canonical: https://jentic.com/apis/sinch.com/sinch

# Sinch Conversation API

The Sinch Conversation API enables sending and receiving messages globally across SMS, RCS, WhatsApp, Viber Business, Facebook Messenger, and other channels through a unified interface. The API exposes 22 endpoints secured with basic, oauth2 authentication.

## For AI agents

Programmatically send a message, get a message. Covers 22 operations with basic, oauth2 authentication.

## Scope

Does not handle payments, crm, or developer tools - use for communications only.

## Capabilities

- Send a message
- Get a message
- Update message metadata
- Delete a message
- List messages
- Fetch last message
- Create an app

## Use cases

### Communications Operations

Use the Sinch Conversation API to perform communications operations programmatically. The API provides 22 endpoints covering core functionality including send a message, get a message, update message metadata.

Example prompt: Call POST /v1/projects/{project_id}/messages:send to send a message

### Automated Apps Management

Automate apps operations by combining multiple Sinch Conversation API endpoints. Agents can get a message and then update message metadata in a single workflow.

Example prompt: Call GET /v1/projects/{project_id}/messages/{message_id} to get a message, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Sinch Conversation 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 basic, oauth2 tokens manually.

Example prompt: Search Jentic for 'send a message', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | /v1/projects/{project_id}/messages:send | Send a message |
| GET | /v1/projects/{project_id}/messages/{message_id} | Get a message |
| PATCH | /v1/projects/{project_id}/messages/{message_id} | Update message metadata |
| DELETE | /v1/projects/{project_id}/messages/{message_id} | Delete a message |
| GET | /v1/projects/{project_id}/messages | List messages |
| POST | /v1/projects/{project_id}/messages:fetch-last-message | Fetch last message |
| POST | /v1/projects/{project_id}/apps | Create an app |
| GET | /v1/projects/{project_id}/apps | List apps |

## Key resources

- **Apps** — Operations related to Apps
- **Capability** — Operations related to Capability
- **Contacts** — Operations related to Contacts
- **Conversations** — Operations related to Conversations
- **Messages** — Operations related to Messages

## Why Jentic

- **Setup:** Wiring the Sinch Conversation API by hand means handling its OAuth2 or basic auth, choosing the right US, EU, or BR region host, and carrying tokens across every message call yourself. Through Jentic you install once, import Sinch from the API Directory, store the credentials once, and your agent calls it.
- **Permission scoping:** Sinch puts the project id and message id in the URL path (/v1/projects/{project_id}/messages/{message_id}), so a rule can pin your agent to one project: it can send and read messages there and nothing else. You choose the operations it may call, so destructive ones like deleting a message or creating apps are not included unless you add them.
- **Credential handling:** Your Sinch credentials are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'send a message' or 'fetch the last message in a conversation', and Jentic returns the matching Sinch 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 Sinch Conversation API use?

The Sinch Conversation API uses basic, oauth2 authentication. 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 send a message with the Sinch Conversation API?

Yes. Use the POST /v1/projects/{project_id}/messages:send endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Sinch Conversation 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 send a message through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'send a message'. Jentic returns the matching Sinch Conversation API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Sinch Conversation API have?

The Sinch Conversation API exposes 22 endpoints covering apps, capability, contacts operations.

### Can I limit what my agent is allowed to do with the Sinch Conversation API?

Yes. Because you run Jentic One yourself, your own rules decide which Sinch operations and credentials your agent may use. Since Sinch puts the project id and message id in the URL path, a rule can pin the agent to a single project so it only sends and reads messages there. You choose the operations it may call, so destructive ones like deleting a message or creating apps stay off limits unless you explicitly add them.