# Bifrost

## Docs

- [Cancel batch job (Anthropic format)](https://docs.getbifrost.ai/api-reference/anthropic-integration/cancel-batch-job-anthropic-format.md): Cancels a batch processing job.
- [Count tokens (Anthropic format)](https://docs.getbifrost.ai/api-reference/anthropic-integration/count-tokens-anthropic-format.md): Counts the number of tokens in a message request.
- [Create batch job (Anthropic format)](https://docs.getbifrost.ai/api-reference/anthropic-integration/create-batch-job-anthropic-format.md): Creates a batch processing job using Anthropic format. Use x-model-provider header to specify the provider.
- [Create completion (Anthropic legacy format)](https://docs.getbifrost.ai/api-reference/anthropic-integration/create-completion-anthropic-legacy-format.md): Creates a text completion using Anthropic's legacy Complete API. Supports streaming via SSE.
- [Create message (Anthropic format)](https://docs.getbifrost.ai/api-reference/anthropic-integration/create-message-anthropic-format.md): Creates a message using Anthropic Messages API format. Supports streaming via SSE.
- [Delete file (Anthropic format)](https://docs.getbifrost.ai/api-reference/anthropic-integration/delete-file-anthropic-format.md): Deletes an uploaded file.
- [Get batch results (Anthropic format)](https://docs.getbifrost.ai/api-reference/anthropic-integration/get-batch-results-anthropic-format.md): Retrieves results of a completed batch job.
- [Get file content (Anthropic format)](https://docs.getbifrost.ai/api-reference/anthropic-integration/get-file-content-anthropic-format.md): Retrieves file content. Returns raw binary file data when Accept header is set to application/octet-stream, or file metadata as JSON when Accept header is set to application/json.
- [List batch jobs (Anthropic format)](https://docs.getbifrost.ai/api-reference/anthropic-integration/list-batch-jobs-anthropic-format.md): Lists batch processing jobs.
- [List files (Anthropic format)](https://docs.getbifrost.ai/api-reference/anthropic-integration/list-files-anthropic-format.md): Lists uploaded files.
- [List models (Anthropic format)](https://docs.getbifrost.ai/api-reference/anthropic-integration/list-models-anthropic-format.md): Lists available models in Anthropic format.
- [Retrieve batch job (Anthropic format)](https://docs.getbifrost.ai/api-reference/anthropic-integration/retrieve-batch-job-anthropic-format.md): Retrieves details of a batch processing job.
- [Upload file (Anthropic format)](https://docs.getbifrost.ai/api-reference/anthropic-integration/upload-file-anthropic-format.md): Uploads a file. Use x-model-provider header to specify the provider.
- [Create async chat completion](https://docs.getbifrost.ai/api-reference/async-jobs/create-async-chat-completion.md): Submits a chat completion request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result. Streaming is not supported for async requests.
- [Create async embedding](https://docs.getbifrost.ai/api-reference/async-jobs/create-async-embedding.md): Submits an embedding request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result.
- [Create async image edit](https://docs.getbifrost.ai/api-reference/async-jobs/create-async-image-edit.md): Submits an image edit request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result. Streaming is not supported for async requests.
- [Create async image generation](https://docs.getbifrost.ai/api-reference/async-jobs/create-async-image-generation.md): Submits an image generation request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result. Streaming is not supported for async requests.
- [Create async image variation](https://docs.getbifrost.ai/api-reference/async-jobs/create-async-image-variation.md): Submits an image variation request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result.
- [Create async OCR job](https://docs.getbifrost.ai/api-reference/async-jobs/create-async-ocr-job.md): Submits an OCR request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result.
- [Create async rerank](https://docs.getbifrost.ai/api-reference/async-jobs/create-async-rerank.md): Submits a rerank request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result.
- [Create async response](https://docs.getbifrost.ai/api-reference/async-jobs/create-async-response.md): Submits a response request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result. Streaming is not supported for async requests.
- [Create async speech](https://docs.getbifrost.ai/api-reference/async-jobs/create-async-speech.md): Submits a speech synthesis request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result. SSE streaming is not supported for async requests.
- [Create async text completion](https://docs.getbifrost.ai/api-reference/async-jobs/create-async-text-completion.md): Submits a text completion request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result. Streaming is not supported for async requests.
- [Create async transcription](https://docs.getbifrost.ai/api-reference/async-jobs/create-async-transcription.md): Submits a transcription request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result. Streaming is not supported for async requests.
