# Vichar

> Vichar is an open-source, OpenAI-compatible API gateway for routing, managing, and analyzing requests across LLM providers. Use one API key, track usage and cost, configure caching and guardrails, and self-host or use the managed cloud.

Use the live [model catalogue](https://app.vichar.io/models) for availability, pricing, and capabilities. The API base URL is `https://api.vichar.io/v1`. Migrate by changing your SDK base URL and API key. The AGPLv3 core is self-hostable with Docker; a managed cloud is also available.

## Developer entry points

- [Vichar developer resources](https://app.vichar.io/developers): Documentation, authentication, dashboard, and MCP.
- [Vichar OpenAPI specification](https://app.vichar.io/openapi.json): Typed request, response, and error schemas.
- [Vichar developer dashboard](https://app.vichar.io/dashboard): Projects, API keys, usage, and budgets.

## Product pages

- [Home](https://app.vichar.io): Unified API for multiple LLM providers.
- [Models](https://app.vichar.io/models): Browse supported models with pricing and capabilities.
- [Providers](https://app.vichar.io/providers): All supported LLM providers.
- [Pricing](https://app.vichar.io/pricing): Plans and pricing.
- [Enterprise](https://app.vichar.io/enterprise): Self-hosting, SSO, and team features.
- [Token Cost Calculator](https://app.vichar.io/token-cost-calculator): Estimate and compare LLM costs across models.
- [Vichar vs LiteLLM](https://app.vichar.io/compare/litellm)
- [Vichar vs OpenRouter](https://app.vichar.io/compare/open-router)
- [Vichar vs Portkey](https://app.vichar.io/compare/portkey)

## Getting Started

- [Introduction to Vichar](https://docs.vichar.io/): Vichar is an open-source API gateway for Large Language Models. Route requests to multiple providers, manage API keys, track usage, and optimize costs.
- [Overview](https://docs.vichar.io/overview): Introduction to Vichar, an open-source API gateway for LLMs.
- [Quickstart](https://docs.vichar.io/quick-start): Fastest way to start using Vichar in any language or framework.
- [AWS](https://docs.vichar.io/self-host/aws): Deploy Vichar on AWS with EKS, RDS for Postgres, ElastiCache, and Secrets Manager.
- [Azure](https://docs.vichar.io/self-host/azure): Deploy Vichar on Azure with AKS, Azure Database for PostgreSQL, Azure Cache for Redis, and Key Vault.
- [Docker Compose](https://docs.vichar.io/self-host/docker-compose): Run Vichar with Docker Compose — each service in its own container for more control.
- [Docker](https://docs.vichar.io/self-host/docker): Run Vichar as a single Docker container — the fastest way to a working instance.
- [Google Cloud](https://docs.vichar.io/self-host/gcp): Deploy Vichar on Google Cloud with GKE, Cloud SQL, Memorystore, and Secret Manager.
- [Self Host Vichar](https://docs.vichar.io/self-host): Deploy Vichar on your own infrastructure with Docker, Docker Compose, or Kubernetes on AWS, GCP, and Azure.
- [Kubernetes](https://docs.vichar.io/self-host/kubernetes): Deploy Vichar to any Kubernetes cluster with the official Helm chart.

## Developer Resources

- [AI SDK Gateway protocol](https://docs.vichar.io/developers/ai-sdk-gateway-protocol): Point an app built on the Vercel AI Gateway at Vichar without changing its code
- [Image Generation with the AI SDK](https://docs.vichar.io/developers/ai-sdk-images): Generate images with generateImage or stream image output through chat using the AI SDK
- [Using the AI SDK](https://docs.vichar.io/developers/ai-sdk): Generate text, stream responses, call tools, and generate video with the Vercel AI SDK and Vichar
- [Vichar CLI](https://docs.vichar.io/developers/cli): Command-line tool for launching coding agents, scaffolding projects, and managing keys, budgets, and usage
- [Vichar Developer Resources](https://docs.vichar.io/developers): Build AI applications on Vichar with the CLI, MCP, the AI SDK, and TanStack AI
- [Vichar MCP Server](https://docs.vichar.io/developers/mcp): Check usage, costs, and your most-used models, providers and coding apps from any MCP client
- [Using TanStack AI](https://docs.vichar.io/developers/tanstack-ai): Stream chat, call tools, and surface reasoning with TanStack AI and Vichar

