Artificial Intelligence · Beta

OpenPipe
API integration

Ship Artificial Intelligence features without building the integration. Full OpenPipe API access via Proxy and 20+ MCP-ready tools for AI agents — extend models and mappings to fit your product.

Built for specific customer use cases. Issues are resolved quickly.

Talk to us

Use Cases

Why integrate with OpenPipe

Common scenarios for SaaS companies building OpenPipe integrations for their customers.

Offer end-users AI cost reduction on autopilot

SaaS platforms that rely on GPT-4 or Claude for user-facing AI features can let their tenants automatically train cheaper, faster fine-tuned models from their own usage data. This turns AI infrastructure cost from a per-tenant liability into a competitive advantage.

Enable tenant-specific model customization

Multi-tenant SaaS products can give each customer their own fine-tuned model trained on that customer's edits, approvals, and domain data — without building an in-house ML pipeline. Every tenant gets a model that sounds like their business.

Ship continuous learning from user feedback

Product teams can wire Accept/Reject/Edit UI actions directly into OpenPipe's logging and metadata layer, so every user correction becomes labeled training data. This closes the loop between product usage and model quality automatically.

Support regulated industries with private fine-tuned models

LegalTech, healthcare, and fintech SaaS products can offer customers custom models trained on their sensitive data pipelines. This lets end-users meet compliance requirements without sacrificing the reasoning quality of frontier models.

Build reliable multi-step agents with RL feedback

SaaS platforms shipping AI agents can push success/failure signals back into OpenPipe as training data, improving agent reliability over time. This is critical for products where end-users judge quality by task completion, not just token output.

What You Can Build

Ship these features with Truto + OpenPipe

Concrete product features your team can ship faster by leveraging Truto’s OpenPipe integration instead of building from scratch.

Silent LLM telemetry capture

Use the report endpoints to log every prompt-completion pair from your product's AI features into each tenant's OpenPipe workspace without altering user workflows.

Feedback-driven metadata tagging

Bind your in-app Accept, Reject, and Edit actions to the logs metadata update endpoint so user corrections instantly flag high-quality training examples in OpenPipe.

Automated dataset curation pipelines

Use dataset creation and dataset entry endpoints to programmatically batch cleaned, tagged conversation logs into per-tenant datasets when quality thresholds are hit.

One-click fine-tuned model training

Trigger training runs directly from your UI using the model creation endpoint, letting end-users kick off custom fine-tunes with their chosen base model and training config.

Drop-in inference routing

Once a tenant's fine-tune completes, route their inference calls through the OpenPipe chat completion endpoint to instantly cut token costs and latency for that customer.

LLM-as-a-judge evaluation gates

Call the criteria judge endpoint to score completions against custom rubrics before they enter a training dataset, ensuring only high-quality data reaches fine-tuning.

SuperAI

OpenPipe AI agent tools

Comprehensive AI agent toolset with fine-grained control. Integrates with MCP clients like Cursor and Claude, or frameworks like LangChain.

create_a_open_pipe_check_cach

Check a cached prompt request in OpenPipe. Returns: respPayload. Deprecated: OpenPipe no longer supports prompt caching. Required: requestedAt.

create_a_open_pipe_chat_completion

Create a chat completion in OpenPipe. Returns the generated completion object including id, object, created, model, choices, and usage. Required: messages, model.

create_a_open_pipe_report

Record a request log from an OpenAI model in OpenPipe. Returns: status.

create_a_open_pipe_report_anthropic

Record a request log from an Anthropic model call in OpenPipe. Returns: status. Optional fields include statusCode, errorMessage, metadata, and tags.

create_a_open_pipe_logs_update_tag

Update tags on OpenPipe log entries matching the given filters. Returns: matchedLogs. Deprecated: use /logs/update-metadata instead. Required: filters, tags.

create_a_open_pipe_logs_update_metadata

Update tags metadata for logged OpenPipe calls matching the provided filters. Returns: matchedLogs. Required: filters, metadata.

list_all_open_pipe_local_testing_only_get_latest_logged_calls

Get the latest logged call from OpenPipe. Returns the call object with createdAt, cacheHit, statusCode, reqPayload, respPayload, tags, and metadata. Local testing only.

create_a_open_pipe_criteria_judge

Judge a completion against an OpenPipe criterion. Returns: score, explanation, usage. Required: criterion_id, output.

list_all_open_pipe_datasets

List datasets in an OpenPipe project. Returns dataset objects with id, name, created, updated, dataset_entry_count, and fine_tune_count.

create_a_open_pipe_dataset

Create a new dataset in OpenPipe. Returns the created dataset including id, name, created, updated, dataset_entry_count, and fine_tune_count. Required: name.

delete_a_open_pipe_dataset_by_id

Delete a dataset in OpenPipe by id. Returns the deletion status with id, object, and deleted. Required: id.

create_a_open_pipe_dataset_entry

Create new dataset entries in OpenPipe. Returns the creation summary including object, entries_created, and errors (with entry_index and message). Max 100 entries per request. Required: dataset_id, entries.

list_all_open_pipe_models

List all models in an OpenPipe project. Returns models with id, name, openpipe status, contextWindow, and pricing.

create_a_open_pipe_model

Train a new model in OpenPipe. Returns the created model including id, name, openpipe status, and pricing. Required: datasetId, slug, trainingConfig.

