canonical: https://jentic.com/apis/respan.ai/respan

# Respan AI API

Respan AI (formerly Keywords AI) API gateway providing OpenAI-compatible chat completions with load balancing, fallback models, caching, and observability features. The API exposes 1 endpoints secured with bearer authentication.

## For AI agents

Programmatically create chat completion. Covers 1 operations with bearer authentication.

## Scope

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

## Capabilities

- Create chat completion
- Manage communications data programmatically
- Integrate Respan AI API into automated workflows
- Query and filter Respan AI API records by parameters
- Monitor Respan AI API operational status and events

## Use cases

### Communications Operations

Use the Respan AI API to perform communications operations programmatically. The API provides 1 endpoints covering core functionality including create chat completion.

Example prompt: Call POST `/chat/completions` to create chat completion

### Data Retrieval and Monitoring

Query Respan AI 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 Respan AI API endpoint, compare response to last known state, and alert if changed

### AI Agent Integration via Jentic

AI agents discover and call Respan AI 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 bearer tokens manually.

Example prompt: Search Jentic for 'create chat completion', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/chat/completions` | Create chat completion |

## Key resources

- **Chat** — Chat completions gateway

## Why Jentic

- **Setup:** Wiring Respan AI by hand means setting its bearer auth on every request against the api.respan.ai/api host and shaping chat completion payloads yourself. Through Jentic you install once, import the Respan AI API from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** Respan AI exposes a single chat completions operation rather than a resource id in the path, so limit the agent to that one operation. You choose whether to grant it, and there is no broader surface it can reach.
- **Credential handling:** Your Respan AI 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 'create a chat completion', and Jentic returns the matching Respan AI 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 Respan AI API use?

The Respan AI API uses a Bearer token 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 create chat completion with the Respan AI API?

Yes. Use the POST `/chat/completions` endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Respan AI 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 create chat completion through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'create chat completion'. Jentic returns the matching Respan AI API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Respan AI API have?

The Respan AI API exposes 1 endpoints covering chat operations.

### Can I limit what my agent is allowed to do with the Respan AI API?

Yes. Because you run Jentic One yourself, you decide which operations and credentials your agent may use, and the Respan AI API exposes only a single chat completions operation (POST `/chat/completions`). You can grant your agent that one operation and no other, since there is no broader resource surface it can reach. Your Respan AI bearer token stays under your own rules and is injected only when that call runs.