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

# Pulze.ai API

At Pulze it's our mission to supercharge today's workforce with AI to maximize the world's prosperity. We are doing so by enabling companies of any size to securely leverage Large Language Models (LLM) and easily build AI features into their apps. Our enterprise platform has access to all best in class LLMs and can route user requests to the most relevant model to get the highest quality response . The API exposes 3 endpoints secured with bearer authentication.

## For AI agents

Programmatically chat completions, get rank of best models for payload. Covers 3 operations with bearer authentication.

## Scope

Does not handle payments, communications, or crm - use for hr and recruiting only.

## Capabilities

- Chat Completions
- Get Rank Of Best Models For Payload
- Access Pulze.ai API resources via REST API

## Use cases

### HR and Recruiting Operations

Use the Pulze.ai API to perform hr recruiting operations programmatically. The API provides 3 endpoints covering core functionality including chat completions, get rank of best models for payload, get log by id.

Example prompt: Call POST `/v1/chat/completions` to chat completions

### Automated chat Management

Automate chat operations by combining multiple Pulze.ai API endpoints. Agents can get rank of best models for payload and then get log by id in a single workflow.

Example prompt: Call POST `/v1/models/rank` to get rank of best models for payload, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Pulze.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 'chat completions', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/v1/chat/completions` | Chat Completions |
| POST | `/v1/models/rank` | Get Rank Of Best Models For Payload |
| GET | `/v1/logs/{log_id}` | Get Log By Id |

## Key resources

- **chat** — Operations related to chat
- **models** — Operations related to models
- **logs** — Operations related to logs

## Why Jentic

- **Setup:** Wiring Pulze.ai by hand means setting up its bearer auth and handling model routing and ranking calls yourself. Through Jentic you install once, import the Pulze.ai API from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** Pulze.ai drives chat completions and model ranking from the request body, so scope the agent to the operations it needs, such as creating a completion or ranking models. You choose that allowed set, so log retrieval is not included unless you add it.
- **Credential handling:** Your Pulze.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 'route a chat completion' or 'rank models for a prompt', and Jentic returns the matching Pulze.ai operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Greenhouse** — Alternative hr recruiting API
- **Lever** — Alternative hr recruiting API
- **Workday** — Complementary hr recruiting API

## FAQ

### What authentication does the Pulze.ai API use?

The Pulze.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 chat completions with the Pulze.ai API?

Yes. Use the POST `/v1/chat/completions` endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Pulze.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 chat completions through Jentic?

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

### How many endpoints does the Pulze.ai API have?

The Pulze.ai API exposes 3 endpoints covering chat, models, logs operations.

### Can I limit what my agent is allowed to do with the Pulze.ai API?

Yes. Because you run Jentic One yourself, you decide which Pulze.ai operations your agent may call, so you can allow chat completions on POST `/v1/chat/completions` and model ranking on POST `/v1/models/rank` while leaving out log retrieval on GET `/v1/logs/{log_id}.` The agent can only invoke the operations you include in that allowed set, and your bearer token stays stored on your own instance rather than in the agent's context. This lets you grant just the completion and ranking access an agent needs and nothing more.