# Planck

- [Quickstart](https://docs.inquantum.ai/getting-started/quick-start.md): Get your first LLM request logged with Planck in under 2 minutes using the AI Gateway.
- [Platform Overview](https://docs.inquantum.ai/getting-started/platform-overview.md): Understand how Planck solves the core challenges of building production LLM applications
- [Migrating from Bifrost](https://docs.inquantum.ai/getting-started/migrating-from-bifrost.md): Use Planck names in new integrations while keeping existing Bifrost integrations working.
- [AI Gateway Overview](https://docs.inquantum.ai/gateway/overview.md): Use supported AI providers through a single OpenAI-compatible API with intelligent routing, fallbacks, and unified observability
- [Chat & Responses](https://docs.inquantum.ai/gateway/text-generation.md): Generate text through OpenAI-compatible and Anthropic-compatible AI Gateway routes.
- [Structured JSON](https://docs.inquantum.ai/gateway/structured-json.md): Constrain a model response to a JSON Schema through the AI Gateway.
- [Embeddings](https://docs.inquantum.ai/gateway/embeddings.md): Create text embeddings through the OpenAI-compatible AI Gateway route.
- [Reranking](https://docs.inquantum.ai/gateway/reranking.md): Rank candidate documents by their relevance to a query through one gateway contract.
- [Image Generation](https://docs.inquantum.ai/gateway/image-generation.md): Generate images through one AI Gateway endpoint.
- [Video Generation](https://docs.inquantum.ai/gateway/video-generation.md): Submit asynchronous video generations, monitor their status, and download completed output.
- [Gateway Integration](https://docs.inquantum.ai/getting-started/integration-method/gateway.md): Use Planck AI Gateway through explicit OpenAI-compatible and Anthropic-compatible routes.
- [Provider Routing](https://docs.inquantum.ai/gateway/provider-routing.md): Automatic model routing across 100+ providers for reliability and performance
- [Resell a Private Model](https://docs.inquantum.ai/gateway/resell-a-model.md): Give each customer an isolated Planck key for a private or fine-tuned model while keeping the upstream provider credential secret.
- [Planck Header Directory](https://docs.inquantum.ai/planck-headers/header-directory.md): Customer-facing headers supported by the Planck AI Gateway.
- [Prompt Management](https://docs.inquantum.ai/gateway/prompt-integration.md): Deploy and iterate prompts through the AI Gateway without code changes
- [LLM Caching](https://docs.inquantum.ai/features/advanced-usage/caching.md)
- [Custom LLM Rate Limits](https://docs.inquantum.ai/features/advanced-usage/custom-rate-limits.md): Set custom rate limits for model provider API calls. Control usage by request count, cost, or custom properties to manage expenses and prevent unintended overuse.
- [LLM Security](https://docs.inquantum.ai/features/advanced-usage/llm-security.md): Enable robust security measures in your LLM applications to protect against prompt injections, detect anomalies, and prevent data exfiltration.
- [Prompt Caching](https://docs.inquantum.ai/gateway/concepts/prompt-caching.md): Cache frequently-used context across LLM providers for reduced costs and faster responses
- [Web Search](https://docs.inquantum.ai/gateway/web-search.md): Enable web search capabilities for Anthropic models through Planck's Gateway using the :online suffix
- [Error Handling & Fallback](https://docs.inquantum.ai/gateway/concepts/error-handling.md): How Planck AI Gateway handles errors and automatically falls back between billing methods
- [Responses API](https://docs.inquantum.ai/gateway/concepts/responses-api.md): Use the OpenAI Responses API format through Planck AI Gateway with your Planck API key
- [OpenAI Codex](https://docs.inquantum.ai/gateway/integrations/codex.md): Use OpenAI Codex CLI and SDK with Planck AI Gateway to log your coding agent interactions.
- [LangChain Integration](https://docs.inquantum.ai/gateway/integrations/langchain.md): Integrate Planck AI Gateway with LangChain to access 100+ LLM providers with unified observability.
- [Semantic Kernel Integration](https://docs.inquantum.ai/gateway/integrations/semantic-kernel.md): Integrate Planck AI Gateway with Microsoft Semantic Kernel to access 100+ LLM providers with unified observability.
- [Vercel AI SDK Integration](https://docs.inquantum.ai/gateway/integrations/vercel-ai-sdk.md): Integrate Planck AI Gateway with Vercel AI SDK to access 100+ LLM providers with full observability.
