> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pioneer.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Pioneer REST API: base URL, auth, and quick reference

> The Pioneer REST API overview: base URL, authentication, the recommended 5-step workflow from dataset to inference, and links to all endpoint group references.

The Pioneer REST API lets you run inference, manage datasets, start training jobs, and evaluate models programmatically. All resources live under a single base URL, and every request is authenticated with your API key. Pioneer also exposes OpenAI- and Anthropic-compatible endpoints so you can integrate with any tool that already supports those formats.

**Base URL:** `https://api.pioneer.ai`

## Authentication

Every request requires an `X-API-Key` header. Generate your key at [pioneer.ai](https://pioneer.ai) → **Settings** → **API Keys**. See the [Authentication](/api-reference/authentication) page for full details, including key management endpoints.

## Recommended workflow

Follow this sequence when you're building a fine-tuned model end to end:

<Steps>
  <Step title="Create or upload a dataset">
    Use `POST /generate` to generate synthetic labeled data — the response includes a `job_id`, poll `GET /generate/jobs/{job_id}` until status returns `ready`.

    To upload your own labeled data, use the three-step upload flow:

    1. Call `POST /felix/datasets/upload/url` to get a presigned S3 URL,
    2. `PUT` your file directly to S3
    3. Call `POST /felix/datasets/upload/process` to trigger processing.

    Poll `GET /felix/datasets/{name}/{version}` until status is `ready`.<br />See the [Datasets](/api-reference/datasets) page for full details.
  </Step>

  <Step title="Start a training job">
    Call `POST /felix/training-jobs` with your model\_name, datasets, and base\_model. The response includes a `job_id` — save it for the following steps.
  </Step>

  <Step title="Poll training status">
    Call `GET /felix/training-jobs/:id` repeatedly until the status field is `complete`. Completed jobs include F1, precision, and recall metrics.
  </Step>

  <Step title="Run an evaluation">
    Call `POST /felix/evaluations` with your training job ID and a held-out dataset name to validate performance before you serve traffic.
  </Step>

  <Step title="Run inference">
    Call `POST /inference` with `base_model` set to your training job ID and dataset\_name set to your held out dataset. You can also use any base model ID (for example `fastino/gliner2-base-v1`) without fine-tuning.
  </Step>
</Steps>

<Note>
  Replace placeholder values such as `YOUR_DATASET_NAME` and `YOUR_TRAINING_JOB_ID` with real values before running any example commands.
</Note>

## Endpoint groups

<CardGroup cols={2}>
  <Card title="Inference" icon="bolt" href="/api-reference/inference/pioneer">
    Run predictions against fine-tuned or base models using the Pioneer format, or via drop-in OpenAI- and Anthropic-compatible endpoints.
  </Card>

  <Card title="Training & Data" icon="database" href="/api-reference/datasets">
    Manage datasets, generate synthetic training data, start and monitor training jobs, and run evaluations.
  </Card>

  <Card title="Projects" icon="folder" href="/api-reference/projects">
    Organize resources into projects, deploy trained models, and run inference against a project endpoint.
  </Card>

  <Card title="API Keys" icon="key" href="/api-reference/api-keys">
    Create, list, and revoke API keys programmatically.
  </Card>
</CardGroup>

## OpenAI and Anthropic compatibility

Pioneer exposes drop-in replacements for the OpenAI and Anthropic SDKs. Point your existing client at `https://api.pioneer.ai/v1` and use your Pioneer API key — no other changes are required.

| SDK       | Base URL                    | Notes                                                         |
| --------- | --------------------------- | ------------------------------------------------------------- |
| OpenAI    | `https://api.pioneer.ai/v1` | Set `base_url`; pass Pioneer-specific fields via `extra_body` |
| Anthropic | `https://api.pioneer.ai/v1` | Set `base_url`; supports streaming                            |

Pass Pioneer-specific fields like `schema` using `extra_body` (OpenAI SDK) or the equivalent extra-parameters mechanism for your client library.