delete_a_open_pipe_model_by_id

Delete an OpenPipe model by its slug. Returns: id, object, deleted. Required: id.

get_single_open_pipe_model_by_id

Get a single OpenPipe model by id. Returns the model object including id, name, openpipe status, contextWindow, and pricing. Required: id.

create_a_open_pipe_dataset_create

Create a new dataset in openpipe. Returns: datasetId. Deprecated; prefer the `/datasets` endpoint. Required: name.

create_a_open_pipe_dataset_delete

Delete an OpenPipe dataset by its datasetId. Returns: datasetId. Deprecated endpoint; use the `/datasets/{dataset}` endpoint instead. Required: datasetId.

list_all_open_pipe_dataset_lists

List OpenPipe dataset lists via the deprecated /unstable/dataset/list endpoint. Returns an array of dataset objects with id, name, createdAt, updatedAt, datasetEntryCount, and fineTuneCount. Prefer the /datasets endpoint instead.

create_a_open_pipe_dataset_entry_create

Create dataset entries in OpenPipe. Returns: createdEntries, errors. Deprecated: use `/datasets/{dataset}/entries` instead. Required: datasetId, entries.

create_a_open_pipe_finetune_create

Create a fine-tune job in OpenPipe. Returns the new fine-tune job's id. Deprecated. Required: datasetId, slug, baseModel.

list_all_open_pipe_finetune_gets

Get a fine-tuned model in openpipe by id or slug. Returns: id, status, slug, baseModel, errorMessage, datasetId, createdAt. Deprecated: use the `/models/{model}` endpoint instead.

create_a_open_pipe_finetune_delete

Delete an openpipe fine-tuned model by id or slug. Returns: deleted. Deprecated: use the `/models/{model}` endpoint instead.

Why Truto

Why use Truto’s MCP server for OpenPipe

Other MCP servers give you a static tool list for one app. Truto gives you a managed, multi-tenant MCP infrastructure across 550+ integrations.

Auto-generated, always up to date

Tools are dynamically generated from curated documentation — not hand-coded. As integrations evolve, tools stay current without manual maintenance.

Fine-grained access control

Scope each MCP server to read-only, write-only, specific methods, or tagged tool groups. Expose only what your AI agent needs — nothing more.

Multi-tenant by design

Each MCP server is scoped to a single connected account with its own credentials. The URL itself is the auth token — no shared secrets, no credential leaking across tenants.

Works with every MCP client

Standard JSON-RPC 2.0 protocol. Paste the URL into Claude, ChatGPT, Cursor, or any MCP-compatible agent framework — tools are discovered automatically.

Built-in auth, rate limits, and error handling

Tool calls execute through Truto’s proxy layer with automatic OAuth refresh, rate-limit handling, and normalized error responses. No raw API plumbing in your agent.

Expiring and auditable servers

Create time-limited MCP servers for contractors or automated workflows. Optional dual-auth requires both the URL and a Truto API token for high-security environments.

How It Works

From zero to integrated

Go live with OpenPipe in under an hour. No boilerplate, no maintenance burden.

Link your customer’s OpenPipe account

Use Truto’s frontend SDK to connect your customer’s OpenPipe account. We handle all OAuth and API key flows — you don’t need to create the OAuth app.

We handle authentication

Don’t spend time refreshing access tokens or figuring out secure storage. We handle it and inject credentials into every API request.

Call our API, we call OpenPipe

Truto’s Proxy API is a 1-to-1 mapping of the OpenPipe API. You call us, we call OpenPipe, and pass the response back in the same cycle.

Unified response format

Every response follows a single format across all integrations. We translate OpenPipe’s pagination into unified cursor-based pagination. Data is always in the result attribute.

FAQs

Common questions about OpenPipe on Truto

Authentication, rate limits, data freshness, and everything else you need to know before you integrate.

How does authentication work for end-users connecting their OpenPipe account?

End-users authenticate by providing their OpenPipe API key, which Truto securely stores and injects into every downstream request. Your app never needs to handle or persist the credential directly.

Can we log completions from both OpenAI and Anthropic through this integration?

Yes. Separate endpoints exist for reporting OpenAI-format logs and Anthropic-format logs, so you can pipe telemetry from either provider into the same tenant workspace.

How do we attach user feedback signals to logged completions?

Use the logs metadata update and tag update endpoints to attach arbitrary key-value metadata (e.g., user_accepted: true) or tags to any previously logged call, which can then be used to filter training data.

Can we push pre-formatted training data directly into a dataset?

Yes. The dataset entry creation endpoints let you push multi-turn chat examples into a specific dataset in batches, bypassing the log-and-curate flow if you already have clean data.

How do we serve inference from a fine-tuned model once training completes?

Call the chat completion endpoint with the fine-tuned model's slug. It follows the OpenAI-compatible request shape, so most existing chat completion code works with minimal changes.

What lifecycle operations are supported for models and datasets?

You can list, create, retrieve, and delete both models and datasets via dedicated endpoints, plus list finetune jobs and delete them — giving you full programmatic control over each tenant's training lifecycle.

OpenPipe

Get OpenPipe integrated into your app

Our team understands what it takes to make a OpenPipe integration successful. A short, crisp 30 minute call with folks who understand the problem.