canonical: https://jentic.com/apis/aicontentdrop.com/aicontentdrop # AI Content Drop API The AI Content Drop API generates AI video and images on your own account and runs autonomous content drops. Generation is submit-and-poll: a request returns a record with status generating, and polling a video by its id reports when it is completed, with credits charged flat per model and only on success. A model catalogue lists each model's credit cost, and a drop engine starts runs you steer with chat, answers, approvals, and interjections. Account, plan, and credit-balance endpoints round out the surface. ## For AI agents Generate AI video and images on your account, poll them to completion, browse model costs, and run steerable content drops through a drop engine. ## Scope Does not host a video CDN, edit uploaded footage, or manage a stock media library. Use for generating AI video and images and running content drops only. ## Capabilities - Start an AI video generation and poll it by id until it completes - Start an AI image generation on your account - Browse the model catalogue and estimate a model's credit cost - Read account details, credit balance, and available plans - Start a content drop and steer it with chat, answers, approvals, and interjections - Mint or revoke a public share link for a drop - Register an agent for a read-scoped token and exchange client credentials for a fresh token ## Use cases ### Agent-Generated Video and Images An AI agent connecting through Jentic can produce media on your account without a dashboard: it starts a video or image generation, then polls the record by its id until the status reaches completed. Jentic injects the bearer token at call time, so the agent runs the submit-and-poll flow without ever holding the key in its prompt, and credits are only charged on success. Example prompt: Start a video generation with a chosen model, then poll the video by its id until its status is completed and return the result URL ### Submit-and-Poll Generation with Cost Control Keep generation spend predictable. The AI Content Drop API lists each model's flat credit cost, estimates the cost for one model or many at once, and charges credits only on success so safety blocks, provider failures, and timeouts cost nothing. An agent can price a job against the account's balance before committing to a generation. Example prompt: Estimate the credit cost for a model, compare it with the account balance from the account endpoint, then start the generation ### Steerable Content Drops Run a longer content job as a drop the agent can guide. The AI Content Drop API starts a drop, reads it in full, and accepts chat, answers to the drop's questions, approvals of decisions it is waiting on, and interjections to steer a drop that is already working, plus a share link so the result can be handed out. Example prompt: Start a drop, answer the questions it asks, approve the decision it is waiting on, then mint a public share link for the finished drop ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/v1/generate/video` | Start a video generation | | POST | `/v1/generate/image` | Start an image generation | | GET | `/v1/videos/{id}` | Poll a generation by id | | GET | `/v1/videos` | List recent generations | | GET | `/v1/models` | List the model catalogue with credit costs | | POST | `/v1/engine/runs` | Start a content drop | | GET | `/v1/me` | Read account and credit balance | ## Key resources - **Generation** — Start video and image generations and poll or list the resulting records - **Models and plans** — List the model catalogue, estimate credit costs, and read plans and the free tier - **Account** — Read account details, credit balance, and run read operations in a single batch - **Drop engine** — Start, read, rename, and delete drops and steer them with chat, answers, approvals, and interjections - **Agent auth** — Register an agent for a read-scoped token, claim a fresh token, and revoke one ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 64 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 52 / 100 - Developer Experience & Jentic Compatibility: 70 / 100 - AI-Readiness & Agent Experience: 53 / 100 - Agent Usability: 94 / 100 - Security: 60 / 100 - AI Discoverability: 86 / 100 - **View full report:** https://jentic.com/apis/aicontentdrop.com/aicontentdrop/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring the AI Content Drop API by hand means creating an API key, carrying it as a bearer token, and handling the submit-and-poll generation flow and per-model credit costs yourself. Through Jentic you install once, import AI Content Drop from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** You choose which AI Content Drop operations your agent may call, so it can start and poll generations while deleting a drop or revoking a token stays out unless you add them. Video and drop ids travel in the URL path (`/v1/engine/runs/{id}`), so a rule can also pin the agent to one drop. - **Credential handling:** Your AI Content Drop key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'generate an AI video' or 'estimate a model cost', and Jentic returns the matching AI Content Drop operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Runway** — Runway generates and edits AI video from prompts and references. - **Shotstack** — Shotstack renders and edits video programmatically from a timeline. - **Mux** — Mux hosts, streams, and measures video delivery. ## FAQ ### What authentication does the AI Content Drop API use? The AI Content Drop API authenticates with an API key created in your dashboard and sent as a bearer token, with keys that look like acd_live_ values. The index, the model catalogue, and the natural-language ask endpoint need no key, while anything that touches an account or spends credits does. Through Jentic the key is injected at call time rather than living in the agent's prompt. ### Can I generate a video and check when it is ready with the AI Content Drop API? Yes. A generate request returns a record immediately with status generating, and you poll the video by its id until the status reaches completed. Credits are flat per model and are only charged on success, so safety blocks, provider failures, and timeouts cost nothing. ### What are the rate limits for the AI Content Drop API? The spec states a limit of 120 requests per minute, and every response carries the RateLimit-Limit, RateLimit-Remaining, and RateLimit-Reset headers, with a 429 when you exceed it. Check the AI Content Drop documentation at https://aicontentdrop.com for any tier-specific limits. ### How do I generate a video with the AI Content Drop API through Jentic? Search Jentic for 'generate an AI video' and it returns the video generation operation with its input schema. Your agent starts the generation, then polls the video by its id until it is completed. To run it on your own infrastructure, install Jentic One from its GitHub repo. ### Can I limit what my agent is allowed to do with the AI Content Drop API? Yes. Write a rule that allows only the generation and polling operations, so the agent can create and read media while deleting a drop or revoking a token stays out unless you add it, and every action it takes is logged. Because video and drop ids appear in the URL path, a rule can also pin the agent to one drop. ### Is there an AI Content Drop MCP server? You don't need an MCP server to give your agent the AI Content Drop API. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls the generation, model, and drop operations on demand without loading another server's tool definitions into its context.