# OpenPipe

## Docs

- [Get Model](https://docs.openpipe.ai/api-reference/get-getModel): Get a model by ID. Consult the OpenPipe team before using.
- [List Models](https://docs.openpipe.ai/api-reference/get-listModels): List all models for a project. Consult the OpenPipe team before using.
- [Chat Completions](https://docs.openpipe.ai/api-reference/post-chatcompletions): OpenAI-compatible route for generating inference and optionally logging the request.
- [Judge Criteria](https://docs.openpipe.ai/api-reference/post-criteriajudge): Get a judgement of a completion against the specified criterion
- [Report](https://docs.openpipe.ai/api-reference/post-report): Record request logs from OpenAI models
- [Report Anthropic](https://docs.openpipe.ai/api-reference/post-report-anthropic): Record request logs from Anthropic models
- [Update Log Metadata](https://docs.openpipe.ai/api-reference/post-updatemetadata): Update tags metadata for logged calls matching the provided filters.
- [Base Models](https://docs.openpipe.ai/base-models): Train and compare across a range of the most powerful base models.
- [Caching](https://docs.openpipe.ai/features/caching):  Improve performance and reduce costs by caching previously generated responses.
- [Anthropic Proxy](https://docs.openpipe.ai/features/chat-completions/anthropic)
- [Custom External Models](https://docs.openpipe.ai/features/chat-completions/external-models)
- [Mixture of Agents Chat Completions](https://docs.openpipe.ai/features/chat-completions/moa)
- [Chat Completions](https://docs.openpipe.ai/features/chat-completions/overview)
- [Prompt Prefilling](https://docs.openpipe.ai/features/chat-completions/prompt-prefilling): Use Prompt Prefilling to control the initial output of the completion.
- [Criterion Alignment Sets](https://docs.openpipe.ai/features/criteria/alignment-set): Use alignment sets to test and improve your criteria.
- [API Endpoints](https://docs.openpipe.ai/features/criteria/api): Use the Criteria API for runtime evaluation and offline testing.
- [Criteria](https://docs.openpipe.ai/features/criteria/overview): Align LLM judgements with human ratings to evaluate and improve your models.
- [Criteria Quick Start](https://docs.openpipe.ai/features/criteria/quick-start): Create and align your first criterion.
- [Exporting Data](https://docs.openpipe.ai/features/datasets/exporting-data):  Export your past requests as a JSONL file in their raw form.
- [Importing Request Logs](https://docs.openpipe.ai/features/datasets/importing-logs):  Search and filter your past LLM requests to inspect your responses and build a training dataset.
- [Datasets](https://docs.openpipe.ai/features/datasets/overview): Collect, evaluate, and refine your training data.
- [Datasets Quick Start](https://docs.openpipe.ai/features/datasets/quick-start): Create your first dataset and import training data.
- [Relabeling Data](https://docs.openpipe.ai/features/datasets/relabeling-data): Use powerful models to generate new outputs for your data before training.
- [Uploading Data](https://docs.openpipe.ai/features/datasets/uploading-data):  Upload external data to kickstart your fine-tuning process. Use the OpenAI chat fine-tuning format.
- [Direct Preference Optimization (DPO)](https://docs.openpipe.ai/features/dpo/overview)
- [DPO Quick Start](https://docs.openpipe.ai/features/dpo/quick-start): Train your first DPO fine-tuned model with OpenPipe.
- [Evaluations](https://docs.openpipe.ai/features/evaluations/overview):  Evaluate your fine-tuned models against comparison LLMs like GPT-4 and GPT-4-Turbo. Add and remove models from the evaluation, and customize the evaluation criteria.
- [Evaluations Quick Start](https://docs.openpipe.ai/features/evaluations/quick-start): Create your first head to head evaluation.
- [Fallback options](https://docs.openpipe.ai/features/fallback):  Safeguard your application against potential failures, timeouts, or instabilities that may occur when using experimental or newly released models.
- [Fine Tuning via API (Beta)](https://docs.openpipe.ai/features/fine-tuning/api):  Fine tune your models programmatically through our API.
- [Fine-Tuning Quick Start](https://docs.openpipe.ai/features/fine-tuning/quick-start): Train your first fine-tuned model with OpenPipe.
- [Fine Tuning via Webapp](https://docs.openpipe.ai/features/fine-tuning/webapp):  Fine tune your models on filtered logs or uploaded datasets. Filter by prompt id and exclude requests with an undesirable output.
- [Mixture of Agents](https://docs.openpipe.ai/features/mixture-of-agents): Use Mixture of Agents to increase quality beyond SOTA models.
- [Pruning Rules](https://docs.openpipe.ai/features/pruning-rules): Decrease input token counts by pruning out chunks of static text.
- [Exporting Logs](https://docs.openpipe.ai/features/request-logs/exporting-logs):  Export your past requests as a JSONL file in their raw form.
- [Logging Requests](https://docs.openpipe.ai/features/request-logs/logging-requests):  Record production data to train and improve your models' performance.
- [Logging Anthropic Requests](https://docs.openpipe.ai/features/request-logs/reporting-anthropic)
- [Updating Metadata Tags](https://docs.openpipe.ai/features/updating-metadata)
- [Installing the SDK](https://docs.openpipe.ai/getting-started/openpipe-sdk)
- [Quick Start](https://docs.openpipe.ai/getting-started/quick-start): Get started with OpenPipe in a few quick steps.
- [OpenPipe Documentation](https://docs.openpipe.ai/introduction):  Software engineers and data scientists use OpenPipe's intuitive fine-tuning and monitoring services to decrease the cost and latency of their LLM operations.  You can use OpenPipe to collect and analyze LLM logs, create fine-tuned models, and compare output from multiple models given the same input.
- [Overview](https://docs.openpipe.ai/overview): OpenPipe is a streamlined platform designed to help product-focused teams train specialized LLM models as replacements for slow and expensive prompts.
- [Pricing Overview](https://docs.openpipe.ai/pricing/pricing)