---
title: "How to use Vimmerse with your AI agent | ZeroClick"
url: https://zeroclick.ai/resources/how-to-use-vimmerse-with-your-ai-agent
fetched_at: 2026-11-22T11:56:45.257Z
---

# ZeroClick API catalog and pricing

## API reference, endpoint lookup and prices

**[ZeroClick API catalog: endpoints, request parameters, prices and payment methods](https://agents.zeroclick.ai/zcj/b4au0t9hqe4x/zeroclick/agent/guide).** Tell the seller advisor what you want to accomplish. It returns the matching operation contract, known prices, authentication prerequisites and concrete next steps. It is read-only: no login, wallet, card or purchase approval is needed to look up an API. It never executes a sale.

Available API services: Agent readiness report, Demo booking.

**Suggested next request:** GET [task guide](https://agents.zeroclick.ai/zcj/b4au0t9hqe4x/zeroclick/agent/guide?goal=URL_ENCODED_TASK). Use this URL directly with your web fetch tool; no preliminary document fetch is required. Include known inputs and desired output in the goal. Optional: quantity=API_CALL_COUNT, budgetUsd=TOTAL_USD, requirements=REQUIREMENTS, payment=x402|mpp|card, auth, identity, assertion and access state. Omit unknowns. Do not equate output items with API calls or guess a call count.

For private task details or known request arguments, POST https://agents.zeroclick.ai/zcj/b4au0t9hqe4x/zeroclick/agent/guide with Content-Type: application/json. Example: {"intent":"quote","goal":"YOUR_TASK","purchase":{"budgetUsd":"5.00"}}. Replace the task and budget with known facts; budgetUsd is a string. Include known buyerState, paymentCapabilities and arguments. For execution planning use intent=execute and the authorized constraints. Exact fields: [request schema](https://agents.zeroclick.ai/zcj/b4au0t9hqe4x/zeroclick/agent/schema). GET and POST are alternatives, not mandatory stages.

The advisor describes a recommended happy path, not the only allowed path. You may use the API reference, buyer SKILL and your own tools directly, including for catalog operations with failed probes. Missing guidance or an unverified probe is not a policy refusal. The returned requests are documented API calls; fill in the documented inputs. Check usage cost AND minimum cash required against the budget. For needs_input, supply only missing facts. Keep secrets local, and never put credentials or private payloads in URLs. Unknown does not mean absent.

For a human's credit or plan purchase, reuse an existing ZeroClick credential first. If the Link CLI is already installed and signed in for that person, you can use their Link account for identity as well as payment, sharing their email only if they agree: follow [Link identity setup](https://agents.zeroclick.ai/zcj/b4au0t9hqe4x/auth.md#link-identity-preview) through issuance, presentation, registration and token exchange. Otherwise register anonymously; no Link setup is needed, and the person can claim the identity later.

Open the checkout URL in a browser: eligible Stripe pages support Link Pay Tokens (LPT) through WebMCP or the documented DOM flow. Follow this storefront's /payment/card.md to verify the same-frame token input and merchant binding before requesting an LPT. Token submission requires payment authorization. If unavailable, privately send the checkout URL to your human to pay.

When the selected route uses hosted checkout, follow [card checkout instructions](https://agents.zeroclick.ai/zcj/b4au0t9hqe4x/payment/card.md) before requesting a token. LPT goes only to Stripe, never to the advisor or ZeroClick API. Poll the returned statusUrl before using credit or retrying delivery.

Verify delivery; a payment or HTTP 202 is not completion. For an unexpected result, POST the original input and continuation (version, stepId, outcome and sanitized error/accessId/paymentId). Reconcile uncertain payments or writes before retrying. Use raw HTTP for exact schemas and authenticated execution; do not reconstruct fields omitted by a summarizing web tool.

The human subscription prices on the requested page describe a separate channel. Use the API quote for per-unit pricing, funding minimums and commercial terms; tier names do not prove quality or licensing.