- [Get async chat completion job](https://docs.getbifrost.ai/api-reference/async-jobs/get-async-chat-completion-job.md): Retrieves the status and result of an async chat completion job. Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
- [Get async embedding job](https://docs.getbifrost.ai/api-reference/async-jobs/get-async-embedding-job.md): Retrieves the status and result of an async embedding job. Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
- [Get async image edit job](https://docs.getbifrost.ai/api-reference/async-jobs/get-async-image-edit-job.md): Retrieves the status and result of an async image edit job. Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
- [Get async image generation job](https://docs.getbifrost.ai/api-reference/async-jobs/get-async-image-generation-job.md): Retrieves the status and result of an async image generation job. Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
- [Get async image variation job](https://docs.getbifrost.ai/api-reference/async-jobs/get-async-image-variation-job.md): Retrieves the status and result of an async image variation job. Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
- [Get async OCR job](https://docs.getbifrost.ai/api-reference/async-jobs/get-async-ocr-job.md): Retrieves the status and result of an async OCR job. Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
- [Get async rerank job](https://docs.getbifrost.ai/api-reference/async-jobs/get-async-rerank-job.md): Retrieves the status and result of an async rerank job. Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
- [Get async response job](https://docs.getbifrost.ai/api-reference/async-jobs/get-async-response-job.md): Retrieves the status and result of an async response job. Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
- [Get async speech job](https://docs.getbifrost.ai/api-reference/async-jobs/get-async-speech-job.md): Retrieves the status and result of an async speech job. Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
- [Get async text completion job](https://docs.getbifrost.ai/api-reference/async-jobs/get-async-text-completion-job.md): Retrieves the status and result of an async text completion job. Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
- [Get async transcription job](https://docs.getbifrost.ai/api-reference/async-jobs/get-async-transcription-job.md): Retrieves the status and result of an async transcription job. Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
- [Create speech](https://docs.getbifrost.ai/api-reference/audio/create-speech.md): Generates audio from the input text. Returns audio data or streams via SSE.
- [Create transcription](https://docs.getbifrost.ai/api-reference/audio/create-transcription.md): Transcribes audio into text in the input language.
- [Cancel a batch job](https://docs.getbifrost.ai/api-reference/batch/cancel-a-batch-job.md): Cancels a batch job.
- [Create a batch job](https://docs.getbifrost.ai/api-reference/batch/create-a-batch-job.md): Creates a batch job for asynchronous processing.
- [Get batch results](https://docs.getbifrost.ai/api-reference/batch/get-batch-results.md): Retrieves results from a completed batch job.
- [List batch jobs](https://docs.getbifrost.ai/api-reference/batch/list-batch-jobs.md): Lists batch jobs for a provider.
- [Retrieve a batch job](https://docs.getbifrost.ai/api-reference/batch/retrieve-a-batch-job.md): Retrieves a specific batch job by ID.
- [Cancel batch inference job (Bedrock format)](https://docs.getbifrost.ai/api-reference/bedrock-integration/cancel-batch-inference-job-bedrock-format.md): Cancels a batch inference job using AWS Bedrock format.
- [Converse with model (Bedrock format)](https://docs.getbifrost.ai/api-reference/bedrock-integration/converse-with-model-bedrock-format.md): Sends messages to a model using AWS Bedrock Converse API format.
- [Create batch inference job (Bedrock format)](https://docs.getbifrost.ai/api-reference/bedrock-integration/create-batch-inference-job-bedrock-format.md): Creates a batch inference job using AWS Bedrock format.
- [Invoke model (Bedrock format)](https://docs.getbifrost.ai/api-reference/bedrock-integration/invoke-model-bedrock-format.md): Invokes a model using AWS Bedrock InvokeModel API format. Accepts raw model-specific request body.
- [Invoke model with streaming (Bedrock format)](https://docs.getbifrost.ai/api-reference/bedrock-integration/invoke-model-with-streaming-bedrock-format.md): Invokes a model with streaming using AWS Bedrock InvokeModelWithResponseStream API format.
- [List batch inference jobs (Bedrock format)](https://docs.getbifrost.ai/api-reference/bedrock-integration/list-batch-inference-jobs-bedrock-format.md): Lists batch inference jobs using AWS Bedrock format.
- [Retrieve batch inference job (Bedrock format)](https://docs.getbifrost.ai/api-reference/bedrock-integration/retrieve-batch-inference-job-bedrock-format.md): Retrieves a batch inference job using AWS Bedrock format.
- [Stream converse with model (Bedrock format)](https://docs.getbifrost.ai/api-reference/bedrock-integration/stream-converse-with-model-bedrock-format.md): Streams messages from a model using AWS Bedrock Converse API format.
