canonical: https://jentic.com/apis/thesmsworks.co.uk/the-sms-works-api # The SMS Works API The SMS Works provides a low-cost, reliable SMS API for developers. Pay only for delivered texts, all failed messages are refunded. The API exposes 18 endpoints secured with apiKey authentication. ## For AI agents Programmatically sendflashmessage. Covers 18 operations with apiKey authentication. ## Scope Does not handle payments, crm, or developer tools - use for communications only. ## Capabilities - sendFlashMessage - Manage communications data programmatically - Integrate The SMS Works API into automated workflows - Query and filter The SMS Works API records by parameters - Monitor The SMS Works API operational status and events ## Use cases ### Communications Operations Use the The SMS Works API to perform communications operations programmatically. The API provides 18 endpoints covering core functionality including sendflashmessage. Example prompt: Call POST `/message/flash` to sendflashmessage ### Data Retrieval and Monitoring Query The SMS Works API resources on a schedule to track changes, generate alerts, or feed downstream dashboards. Agents poll relevant endpoints, compare against previous state, and trigger actions when thresholds are crossed. Example prompt: Poll the primary The SMS Works API endpoint, compare response to last known state, and alert if changed ### AI Agent Integration via Jentic AI agents discover and call The SMS Works API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually. Example prompt: Search Jentic for 'sendflashmessage', load the operation schema, and execute with Jentic-managed credentials ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/message/flash` | sendFlashMessage | ## Key resources - **Batch** — Operations for batch - **Batches** — Operations for batches - **Credits** — Operations for credits - **Message** — Operations for message - **Messages** — Operations for messages ## 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:** 39 / 100 - **Maturity:** Non-Ready - **Dimensions:** - Foundational Compliance: 64 / 100 - Developer Experience & Jentic Compatibility: 71 / 100 - AI-Readiness & Agent Experience: 16 / 100 - Agent Usability: 94 / 100 - Security: 50 / 100 - AI Discoverability: 100 / 100 - **View full report:** https://jentic.com/apis/thesmsworks.co.uk/the-sms-works-api/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 SMS Works by hand means exchanging your credentials for a JWT, passing it in the Authorization header on each send, and handling your own retries. Through Jentic you install once, import The SMS Works from the API Directory, store the credential once, and your agent calls it. - **Permission scoping:** The SMS Works takes the recipient in the request body rather than an owned URL path, so scope it by operations: limit the agent to the operations it needs, such as sending a flash message, and leave out anything else. Every operation you credit it with stays inside that allowed set. - **Credential handling:** Your The SMS Works credential 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 'send a flash SMS', and Jentic returns the matching The SMS Works operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Twilio** — Alternative communications API - **Sendgrid** — Alternative communications API - **Pusher** — Complementary communications API ## FAQ ### What authentication does the The SMS Works API use? The The SMS Works API uses an API key passed in the `Authorization` header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context. ### Can I sendflashmessage with the The SMS Works API? Yes. Use the POST `/message/flash` endpoint. The API returns structured JSON responses that agents can parse and act on directly. ### What are the rate limits for the The SMS Works API? Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer. ### How do I sendflashmessage through Jentic? Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'sendflashmessage'. Jentic returns the matching The SMS Works API operation with its input schema. Load the schema and execute the call - credentials are injected automatically. ### How many endpoints does the The SMS Works API have? The The SMS Works API exposes 18 endpoints covering batch, batches, credits operations. ### Can I limit what my agent is allowed to do with the The SMS Works API? Yes. Because The SMS Works takes the recipient in the request body rather than an owned URL path, you scope the agent by operations in your self-hosted Jentic One instance, where your own rules decide which operations and credentials the agent may use. Grant it only the operations it needs, such as POST `/message/flash` to send a flash message, and leave out the rest of the 18 endpoints like credits, batches, and message queries. Every operation you credit the agent with stays inside that allowed set, and anything you do not grant it cannot call.