plan` only prints what a call would cost (`credits` is an estimate in HyperFrames credits), for your own planning; never pass it on. When the person names a credit limit, record it in the project's credit-limit file (SKILL.md, Credits). A GPT Image call is charged the vendor's cost, so the limit checks it against its estimate plus 10% and is not a hard ceiling for it: a reference-heavy edit can still go past. A finished call's charge, when HeyGen reports it, counts toward the limit afterwards. Make a piece again only for a fault you can name (a cut inside it, text in it, the wrong framing), once, never to chase a motion or look score; a `content_policy_violation` gets one reworded try. A failed or refused job also gets one more try, test calls included; then stop and ask the person, without saying what was spent or what another try costs. +Make it without quoting a price or asking for a budget; `--plan` only prints what a call would cost (`credits` is an estimate in HyperFrames credits), for your own planning; never pass it on. When the person names a credit limit, record it in the project's credit-limit file (SKILL.md, Credits). A GPT Image or MiniMax H3 call is charged on the vendor's bill, so the limit checks it against its estimate plus 10% and is not a hard ceiling for it: a reference-heavy edit can still go past. A finished call's charge, when HeyGen reports it, counts toward the limit afterwards. Make a piece again only for a fault you can name (a cut inside it, text in it, the wrong framing), once, never to chase a motion or look score; a `content_policy_violation` gets one reworded try. A failed or refused job also gets one more try, test calls included; then stop and ask the person, without saying what was spent or what another try costs. ```bash # a still, edited from a reference picture: a clean plate with the words removed @@ -46,15 +46,17 @@ npx hyperframes media-use generate --type music --prompt "warm lo-fi, soft keys" The file lands at `--out` and the media ledger records it as generated, with the route, model, job, prompt and the files it was made from. Pictures and shots carry no text or logos: ask for clean plates and draw words in HyperFrames. -| Type | Model | Price | -| ------- | --------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| image | nano-banana-2 (default), or nano-banana-2.1, gpt-image-2.5, gpt-image-2.6 or gpt-image-2.6-flare with `--model` | $0.067 an image; nano-banana-2.1 $0.034 plus $0.0017 a reference; gpt-image about $0.036–0.053 by aspect plus $0.0125 a reference, a plan charges vendor cost | -| video | heygen-video-1, 768p | $0.02 a second from a prompt or first frame; $0.05 a second with a reference picture, voice or guide clip, and the guide's seconds count too (1080p costs about twice) | -| lipsync | HeyGen lipsync, speed | 7 credits a second of the video on a plan | -| avatar | talking photo | $4.83 a minute of speech | -| cutout | HeyGen background removal | not priced ahead | -| music | lyria-3-pro | $0.08 a track | -| voice | the voice's engine | charged per character, not priced ahead | +| Type | Model | Price | +| ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| image | nano-banana-2 (default), or nano-banana-2.1, gpt-image-2.5, gpt-image-2.6, gpt-image-2.6-flare, minimax-h3-image (2K) or minimax-h3-image-4k with `--model` | 1.5x the vendor price on an API key: $0.10 an image; nano-banana-2.1 $0.05 plus $0.0025 a reference; gpt-image about $0.054–0.079 by aspect plus $0.019 a reference; minimax-h3-image $0.0375 (4K $0.105) plus $0.0225 a reference. A plan charges the vendor price x1.6545 in credits; gpt-image and minimax-h3-image are charged on the vendor's bill | +| video | heygen-video-1, 768p | $0.02 a second from a prompt or first frame; $0.05 a second with a reference picture, voice or guide clip, and the guide's seconds count too (1080p costs about twice) | +| lipsync | HeyGen lipsync, speed | 7 credits a second of the video on a plan | +| avatar | talking photo | $4.83 a minute of speech | +| cutout | HeyGen background removal | not priced ahead | +| music | lyria-3-pro | $0.08 a track | +| voice | the voice's engine | charged per character, not priced ahead | + +Each image model takes only its own aspect ratios and reference count, and generate refuses the rest: gpt-image 1:1, 16:9, 9:16, 4:3 or 3:4 with up to 16 references; nano-banana those and 3:2, 2:3 or 21:9 with up to 14; minimax-h3-image gpt-image's and 21:9 with up to 16. `--plan`'s `usd` is what an API key is charged (HeyGen rounds up to units of $1/60); its `credits` is what a HyperFrames plan charges, on the plan's own rates: a video shot's seconds and guide seconds, plus each picture past the first two. Without `--voice`, generate lists voice ids to pick from on the sign-in alone; a cloned voice from `heygen voice clone create` (`operations.md`).