canonical: https://jentic.com/apis/elopstudio.com/elopstudio # Elopstudio AI Wave API The AI Wave API delivers a single normalized feed of AI model changes, merging vendor release notes, Hugging Face uploads, the OpenRouter catalog, and GitHub, and collapsing duplicate entries for the same model. It serves a change feed, a model list, and per-model price history, a daily digest of what moved, and a token-cost estimate, and it registers webhooks so a change pushes to your endpoint. Pricing and context values come from the OpenRouter public catalog, so when only those are needed the source can be called directly. ## For AI agents Track AI model changes in one normalized feed: new releases, price history, and a daily digest across vendor notes, Hugging Face, OpenRouter, and GitHub, with webhooks for updates and a token-cost estimate. ## Scope Does not run inference, host models, or route prompts. Use for tracking AI model changes, pricing history, and cost estimates only. ## Capabilities - Read a normalized feed of AI model changes across vendors and sources - List tracked models and read per-model price history - Get a daily digest of what changed across models - Estimate token cost for a model from the catalog - Register webhooks so a model change pushes to your endpoint - Re-enable or remove a webhook subscription ## Use cases ### Agent that reacts to model changes An agent keeps its model choices current. Through Jentic the agent registers a webhook and reads the normalized change feed, so when a model is released, repriced, or deprecated across vendor notes, Hugging Face, OpenRouter, or GitHub, the agent learns about it and can switch. Duplicate entries for the same model are already collapsed. Example prompt: Register a webhook for model changes, then read the change feed and flag any tracked model that was repriced ### Model price monitoring A team watches what its models cost over time. The model list and per-model price-history calls return how pricing has moved, and the daily digest summarizes the day's changes, so a workflow can chart price trends and catch an increase. Pricing comes from the OpenRouter public catalog. Example prompt: Read a model's price history, compare it with the daily digest, and report any model whose price rose ### Cost estimation before a run An agent estimates spend before it commits. The estimate operation returns a token-cost estimate for a model drawn from the catalog, so a workflow can compare candidate models on price before routing a prompt. The model list supplies the identifiers to estimate against. Example prompt: Estimate the token cost for a prompt on two candidate models and return the cheaper one ## Key endpoints | Method | Path | Description | | --- | --- | --- | | GET | `/api/v1/changes` | Read the model change feed | | GET | `/api/v1/models` | List tracked models | | GET | `/api/v1/models/{slug}/history` | Read a model's price history | | GET | `/api/v1/digest` | Get today's digest of changes | | POST | `/api/v1/estimate` | Estimate token cost for a model | | POST | `/api/webhooks` | Register a webhook | | GET | `/api/webhooks` | List webhook addresses | | DELETE | `/api/webhooks/{id}` | Remove a webhook | ## Key resources - **Changes** — A normalized feed of AI model changes across sources - **Models** — The tracked model list and per-model price history - **Digest** — A daily summary of what changed - **Estimate** — A token-cost estimate for a model from the catalog - **Webhooks** — Register, list, re-enable, and remove change notifications ## 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:** 61 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 74 / 100 - Developer Experience & Jentic Compatibility: 65 / 100 - AI-Readiness & Agent Experience: 46 / 100 - Agent Usability: 94 / 100 - Security: 60 / 100 - AI Discoverability: 49 / 100 - **View full report:** https://jentic.com/apis/elopstudio.com/elopstudio/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 Wave API by hand means handling its bearer key, reconciling model names across vendor notes, Hugging Face, OpenRouter, and GitHub, and managing webhook subscriptions yourself. Through Jentic you install once, import AI Wave from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** AI Wave is mostly read-only, and its webhook id travels in the URL path (`/api/webhooks/{id}`), so a rule bounds your agent to the operations it needs: reading the change feed, model list, and price history. Registering or removing webhooks is not included unless you add it. - **Credential handling:** Your AI Wave 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 'get today's model changes' or 'read a model's price history', and Jentic returns the matching AI Wave operation with its input schema so the agent calls the right endpoint without reading the reference docs. ## Related APIs - **OpenRouter** — Serves a live model catalog with pricing and routes prompts to models - **Hugging Face Hub** — Hosts the model repositories whose uploads feed the change feed - **Portkey AI Gateway** — Routes and observes LLM calls across providers ## FAQ ### What authentication does the AI Wave API use? The AI Wave API authenticates with a bearer API key per its OpenAPI spec, issued from your member dashboard and sent as `Authorization: Bearer ...`. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's context. ### Is there an AI Wave MCP server? You don't need to wire a separate MCP server to give your agent the AI Wave API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent reads the change feed and price history on demand without loading extra tool definitions into its context. ### Can I track a model's price history with the AI Wave API? Yes. The model list returns the models AI Wave tracks, and a per-model history call returns its pricing over time. A daily digest summarizes what changed, and you can register a webhook to be notified when a model moves. ### What are the rate limits for the AI Wave API? The OpenAPI spec does not state specific rate limits. Check the provider's documentation at https://aiwave.elopstudio.com for the limits that apply to your key before polling the change feed heavily. ### Can I limit what my agent is allowed to do with the AI Wave API? Yes. Write a rule that allows only the read operations your agent needs, such as the change feed, model list, and price history, so registering or removing webhooks stays out of its reach. Every call it makes is logged. ### How do I get today's model changes with the AI Wave API through Jentic? Search Jentic for 'get today's AI model changes' and it returns the digest operation with its input schema; your agent reads back the day's released, repriced, and deprecated models. To run it on your own infrastructure, install Jentic One from its GitHub repo.