- [Zapier Integration](https://docs.inquantum.ai/gateway/integrations/zapier.md): Use the Planck Zapier app to run Chat Completions via the AI Gateway — no provider keys required.
- [Custom Properties](https://docs.inquantum.ai/features/advanced-usage/custom-properties.md)
- [Sessions](https://docs.inquantum.ai/features/sessions.md)
- [User Metrics & Analytics](https://docs.inquantum.ai/features/advanced-usage/user-metrics.md): Understand user behavior, track engagement patterns, and optimize AI experiences with detailed user analytics
- [Datasets](https://docs.inquantum.ai/features/datasets.md): Curate and export LLM request/response data for fine-tuning, evaluation, and analysis
- [Reports](https://docs.inquantum.ai/features/reports.md): Get automated weekly summaries of your LLM usage, costs, and performance delivered to email or Slack
- [Eval Scores](https://docs.inquantum.ai/features/advanced-usage/scores.md)
- [User Feedback](https://docs.inquantum.ai/features/advanced-usage/feedback.md)
- [Webhooks](https://docs.inquantum.ai/features/webhooks.md)
- [Testing Webhooks](https://docs.inquantum.ai/features/webhooks-testing.md)
- [Trace Tools with cURL](https://docs.inquantum.ai/integrations/tools/curl.md): Send a completed external operation to Planck's manual logging endpoint.
- [Trace Tools with the Logger SDK](https://docs.inquantum.ai/integrations/tools/logger-sdk.md): Wrap external operations and record their inputs, outputs, timing, and errors in Planck.
- [Planck MCP Server](https://docs.inquantum.ai/integrations/tools/mcp.md): Query your Planck observability data directly from MCP-compatible AI assistants using the Planck MCP server.
- [Vector DB tracing with cURL](https://docs.inquantum.ai/integrations/vectordb/curl.md): Log any Vector DB interactions to Planck using cURL.
- [Trace Any Vector DB interactions](https://docs.inquantum.ai/integrations/vectordb/logger-sdk.md): Log any Vector DB interactions using Planck's Logger SDK.
- [Prompt Management Overview](https://docs.inquantum.ai/features/advanced-usage/prompts/overview.md): Compose and iterate prompts, then easily deploy them in any LLM call with the AI Gateway.
- [Prompt Assembly](https://docs.inquantum.ai/features/advanced-usage/prompts/assembly.md): Understand how prompts are compiled from templates and runtime parameters
- [SDK Integration](https://docs.inquantum.ai/features/advanced-usage/prompts/sdk.md): Use prompts directly via SDK without the AI Gateway
- [OpenLLMetry Async Integration](https://docs.inquantum.ai/getting-started/integration-method/openllmetry.md): Log LLM traces directly to Planck, bypassing our proxy, with OpenLLMetry. Supports OpenAI, Anthropic, Azure OpenAI, Cohere, Bedrock, Google AI Platform, and more.
- [Manual Logger - cURL](https://docs.inquantum.ai/getting-started/integration-method/manual-logger-curl.md): Integrate any custom LLM with Planck using cURL. Step-by-step guide for direct API integration to connect your proprietary or open-source models.
- [Manual Logger - TypeScript](https://docs.inquantum.ai/getting-started/integration-method/manual-logger-typescript.md): Integrate any custom LLM with Planck using the TypeScript Manual Logger. Step-by-step guide for NodeJS implementation to connect your proprietary or open-source models.
- [Manual Logger - Python](https://docs.inquantum.ai/getting-started/integration-method/manual-logger-python.md): Integrate any custom LLM with Planck using the Python Manual Logger. Step-by-step guide for Python implementation to connect your proprietary or open-source models.
- [Manual Logger - Go](https://docs.inquantum.ai/getting-started/integration-method/manual-logger-go.md): Integrate any custom LLM with Planck using the Go Manual Logger. Step-by-step guide for Go implementation to connect your proprietary or open-source models.
- [Custom Logs with the Logger SDK](https://docs.inquantum.ai/integrations/data/logger-sdk.md): Log any custom operations using Planck's Logger SDK for complete observability across your application stack.
- [Custom Logs with cURL](https://docs.inquantum.ai/integrations/data/curl.md): Log any custom operations to Planck using cURL for complete observability across your application stack.