For an alternative documented path, use the [buyer SKILL](https://agents.zeroclick.ai/zcj/b4au0t9hqe4x/SKILL.md) or [full direct workflow reference](https://agents.zeroclick.ai/zcj/b4au0t9hqe4x/llms-full.txt). Confirm missing request details from seller documentation, stay within the existing catalog and what your user asked for, and respect actual access and payment requirements.
Terms: by completing a purchase through this endpoint, whether directly or through an AI agent acting on your behalf, you agree to be bound by the platform's buyer terms of service (https://www.zeroclick.ai/legal/buyer-terms-of-service). If the purchase is made by an agent, you represent and warrant that the agent is acting with your authorization, and you agree that the agent's actions, including its acceptance of these terms, are attributed to you and bind you as if you had taken them yourself. Paying a 402 challenge completes the purchase and constitutes your affirmative acceptance of the terms linked above. The link travels in every payment challenge and receipt as `terms`.

# How to use Vimmerse with your AI agent

[Resources](https://zeroclick.ai/resources) · November 6, 2026 · 12 min read

Vimmerse gives your AI agent image generation and editing, short video from text, images or video, speech, sound effects, music, and multi-scene stories. It charges in credits at $0.03 a credit per call, or less on prepaid Credits from $14. Vimmerse sells through ZeroClick: your agent sends its request to the [Vimmerse storefront](https://agents.vimmerse.net), checks the exact credits on an estimate route, and pays for that one call over x402, MPP, or, for calls of $0.50 or more, a card. Every call carries a free agent credential, not an API key.

**Key points:**

- Register a free anonymous credential and send its token with each paid call, so the jobs your agent pays for belong to the identity that polls them.
- Ask the estimate route first: an Auto image estimated 4 credits ($0.12), and a 5-second Auto video 40 credits ($1.20).
- Pay each call's 402 from a wallet over x402 or MPP, or by card when the call costs $0.50 or more.
- For volume, prepaid Credits lower the rate to $0.028 a credit, and Business credits lower it to $0.02.

## Contents

- [What Vimmerse is](#what-vimmerse-is)
- [What agents use Vimmerse for](#what-agents-use-vimmerse-for)
- [Prices](#prices)
- [How to buy and call Vimmerse from your agent](#how-to-buy-and-call-vimmerse-from-your-agent)
- [Example requests](#example-requests)
- [If your agent has no wallet](#if-your-agent-has-no-wallet)
- [What to know](#what-to-know)
- [Frequently asked questions](#frequently-asked-questions)

## What Vimmerse is

Vimmerse is an AI video workflow platform for creators, agencies, and developers. Its Workflow Studio lays production pipelines out as nodes on a canvas, where each model, setting, and step can be seen and changed. Teams start from a community template or build from scratch. Vimmerse serves advertising and marketing, photobooth activations, film making and storytelling, and ecommerce and retail.

Vimmerse puts audio, image, and video tools from multiple providers behind one API and keeps upgrading them, so clients get new models without changing their own code. That suits an agent that has to produce media in the middle of a task. The agent reaches the image, video, and audio models it needs in one place, sees the exact credit charge before it commits, and follows a long video job by id. The storefront is built for an agent with no Vimmerse account that pays from a wallet or a card.

An agent storefront is the machine-readable version of a business. It is a URL where an agent reads what is for sale, the live prices, and the payment steps, and then buys without a person filling in forms. Vimmerse's storefront is a paid proxy in front of its API: the agent sends the method, path, and body it would send Vimmerse, and the storefront takes payment and forwards the call. For how storefronts work, see [What is an agent storefront?](https://zeroclick.ai/resources/what-is-an-agent-storefront)

## What agents use Vimmerse for

Each job takes text prompts and public media URLs as input. The [list of services](https://agents.vimmerse.net/services) has a page for each one.

