# Pioneer

> Docs for building, fine-tuning, evaluating, and deploying models with Pioneer.

## Docs

- [Drop us in. We'll ship the models.](https://docs.pioneer.ai/introduction.md): Pioneer spots where your model fails, then quietly retrains it on your own data — fine-tuning, evaluation, and deployment with no MLOps team required.
- [Pioneer quickstart: from signup to your first inference](https://docs.pioneer.ai/quickstart.md): Go from zero to a working Pioneer inference call in minutes. Generate an API key, browse available models, and run your first NER prediction.
- [CLI installation](https://docs.pioneer.ai/CLI-Installation.md): Install the Pioneer CLI on macOS, Linux, or Windows, authenticate with your API key, and verify the setup by running your first command in the terminal.
- [How to authenticate your requests with Pioneer API](https://docs.pioneer.ai/authentication.md): Generate an API key from your Pioneer account, then include it in the X-API-Key header on every request. No OAuth or token refresh required.
- [Set up Claude Opus 5 with Pioneer in 60 seconds](https://docs.pioneer.ai/api-reference/integrating-with-opus-5.md): Point Claude Code at Pioneer's inference endpoint and start using Claude Opus 5 in under a minute, then swap models on the fly with the /model command.
- [Claude Code](https://docs.pioneer.ai/claude-code.md): Point Claude Code at Pioneer for multi-model inference with router-backed pioneer/auto routing, model discovery, and full /model picker support inside the CLI.
- [Codex](https://docs.pioneer.ai/codex.md): Configure the OpenAI Codex CLI to run against Pioneer's OpenAI-compatible endpoint, load a fresh model catalog, and default to pioneer/auto routing.
- [Cursor](https://docs.pioneer.ai/cursor.md): Configure Cursor's chat panel to use Pioneer's OpenAI-compatible API, add custom models, and switch between them from the model picker.
- [Use Pioneer with OpenClaw as a custom provider](https://docs.pioneer.ai/openclaw.md): Configure OpenClaw to use Pioneer's OpenAI-compatible endpoint, discover models via /v1/models, and run the local gateway with Pioneer Auto.
- [Hermes Agent](https://docs.pioneer.ai/hermes.md): Configure Hermes Agent with Pioneer using a one-time setup command that imports a filtered model catalog and defaults to Claude Opus 5.
- [OpenCode](https://docs.pioneer.ai/opencode.md): Connect the OpenCode CLI or desktop app to Pioneer to route model calls, switch between 70+ models, and optionally enable Exa-powered web search.
- [Pioneer model catalog: encoders, decoders, and inference](https://docs.pioneer.ai/concepts/models.md): Browse Pioneer's encoder (GLiNER) and decoder (LLM) models for fine-tuning and inference. Covers on-demand vs. serverless and how to query the live catalog.
- [GLiGuard: Safety Moderation SLM](https://docs.pioneer.ai/concepts/g-li-guard.md): Run GLiGuard, Pioneer's open-source 300M safety moderation SLM, to classify prompts and completions for harmful, unsafe, or policy-violating content.
- [GLiNER2-PII: PII Detection SLM](https://docs.pioneer.ai/concepts/g-li-ner-2-pii.md): Run GLiNER2-PII, Pioneer's open-source multilingual PII detection SLM, to identify names, emails, phone numbers, and other personal data in text.
- [Pioneer datasets: create, version, inspect, and delete](https://docs.pioneer.ai/concepts/datasets.md): Pioneer stores and versions your training datasets automatically. Learn how to create them via generation or auto-labeling, then list, inspect, and delete them.
- [Pioneer training jobs: lifecycle, metrics, and weights](https://docs.pioneer.ai/concepts/training.md): Understand how Pioneer training jobs work — from submitting a job and polling status to reading metrics, stopping jobs, and downloading trained model weights.
- [Inference on Pioneer: native, OpenAI, and Anthropic APIs](https://docs.pioneer.ai/concepts/inference.md): Run inference on Pioneer via the native /inference endpoint, OpenAI-compatible chat completions, or Anthropic-compatible messages — all reach the same models.
- [Pioneer Model Router: automatic per-request model selection](https://docs.pioneer.ai/concepts/router.md): The Pioneer Router picks a decoder model per request from Pioneer's supported families, using your configured quality-versus-cost policy and routing rules.
- [Model evaluations in Pioneer: F1, precision, recall](https://docs.pioneer.ai/concepts/evaluations.md): Run Pioneer evaluations to measure F1, precision, and recall on a labeled dataset before deploying your fine-tuned model to production traffic.
- [Pioneer REST API: base URL, auth, and quick reference](https://docs.pioneer.ai/api-reference/overview.md): The Pioneer REST API overview: base URL, authentication, the recommended 5-step workflow from dataset to inference, and links to all endpoint group references.
- [Pioneer API authentication: generate and use API keys](https://docs.pioneer.ai/api-reference/authentication.md): Authenticate Pioneer API requests with the X-API-Key header. Generate keys in the dashboard, then list, rotate, or revoke them programmatically.
- [Pioneer API key management: create, list, and revoke](https://docs.pioneer.ai/api-reference/api-keys.md): Manage Pioneer API keys: create keys in the dashboard, list active keys, and revoke keys programmatically. The secret_key is returned only at creation.
- [Rate limits and credit / spending caps for the Pioneer API](https://docs.pioneer.ai/api-reference/rate-limits.md): Per-endpoint request-rate limits, edge WAF quotas, monthly credit and overage spending caps, 429 handling, and how to request higher limits on the Pioneer API.