- [Chat Completions (Gateway)](https://docs.inquantum.ai/rest/ai-gateway/post-v1-chat-completions.md): Create chat completions via the AI Gateway
- [Responses (Gateway)](https://docs.inquantum.ai/rest/ai-gateway/post-v1-responses.md): Create responses via the AI Gateway
- [Embeddings](https://docs.inquantum.ai/rest/ai-gateway/post-v1-embeddings.md): Create one or more text embeddings through the OpenAI-compatible AI Gateway route.
- [Image Generation](https://docs.inquantum.ai/rest/ai-gateway/post-v1-images-generations.md): Create images through the AI Gateway image-generation route.
- [Rerank](https://docs.inquantum.ai/rest/ai-gateway/post-v1-rerank.md): Score candidate documents against a query with a provider-neutral reranking contract.
- [Video Generation](https://docs.inquantum.ai/rest/ai-gateway/post-v1-videos.md): Submit, poll, and download asynchronous video generations.
- [Audio](https://docs.inquantum.ai/rest/ai-gateway/post-v1-audio.md): Use OpenAI-compatible audio routes through the Planck AI Gateway.
- [Files](https://docs.inquantum.ai/rest/ai-gateway/files.md): Use OpenAI-compatible files routes through the Planck AI Gateway.
- [Anthropic Messages](https://docs.inquantum.ai/rest/ai-gateway/post-v1-messages.md): Create Anthropic-style message requests through the Planck AI Gateway.
- [Native Anthropic Passthrough](https://docs.inquantum.ai/rest/ai-gateway/anthropic-native.md): Proxy Anthropic-native routes through the Planck AI Gateway.
- [Gateway Metadata](https://docs.inquantum.ai/rest/ai-gateway/gateway-metadata.md): Inspect Planck AI Gateway status and provider metadata.
- [Get Models](https://docs.inquantum.ai/rest/ai-gateway/get-v1models.md): Returns all available models supported by Planck AI Gateway (OpenAI-compatible endpoint)
- [Get Multimodal Models](https://docs.inquantum.ai/rest/ai-gateway/get-v1models-multimodal.md): Returns all available multimodal models supported by Planck AI Gateway (OpenAI-compatible endpoint)
- [Get Model Registry](https://docs.inquantum.ai/rest/models/get-v1public-model-registry-models.md): Returns all models and endpoints supported by the Planck AI Gateway
- [Get Requests](https://docs.inquantum.ai/rest/request/post-v1requestquery-clickhouse.md): Retrieve all requests visible in the request table at Planck.
- [Get Requests (Point Queries)](https://docs.inquantum.ai/rest/request/post-v1requestquery.md): Retrieve all requests visible in the request table at Planck.
- [Get Single Request](https://docs.inquantum.ai/rest/request/get-v1request.md): Retrieve a single request visible in the request table at Planck.
- [Get Requests by IDs](https://docs.inquantum.ai/rest/request/post-v1requestquery-ids.md): Retrieve all requests visible in the request table at Planck.
- [Submit Feedback](https://docs.inquantum.ai/rest/request/post-v1request-feedback.md): Submit feedback for a specific request.
- [Upsert Request Property](https://docs.inquantum.ai/rest/request/put-v1request-property.md): Create or update a property of a specific request.
- [Submit Request Assets](https://docs.inquantum.ai/rest/request/post-v1request-assets.md): Submit assets for a specific request. - If you don't know what this is, you probably don't need this.
- [Submit Score](https://docs.inquantum.ai/rest/request/post-v1request-score.md): Submit a score for a specific request.