## Features

- [Anthropic API Compatibility](https://docs.vichar.io/features/anthropic-endpoint): Use the Anthropic-compatible endpoint to access any LLM model through the familiar Anthropic API format.
- [Vichar Authentication, API Keys & IAM Rules](https://docs.vichar.io/features/api-keys): Comprehensive guide to API key management and Identity Access Management (IAM) rules for fine-grained access control
- [Cost Breakdown](https://docs.vichar.io/features/cost-breakdown): Get real-time cost information for each API request directly in the response.
- [Data Retention](https://docs.vichar.io/features/data-retention): Store and access your full request and response data for debugging, analytics, and compliance.
- [Document Reading](https://docs.vichar.io/features/documents): Learn how to send PDFs and other document data to document-capable models.
- [Embeddings](https://docs.vichar.io/features/embeddings): Generate vector embeddings using OpenAI-compatible embedding models.
- [Image Generation](https://docs.vichar.io/features/image-generation): Generate images using AI models through the OpenAI-compatible images API or chat completions API
- [Metadata](https://docs.vichar.io/features/metadata): Send additional context and metadata to Vichar using custom headers.
- [Org Models Directory](https://docs.vichar.io/features/models-directory): One directory of every model your organization can use, searchable by capability, provider, price, and context size.
- [Moderations](https://docs.vichar.io/features/moderations): Classify unsafe text and image inputs with the OpenAI-compatible moderations API
- [Notifications](https://docs.vichar.io/features/notifications): Receive budget, model retirement, and provider health alerts
- [OCR](https://docs.vichar.io/features/ocr): Extract text and structure from documents and images as markdown with the OCR API
- [Project access](https://docs.vichar.io/features/project-access): Delegate project administration without granting organization-wide access
- [Realtime API](https://docs.vichar.io/features/realtime): Low-latency speech-to-speech conversations over WebSockets through the OpenAI-compatible realtime API
- [Reasoning](https://docs.vichar.io/features/reasoning): Learn how to use reasoning-capable models that show their step-by-step thought process.
- [Rerank](https://docs.vichar.io/features/rerank): Reorder candidate documents by relevance to a query with the rerank API
- [Response Healing](https://docs.vichar.io/features/response-healing): Automatically repair malformed JSON responses from AI models.
- [Routing](https://docs.vichar.io/features/routing): Learn how Vichar intelligently routes your requests to the best available models and providers.
- [Service Tiers](https://docs.vichar.io/features/service-tiers): Trade latency against cost on supported OpenAI, Google, and Fireworks models with Flex and Priority processing tiers.
- [Source Attribution](https://docs.vichar.io/features/source): Use the X-Source header to identify your domain for public usage statistics.
- [Speech Generation](https://docs.vichar.io/features/speech-generation): Generate speech (text-to-speech) using ElevenLabs, Gemini, OpenAI, and Qwen models through the OpenAI-compatible audio API
- [System One](https://docs.vichar.io/features/system-one): Get typed, probabilistic decisions instead of generated text with the /v1/systemone endpoint
- [Request Timeouts](https://docs.vichar.io/features/timeouts): Per-request time limits on the gateway, how they interact with streaming and agentic workloads, and how to change them.
- [Transcription](https://docs.vichar.io/features/transcription): Transcribe audio into text (speech-to-text) with word-level timestamps through the audio transcriptions API
- [Video Generation](https://docs.vichar.io/features/video-generation): Generate videos with an OpenAI-compatible async API and signed completion callbacks
- [Vision Support](https://docs.vichar.io/features/vision): Learn how to send images to vision-enabled models using URLs or inline base64 data.
- [Native Web Search](https://docs.vichar.io/features/web-search): Enable real-time web search capabilities to get up-to-date information from the internet.
- [Gateway Caching](https://docs.vichar.io/features/caching/gateway-caching): Serve repeated identical requests entirely from Vichar at $0 cost.
- [Caching](https://docs.vichar.io/features/caching): Overview of the two types of caching available in Vichar.
- [Provider Cache Control](https://docs.vichar.io/features/caching/provider-cache-control): Use provider-side prompt caching to reduce the cost of long, reused prompts in chat and coding tools.