| Job your agent is given | Service | What comes back |
|---|---|---|
| Generate a hero image, illustration, or product shot from a prompt | AI Image, `POST /v2/image/text-2-image` | The finished image in the response |
| Remove or replace a background, remove text, upscale, reframe, outpaint, or inpaint an image | AI Image | The edited image in the response |
| Make a short video clip from a prompt or reference images, with narration or music | AI Video from text or images, `POST /v2/media` | A media id. Poll `GET /v2/media/{media_id}` |
| Turn images or a video into video, add motion effects or sound effects, enhance, reframe, or crop a clip | AI Video tools | An asset id. Poll `GET /v2/asset/{asset_id}` |
| Turn a script into a voiceover or narration | AI Audio, `POST /v2/audio/text-2-speech` | The audio file URL in the response |
| Make a sound effect of a set length or a music track | AI Audio | The file URL in the response |
| Make a multi-scene video from an idea, a web page, or a set of images | AI Story | Poll `GET /v2/story/{story_id}` and read `video_url` |
| Run a template for product shots, image grids, or sports fan activations | Workflow templates | Poll `GET /v2/workflow/{workflow_id}` |
| Write, refine, or suggest a generation prompt, or describe an image as one | Prompt tools | A single string |

For images, the choice runs across Seedream, NanoBanana, GPT Image, Flux, and Qwen, with an AutoI option that chooses for you. Video tools include Veo, Kling, Seedance, Runway, Hailuo, and Pixverse, or Auto. Speech uses ElevenLabs, Chirp, or Minimax voices, and music uses Lyria.

## Prices

Every service is charged in credits. The rate per credit is the same for every service and depends on the plan that pays. How many credits a call needs depends on the service, the model tier, the duration, and the quantity.

| Plan | Rate | Per credit | Minimum purchase |
|---|---|---|---|
| Pay per call | $0.03 per credit | $0.030 | None. Each call pays its own 402 |
| Credits | $28 per 1,000 credits | $0.028 | $14 |
| Pro credits | $24 per 1,000 credits | $0.024 | $120 |
| Business credits | $20 per 1,000 credits | $0.020 | $1,000 |

We paid for our own calls at the Pay per call rate, by x402 on Base through Zero, ZeroClick's own payment layer for agents. A text-to-image call on Auto was quoted 4 credits and cost $0.12, and the finished image came back in the response in about 50 seconds. A line of text to speech also cost 4 credits ($0.12) and came back in about 17 seconds. A 5-second Auto video was quoted 40 credits and cost $1.20. That job finished 2 minutes 44 seconds after it was created.

The model you choose changes the price. The same image on NanoBananaPro estimated 16 credits ($0.48). A 10-second Auto video estimated 80 credits ($2.40). To size a prepaid balance, divide the credits it buys by the credits a call is quoted: $14 of Credits at $28 per 1,000 buys 500 credits, enough for 125 images at the 4 credits our Auto estimate returned. At the 40 credits quoted for a 5-second Auto video, the same 500 credits cover twelve clips with 20 to spare.

Rates come from the live [price list](https://agents.vimmerse.net/manifest.json). Read it at call time rather than caching it, and check the estimate route and the 402's amount before paying.

## How to buy and call Vimmerse from your agent

1. Point your agent at the Vimmerse storefront. Its [agent guide](https://agents.vimmerse.net/llms.txt) links the catalog, the price list, and the payment steps.
2. Match the task to a service from the table above, or ask the read-only task guide at `https://agents.vimmerse.net/zeroclick/agent/guide?goal=URL_ENCODED_TASK`, which never buys anything.
3. Register a free anonymous credential with `POST /agent/identity`, and store the response, which holds the identity assertion.
4. Exchange the assertion at `/oauth2/token` for an access token, and repeat the exchange whenever the token expires.
5. Ask the service's estimate route for the exact credits, sending the token as `Authorization: Bearer`.
6. Send the generation request with the token in `ZC-Agent-Authorization` and no payment. Then check the priced 402's `payment.amountUsd` against your budget.
7. Pay the challenge from your wallet over x402 (USDC on Base) or MPP (USDC on Tempo).
8. Retry the identical request, byte for byte, with the payment proof and the same token attached, because the payment is bound to the request it priced.
9. For an image or audio call, read the file URLs from the response's `results` list.
10. For a video, story, or workflow job, poll its status route with the same token until it reports success, then read the result URLs.