- [Query Sessions](https://docs.inquantum.ai/rest/session/post-v1sessionquery.md): Search and filter through session data
- [Query Session Metrics](https://docs.inquantum.ai/rest/session/post-v1sessionmetricsquery.md): Search and analyze session performance metrics
- [Add Session Feedback](https://docs.inquantum.ai/rest/session/post-v1session-feedback.md): Submit feedback for a specific session
- [Create Prompt](https://docs.inquantum.ai/rest/prompts/post-v1prompt-2025.md): Create a new prompt with initial version
- [Get Prompt](https://docs.inquantum.ai/rest/prompts/get-v1prompt-2025-id-promptid.md): Retrieve a specific prompt by ID
- [Rename Prompt](https://docs.inquantum.ai/rest/prompts/post-v1prompt-2025-id-promptid-rename.md): Rename an existing prompt
- [Update Prompt Tags](https://docs.inquantum.ai/rest/prompts/patch-v1prompt-2025-id-promptid-tags.md): Update the tags for a prompt
- [Delete Prompt](https://docs.inquantum.ai/rest/prompts/delete-v1prompt-2025-promptid.md): Delete an entire prompt and all its versions
- [Update Prompt](https://docs.inquantum.ai/rest/prompts/post-v1prompt-2025-update.md): Create a new version of an existing prompt
- [Set Version Environment](https://docs.inquantum.ai/rest/prompts/post-v1prompt-2025-update-environment.md): Set the environment for a specific prompt version
- [Delete Prompt Version](https://docs.inquantum.ai/rest/prompts/delete-v1prompt-2025-promptid-versionid.md): Delete a specific version of a prompt
- [Query Prompts](https://docs.inquantum.ai/rest/prompts/post-v1prompt-2025-query.md): Search and filter prompts with pagination
- [Get Prompt Version](https://docs.inquantum.ai/rest/prompts/post-v1prompt-2025-query-version.md): Retrieve a specific prompt version with its content
- [Get Prompt Version by Environment](https://docs.inquantum.ai/rest/prompts/post-v1prompt-2025-query-environment-version.md): Retrieve a prompt version for a specific environment
- [Get Prompt Versions](https://docs.inquantum.ai/rest/prompts/post-v1prompt-2025-query-versions.md): Retrieve all versions of a specific prompt
- [Get Production Version](https://docs.inquantum.ai/rest/prompts/post-v1prompt-2025-query-production-version.md): Retrieve the production version of a specific prompt
- [Get Prompt Version Counts](https://docs.inquantum.ai/rest/prompts/post-v1prompt-2025-query-total-versions.md): Get version count statistics for a specific prompt
- [Get Prompt Inputs](https://docs.inquantum.ai/rest/prompts/get-v1prompt-2025-id-promptid-versionid-inputs.md): Get the inputs used for a specific prompt version in a request
- [Get Prompt Tags](https://docs.inquantum.ai/rest/prompts/get-v1prompt-2025-tags.md): Retrieve all available prompt tags
- [Get Environments](https://docs.inquantum.ai/rest/prompts/get-v1prompt-2025-environments.md): Get all available environments across your prompts
- [Get Prompt Count](https://docs.inquantum.ai/rest/prompts/get-v1prompt-2025-count.md): Get the total number of prompts
- [Query User Metrics Overview](https://docs.inquantum.ai/rest/user/post-v1usermetrics-overviewquery.md): Get an overview of aggregated user metrics
- [Query User Metrics](https://docs.inquantum.ai/rest/user/post-v1usermetricsquery.md): Search and filter through user-specific metrics
- [Get User Data](https://docs.inquantum.ai/rest/user/post-v1userquery.md): Retrieve user data based on specified user IDs and time filters
- [Query Evaluations](https://docs.inquantum.ai/rest/evals/post-v1evalsquery.md): Search and filter through evaluation results
- [Get Evaluation Scores](https://docs.inquantum.ai/rest/evals/get-v1evalsscores.md): Retrieve scoring metrics for evaluations
- [Create Evaluation](https://docs.inquantum.ai/rest/evals/post-v1evals.md): Create a new evaluation for a specific request
- [Query Score Distributions](https://docs.inquantum.ai/rest/evals/post-v1evalsscore-distributionsquery.md): Analyze distribution of evaluation scores
- [Get Webhooks](https://docs.inquantum.ai/rest/webhooks/get-v1webhooks.md): Get all webhooks
- [Create Webhook](https://docs.inquantum.ai/rest/webhooks/post-v1webhooks.md): Create a new webhook
- [Delete Webhook](https://docs.inquantum.ai/rest/webhooks/delete-v1webhooks.md): Delete a webhook
- [Log Trace](https://docs.inquantum.ai/rest/trace/post-v1tracelog.md): Log a trace to the Planck API
- [Query Properties](https://docs.inquantum.ai/rest/property/post-v1propertyquery.md): Query properties for a specific user
- [Query Dashboard Scores](https://docs.inquantum.ai/rest/dashboard/post-v1dashboardscoresquery.md): Retrieve and filter dashboard scoring metrics

## OpenAPI Specs

- [ai-gateway.openapi](/ai-gateway.openapi.json)
- [openapi](/api-reference/openapi.json)
- [swagger](/swagger.json)