- [Pioneer API error codes and response body shapes](https://docs.pioneer.ai/api-reference/errors.md): Every 4xx and 5xx status code the Pioneer API returns, the JSON body shape for each family, and steps to resolve billing, rate-limit, and validation errors.
- [Prompt Caching on Inference](https://docs.pioneer.ai/api-reference/prompt-caching.md): How prompt caching works on Pioneer's inference API — what qualifies for caching, how cached input tokens are billed, and where to view cache hit rates.
- [POST /inference — Pioneer native inference endpoint](https://docs.pioneer.ai/api-reference/inference/pioneer.md): POST /inference runs schema-based predictions on encoder or decoder models. Accepts model_id, text, schema with entities or classifications, and a threshold.
- [OpenAI-compatible chat and completions on Pioneer API](https://docs.pioneer.ai/api-reference/inference/openai-compatible.md): Drop-in OpenAI replacement on Pioneer. Set base_url to https://api.pioneer.ai/v1, use your Pioneer key, and all SDK methods including streaming work unchanged.
- [Anthropic-compatible POST /v1/messages on Pioneer API](https://docs.pioneer.ai/api-reference/inference/anthropic-compatible.md): Use Pioneer as a drop-in Anthropic SDK replacement. Point base_url to https://api.pioneer.ai/v1 and use your Pioneer API key to access fine-tuned models.
- [Inference history and feedback endpoints on Pioneer](https://docs.pioneer.ai/api-reference/inference/history.md): List Pioneer inference history, filter by model or project, retrieve individual results, and submit corrections to improve your model via Adaptive Inference.
- [Dataset management API — list, inspect, and delete](https://docs.pioneer.ai/api-reference/datasets.md): List all datasets in your Pioneer account, inspect version history and example counts, and delete datasets you no longer need. Storage is free on all plans.
- [Synthetic data API — POST /generate and label-existing](https://docs.pioneer.ai/api-reference/synthetic-data.md): Start Pioneer data generation jobs for NER, classification, or decoder tasks, poll job status, and auto-label existing text without manual annotation.
- [Training jobs API — start, poll, stop, and download](https://docs.pioneer.ai/api-reference/training-jobs.md): Submit Pioneer fine-tuning jobs, poll status, stream logs, list checkpoints, download weights, and stop or delete jobs. Supports LoRA and full fine-tuning.
- [Evaluation API — measure model F1 before deploying](https://docs.pioneer.ai/api-reference/evaluations.md): Run Pioneer evaluations against labeled datasets to measure F1, precision, and recall with per-entity breakdowns before promoting a model to production.
- [Fine-tune a GLiNER NER model from data to inference](https://docs.pioneer.ai/guides/fine-tune-ner.md): Train a custom Named Entity Recognition model on your data using Pioneer's GLiNER encoder models, from dataset prep through evaluation and inference.
- [Fine-tune a GLiNER text classification model on Pioneer](https://docs.pioneer.ai/guides/fine-tune-classification.md): Train a custom single- or multi-label text classification model on Pioneer's GLiNER encoders, from dataset prep through evaluation and inference on your data.
- [Fine-tune a GLiNER structured extraction model on Pioneer](https://docs.pioneer.ai/guides/fine-tune-extraction.md): Train a custom JSON extraction model on Pioneer's GLiNER encoders to pull invoices, forms, and structured records out of unstructured text — data to inference.
- [Fine-tune Nemotron 3.5 Lightning on Pioneer](https://docs.pioneer.ai/guides/fine-tune-llm.md): LoRA fine-tune Nemotron 3.5 Lightning on Pioneer with supervised fine-tuning via one training endpoint — from dataset prep to a deployed decoder model.
- [Generate synthetic training data for NER and LLM tasks](https://docs.pioneer.ai/guides/synthetic-data.md): Use Pioneer's data generation API to create labeled NER, classification, and decoder training examples without manual annotation, or auto-label existing text.
- [Adaptive Inference: automatic continuous retraining](https://docs.pioneer.ai/guides/adaptive-inference.md): Pioneer's Adaptive Inference monitors live traffic, collects corrections, retrains a new checkpoint, and promotes it automatically when performance improves.
- [Use Pioneer with AI coding agents via Agent Skills](https://docs.pioneer.ai/guides/agent-skills.md): Add a SKILL.md file to your AI coding agent so Cursor, Claude Code, or similar agents can manage Pioneer datasets, training, and inference autonomously.
- [Pioneer plans: Pro and Enterprise](https://docs.pioneer.ai/pricing.md): Compare Pioneer's Pro and Enterprise plans. Start with $40 of platform credits on Pro plans and scale to advanced features on Enterprise as your needs grow.
- [Pioneer FAQ: plans, data privacy, storage, and teams](https://docs.pioneer.ai/faq.md): Answers to common questions about Pioneer plans, storage costs, data training practices, team collaboration, and special pricing for nonprofits and students.
- [Legacy pricing (before July 1, 2026)](https://docs.pioneer.ai/legacy-pricing.md): Pioneer's legacy Hobby and Pro plan pricing for accounts created before July 1, 2026, and how it compares to the current plan rates and included credits.
- [Trust & Safety](https://docs.pioneer.ai/trust-safety.md): How Pioneer protects your data, secures its infrastructure, and builds AI you can deploy responsibly.
- [Pioneer changelog: new models, features, and deprecations](https://docs.pioneer.ai/changelog.md): Track Pioneer platform updates, including new model releases, deprecations and sunsets, API changes, and bug fixes

## OpenAPI Specs

- [openapi](https://docs.pioneer.ai/openapi.json)