## Platform & Dashboard

- [Activity](https://docs.vichar.io/learn/activity): View and inspect every API request made through Vichar
- [Analytics](https://docs.vichar.io/learn/analytics): Break down cost, requests, and tokens by model for any project
- [API Keys](https://docs.vichar.io/learn/api-keys): Create, limit, and control API keys for authenticating with Vichar
- [Billing](https://docs.vichar.io/learn/billing): Manage your credits, payment methods, and auto top-up
- [Dashboard](https://docs.vichar.io/learn/dashboard): Your central hub for monitoring LLM usage, costs, and performance
- [Introduction](https://docs.vichar.io/learn): Learn how to navigate and use the Vichar dashboard
- [Invoices](https://docs.vichar.io/learn/invoices): Download invoices and credit notes for every payment
- [Member Analytics](https://docs.vichar.io/learn/member-analytics): See organization usage and cost broken down per team member
- [Model Usage](https://docs.vichar.io/learn/model-usage): Track usage breakdown by individual model
- [Models](https://docs.vichar.io/learn/models): Browse every model available on Vichar — pricing, capabilities, and lifecycle status
- [Org Preferences](https://docs.vichar.io/learn/org-preferences): Manage your organization's name, billing email, and billing details
- [Preferences](https://docs.vichar.io/learn/preferences): Configure project-level settings including caching and project mode
- [Referrals](https://docs.vichar.io/learn/referrals): Earn credits by referring other users to Vichar
- [Self-Service Refunds](https://docs.vichar.io/learn/refunds): Refund a recent credit top-up yourself
- [Structured outputs](https://docs.vichar.io/learn/structured-outputs): Soft JSON output vs strict JSON output schema — what Vichar declares and how it enforces each
- [Team](https://docs.vichar.io/learn/team): Manage organization members and shared developer policy
- [Transactions](https://docs.vichar.io/learn/transactions): View your complete payment and credit history
- [Usage & Metrics](https://docs.vichar.io/learn/usage-metrics): Detailed analytics for requests, models, errors, caching, and costs

## Migration Guides

- [Migrate from LiteLLM](https://docs.vichar.io/migrations/litellm): Switch from self-hosted LiteLLM to managed Vichar. Same API format, zero infrastructure to maintain.
- [Migrate from OpenRouter](https://docs.vichar.io/migrations/openrouter): Switch to Vichar for built-in analytics, self-hosting options, and free bring-your-own-keys at any volume. Two-line code change.
- [Migrate from Vercel AI Gateway](https://docs.vichar.io/migrations/vercel-ai-gateway): Keep your Vercel AI SDK code, add response caching, detailed analytics, and smart routing. One provider for all models.

## Resources

- [Vichar API Versioning and Deprecation Policy](https://docs.vichar.io/resources/api-versioning): API compatibility, deprecation notices, and retirement information for Vichar integrations.
- [Vichar API Errors](https://docs.vichar.io/resources/error-handling): How Vichar returns errors in an OpenAI-compatible format on the OpenAI-compatible endpoints.
- [Rate Limits](https://docs.vichar.io/resources/rate-limits): Understanding rate limits per organization, endpoint, and plan on Vichar.

## API Reference

- [Health check](https://docs.vichar.io/health): Health check endpoint.
- [Create speech](https://docs.vichar.io/v1_audio_speech): >-
- [Create transcription](https://docs.vichar.io/v1_audio_transcriptions): >-
- [Chat Completions](https://docs.vichar.io/v1_chat_completions): Create a completion for the chat conversation
- [Embeddings](https://docs.vichar.io/v1_embeddings): >-
- [Edit image](https://docs.vichar.io/v1_images_edits): Creates an edited image from one or more source images and a prompt.
- [Create image](https://docs.vichar.io/v1_images_generations): >-
- [Retrieve key status](https://docs.vichar.io/v1_key_retrieve): >-
- [Anthropic Messages](https://docs.vichar.io/v1_messages): Create a message using Anthropic's API format
- [Models](https://docs.vichar.io/v1_models): >-
- [Moderations](https://docs.vichar.io/v1_moderations): Classify text or multimodal inputs with OpenAI moderation.
- [OCR](https://docs.vichar.io/v1_ocr): >-
- [Create a realtime client secret](https://docs.vichar.io/v1_realtime_client_secrets)
- [Rerank](https://docs.vichar.io/v1_rerank): >-
- [System One](https://docs.vichar.io/v1_systemone): >-
- [Video content](https://docs.vichar.io/v1_videos_content): >-
- [Create video](https://docs.vichar.io/v1_videos_create): >-
- [Video log content](https://docs.vichar.io/v1_videos_log_content): >-
- [Retrieve video](https://docs.vichar.io/v1_videos_retrieve): Retrieves the current state of a video generation job.