canonical: https://jentic.com/apis/gessa.ai/gessa # Gessa Game Platform API The Game Platform API runs asynchronous content generation jobs against named capabilities on the Gessa platform. An agent lists the capabilities its organization can use, quotes a job to see its cost, then creates the job with an input payload, a normal or fast lane, a priority, and a budget. While the job runs it can list or stream the job's events, and once the job finishes it downloads the produced draft or cancels a job still in progress. Responses are JSON and authentication is an organization API key or a short-lived capability token. ## For AI agents Run asynchronous generation jobs against named capabilities, quote their cost first, stream job events, and download the resulting draft. Authenticates with an organization API key or a short-lived capability token in a request header. ## Scope Does not handle asset hosting, player accounts, or payment processing. Use for running content generation jobs only. ## Capabilities - Create an asynchronous generation job from a named capability - Quote the cost of a generation job before running it - List the generation capabilities available to an organization - Stream a generation job's events as it progresses - Download the draft a completed generation job produced - Cancel a generation job that is still running ## Use cases ### Agent-Run Content Generation An AI agent building game content can call the Game Platform API through Jentic to run a generation job end to end: it lists the available capabilities, quotes the job, creates it, and downloads the draft once it finishes. The agent drives the whole flow without the developer wiring the API key or capability-token auth or the job polling by hand. Jentic returns the matching operation and its input schema so the agent runs the job inline. Example prompt: Quote a generation job for a chosen capability, create it if the cost is acceptable, and download the draft once it completes ### Cost-Checked Generation A service that generates content on a budget can quote every job before it runs so it never starts work it cannot afford. The quote operation returns the expected cost for a capability and input, and the create operation accepts a budget and a priority, so a workflow decides whether and how urgently to run each job. Example prompt: Quote a job, and only create it when the returned cost is within a set budget, using the fast lane for urgent jobs ### Job Monitoring and Retrieval A dashboard or pipeline that kicks off long-running generation can follow each job's progress and collect the output when ready. The Game Platform API lists a job's events, streams them live as the job runs, serves the finished draft for download, and cancels a job that is no longer needed. Example prompt: Stream a running job's events, then download its draft when the stream reports completion ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/api/generation/jobs` | Create a generation job | | GET | `/api/generation/jobs` | List generation jobs | | POST | `/api/generation/quote` | Quote a generation job | | GET | `/api/generation/capabilities` | List available generation capabilities | | GET | `/api/generation/jobs/{jobId}` | Get a generation job | | GET | `/api/generation/jobs/{jobId}/draft` | Download a generation draft | | POST | `/api/generation/jobs/{jobId}/cancel` | Cancel a generation job | ## Key resources - **Capabilities** — List the generation capabilities available to an organization. - **Quotes** — Estimate the cost of a generation job before running it. - **Jobs** — Create, list, read, and cancel generation jobs. - **Job Events and Drafts** — List or stream a job's events and download the draft it produced. ## 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:** 70 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 100 / 100 - Developer Experience & Jentic Compatibility: 69 / 100 - AI-Readiness & Agent Experience: 53 / 100 - Agent Usability: 94 / 100 - Security: 50 / 100 - AI Discoverability: 98 / 100 - **View full report:** https://jentic.com/apis/gessa.ai/gessa/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 Game Platform API by hand means handling either its organization API key or its short-lived capability token, quoting a job before you create it, and polling or streaming the job events until a draft is ready. Through Jentic you install once, import it from the API Directory, store the credential once, and your agent calls it. - **Permission scoping:** Gessa puts the job id in the URL path for the job operations, so a rule can bound your agent to the operations it needs. You choose which it may call, so job cancellation is not included unless you add it. - **Credential handling:** Your Gessa key or capability token 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 'run a generation job' or 'quote a job', and Jentic returns the matching Game Platform operation with its input schema so the agent calls the right endpoint directly. ## Related APIs - **fal Platform APIs** — Also queues generative model inference and estimates job pricing first. - **Replicate API** — Runs predictions on open-source models as async jobs you poll for results. - **Baseten management API** — Deploys and autoscales your own model infrastructure behind an API. ## FAQ ### What authentication does the Game Platform API use? The Game Platform API accepts an organization-scoped API key in the x-api-key header or a short-lived capability token in the x-capability-token header, per its OpenAPI spec. Through Jentic the credential is stored once, encrypted, by your own Jentic One instance and injected at call time, so it never reaches the agent's prompt or logs. ### Is there a Game Platform MCP server? You don't need an MCP server to give your agent the Game Platform API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent can quote and run generation jobs straight away. ### Can I limit what my agent is allowed to do with the Game Platform API? Yes. Gessa puts the job id in the URL path for job operations, so a rule can bound your agent to the job operations it needs. Allow it to quote, create, and read jobs but leave cancellation out unless you add it, and every call it makes is logged. ### Can I estimate the cost of a job before running it with the Game Platform API? Yes. The quote operation takes the same request as a job, such as the capability and input, and returns the expected cost, so an agent can decide whether to create the job and can set a budget and priority when it does. ### What are the rate limits for the Game Platform API? The OpenAPI spec does not publish a numeric rate limit; instead a job request carries a priority and a budget that control its ordering and spend. Check the Gessa documentation for the current limits on your plan. ### How do I run a generation job with the Game Platform API through Jentic? Search Jentic for an intent like 'run a content generation job' and it returns the Game Platform create-job operation with its input schema, so your agent submits the capability and input and collects the draft. To run it on your own infrastructure, install Jentic One from its GitHub repo.