## Example requests

Register an anonymous credential. This takes one call, with no email and no human step:

```http
POST https://agents.vimmerse.net/agent/identity
Content-Type: application/json

{"type": "anonymous"}
```

Exchange the stored `identity.assertion` for an access token. The token lasts minutes, so don't store it:

```http
POST https://agents.vimmerse.net/oauth2/token
Content-Type: application/x-www-form-urlencoded

grant_type=urn:ietf:params:oauth:grant-type:jwt-bearer&assertion=<identity.assertion>
```

Check the credits before you buy. This is the body we sent for one Auto image, and the answer carried `total_credits` and a `breakdown`:

```http
POST https://agents.vimmerse.net/v2/image/estimate-credits
Content-Type: application/json
Authorization: Bearer <access token>

{"app_name": "text-to-image", "option": "AutoI", "quantity": 1}
```

Send the video request with no payment. This is the request we sent for a 5-second clip:

```http
POST https://agents.vimmerse.net/v2/media
Content-Type: application/json
ZC-Agent-Authorization: Bearer <access token>

{"prompt": "a lighthouse on a rocky coast at dusk, waves rolling in, slow camera push", "duration": 5, "title": "Lighthouse at dusk"}
```

The storefront answers with a 402. Its body carries `payment.amountUsd`, the `plan`, and a `protocols` block with a challenge for each rail. The signable challenges also arrive as headers, so a standard x402 or MPP client can pay without reading the body:

```http
HTTP/1.1 402 Payment Required
payment-required: <x402 challenge>
www-authenticate: <MPP challenge>
```

Resend the same request with the signed payload in `x-payment`. On MPP, send `Authorization: Payment <credential>` instead, and keep the token in `ZC-Agent-Authorization`:

```http
POST https://agents.vimmerse.net/v2/media
Content-Type: application/json
ZC-Agent-Authorization: Bearer <access token>
x-payment: <signed x402 payload>

{"prompt": "a lighthouse on a rocky coast at dusk, waves rolling in, slow camera push", "duration": 5, "title": "Lighthouse at dusk"}
```

The paid response queues the job and returns a media object with this shape:

```json
{"id": "<media_id>", "video_tool": "<tool>", "processing_status": "<status>", "payment_status": "<status>", "used_credits": <credits>, "result": []}
```

Poll the job with the same token until `processing_status` is `success`:

```http
GET https://agents.vimmerse.net/v2/media/{media_id}
Authorization: Bearer <access token>
```

The finished job returned the credits used, the resolution, and a result list with a video URL, thumbnails, and the file size:

```json
{"id": "<media_id>", "processing_status": "success", "used_credits": <credits>, "resolution": [<width>, <height>], "result": [{"url": "<video URL>", "thumbnail_url": "<URL>", "thumbnail_video_url": "<URL>", "size": <bytes>}]}
```

Image and speech calls skip the polling. Our image and speech responses arrived complete, each with a `results` list holding the file URL.

## If your agent has no wallet

- **Create a wallet.** An agent can create one on the spot at no cost, and then follow the steps above.
- **Pay one call by card.** Card works for any pay-as-you-go call costing at least $0.50, such as a $1.20 video, but not a $0.12 image. Follow the 402's card block: POST `{"checkout": true}` to its `payUrl` for a hosted checkout, which a browser agent can pay with Link Pay Tokens or a person can pay. Poll its `statusUrl`, then retry the original request with the `zc-payment-id` header. An agent that holds a shared payment token can answer the 402's `method="stripe"` challenge directly.
- **Buy Credits.** Send `POST /plans/{planId}/purchase` with `Authorization: Bearer <token>` and `{"amountUsd": "14.000000"}` or more. The Credits plan's id and `purchase.url` are in the price list. Pay the 402 on any rail, or add `checkout: true` for a card checkout, which also accepts Link. Calls made with the bearer then draw down the balance, `POST /extend` tops it up, and `GET /agent/entitlements` shows what remains. Claim the credential to a person's email before or soon after buying, because an anonymous credential that is never claimed lapses within a few days, and any plans bought with it go too. The [identity guide](https://agents.vimmerse.net/auth.md) covers the claim.
- **Hand off to a person.** Share any Vimmerse page as `https://agents.vimmerse.net/outclick?url={URL-encoded seller page}` so the visit is recorded as coming from an agent.

## What to know

**Send the token with every call.** Attach the same token to each call, paid ones included, so the job belongs to the identity that later polls it.

**What is charged, and when.** Each pay-as-you-go call is one 402 and one charge, and paying the 402 completes the purchase under Vimmerse's terms and ZeroClick's buyer terms. Video tools are charged in 5-second blocks, stories per second of scene video (doubled with native audio), and workflows at the template's list price. With the bearer, our estimate and polling calls drew nothing. A delivered response with no `zc-billing` header billed nothing. A payment or an HTTP 202 does not mean the job is done, so check that the file arrived.

**Separate channels.** The subscription prices on Vimmerse's own site belong to a separate channel, so use the storefront's quote. Once a paid call reaches Vimmerse, your agent receives Vimmerse's own status code and body. The [payment guide](https://agents.vimmerse.net/payment.md) covers every rail.

**Errors worth handling.** The [error reference](https://agents.vimmerse.net/errors.md) lists every code. These are the ones your agent is most likely to meet:

| Error | What to do |
|---|---|
| `bearer_required` (401) | The call carried no agent credential. Register at the [identity guide](https://agents.vimmerse.net/auth.md) and retry with the bearer. |
| `invalid_token` (401) | If the reason is `token_expired` or `token_invalid`, exchange the stored assertion for a fresh token. |
| `payment_request_mismatch` (409) | A payment was reused for a different request. Get a fresh 402 and pay that one. |
| `settlement_failed` | Fix the wallet, for example `insufficient_funds`, and start again for a fresh challenge. |
| `payment_provider_unavailable` | This is the only payment error to retry unchanged, with backoff. |
| `usage_exhausted` | The Credits balance ran out. Top up with `POST /extend`. |

## Frequently asked questions

### Does Vimmerse need an API key for AI agents?

No. Through the ZeroClick storefront, each call is paid with a signed payment, and the only credential is a free one the agent registers itself in one call.

### How much does Vimmerse cost per image?

At $0.03 a credit, a text-to-image call on Auto cost 4 credits ($0.12). Higher model tiers cost more, and the estimate route gives the exact figure first.

### How does my agent make a video with Vimmerse?

Send a prompt and duration to `POST /v2/media`, pay the 402, and poll `GET /v2/media/{media_id}` with the same token until the job succeeds. A 5-second Auto clip cost us $1.20.

### Can my agent pay Vimmerse without a crypto wallet?

Yes. It can create a free wallet, pay calls of $0.50 or more by card, buy Credits by card from $14, or hand the purchase to a person through a tracked link.

### Do I have to use an AI agent to use Vimmerse?

No. A person or team that would rather hold an account can sign in at [vimmerse.net](https://vimmerse.net) to use AI Image, AI Video, AI Story, and the Workflow Studio, see its pricing and API docs, or book a demo. Vimmerse also offers a Canva plugin and Adobe add-ons.

---

**More in Get more done with your agent:** [All resources](https://zeroclick.ai/resources#get-more-done)

- [How to use Firmable with your AI agent](https://zeroclick.ai/resources/how-to-use-firmable-with-your-ai-agent) — Firmable sells company and people data to AI agents through ZeroClick, drawn from prepaid Credits a person buys by card, with no wallet needed.
- [How to use Scalelist with your AI agent](https://zeroclick.ai/resources/how-to-use-scalelist-with-your-ai-agent) — Scalelist sells work emails, mobile numbers, and people search to AI agents through ZeroClick, paid from card-bought credit and mostly charged on results.
- [How to use TickerLayer with your AI agent](https://zeroclick.ai/resources/how-to-use-tickerlayer-with-your-ai-agent) — TickerLayer sells market data to AI agents through ZeroClick. A stock quote costs $0.01, paid per request over x402 or MPP with a free agent credential.