- [Clear cache by cache key](https://docs.getbifrost.ai/api-reference/cache/clear-cache-by-cache-key.md): Clears a cache entry by its direct cache key.
- [Clear cache by request ID](https://docs.getbifrost.ai/api-reference/cache/clear-cache-by-request-id.md): Clears cache entries associated with a specific request ID.
- [Create a chat completion](https://docs.getbifrost.ai/api-reference/chat-completions/create-a-chat-completion.md): Creates a completion for the provided messages. Supports streaming via SSE.
- [Chat with model (Cohere v2 format)](https://docs.getbifrost.ai/api-reference/cohere-integration/chat-with-model-cohere-v2-format.md): Sends a chat request using Cohere v2 API format.
- [Create embeddings (Cohere v2 format)](https://docs.getbifrost.ai/api-reference/cohere-integration/create-embeddings-cohere-v2-format.md): Creates embeddings using Cohere v2 API format.
- [Tokenize text (Cohere format)](https://docs.getbifrost.ai/api-reference/cohere-integration/tokenize-text-cohere-format.md): Tokenizes text using Cohere v1 API format.
- [Force pricing sync](https://docs.getbifrost.ai/api-reference/configuration/force-pricing-sync.md): Triggers an immediate pricing sync and resets the pricing sync timer.
- [Get configuration](https://docs.getbifrost.ai/api-reference/configuration/get-configuration.md): Retrieves the current Bifrost configuration including client config, framework config, auth config, and connection status for various stores.
- [Get proxy configuration](https://docs.getbifrost.ai/api-reference/configuration/get-proxy-configuration.md): Retrieves the current global proxy configuration.
- [Get version](https://docs.getbifrost.ai/api-reference/configuration/get-version.md): Returns the current Bifrost version information.
- [Update configuration](https://docs.getbifrost.ai/api-reference/configuration/update-configuration.md): Updates the Bifrost configuration. Supports hot-reloading of certain settings like drop_excess_requests. Some settings may require a restart to take effect.
- [Update proxy configuration](https://docs.getbifrost.ai/api-reference/configuration/update-proxy-configuration.md): Updates the global proxy configuration.
- [Create a container](https://docs.getbifrost.ai/api-reference/containers/create-a-container.md): Creates a new container for storing files and data.
- [Create a file in a container](https://docs.getbifrost.ai/api-reference/containers/create-a-file-in-a-container.md): Creates a new file in a container. You can either upload file content directly via multipart/form-data or reference an existing file by its ID.
- [Delete a container](https://docs.getbifrost.ai/api-reference/containers/delete-a-container.md): Deletes a container.
- [Delete a file from a container](https://docs.getbifrost.ai/api-reference/containers/delete-a-file-from-a-container.md): Deletes a file from a container.
- [Download file content from a container](https://docs.getbifrost.ai/api-reference/containers/download-file-content-from-a-container.md): Downloads the content of a file from a container.
- [List containers](https://docs.getbifrost.ai/api-reference/containers/list-containers.md): Lists containers for a provider.
- [List files in a container](https://docs.getbifrost.ai/api-reference/containers/list-files-in-a-container.md): Lists all files in a container.
- [Retrieve a container](https://docs.getbifrost.ai/api-reference/containers/retrieve-a-container.md): Retrieves a specific container by ID.
- [Retrieve a file from a container](https://docs.getbifrost.ai/api-reference/containers/retrieve-a-file-from-a-container.md): Retrieves metadata for a specific file in a container.
- [Count tokens](https://docs.getbifrost.ai/api-reference/count-tokens/count-tokens.md): Counts the number of tokens in the provided messages.
- [Create embeddings](https://docs.getbifrost.ai/api-reference/embeddings/create-embeddings.md): Creates an embedding vector representing the input text.
- [Delete a file](https://docs.getbifrost.ai/api-reference/files/delete-a-file.md): Deletes a file.
- [Download file content](https://docs.getbifrost.ai/api-reference/files/download-file-content.md): Downloads the content of a file.
- [List files](https://docs.getbifrost.ai/api-reference/files/list-files.md): Lists files for a provider.
- [Retrieve file metadata](https://docs.getbifrost.ai/api-reference/files/retrieve-file-metadata.md): Retrieves metadata for a specific file.
- [Upload a file](https://docs.getbifrost.ai/api-reference/files/upload-a-file.md): Uploads a file to be used with batch operations or other features.
- [Count tokens (Gemini format)](https://docs.getbifrost.ai/api-reference/genai-integration/count-tokens-gemini-format.md): Counts tokens using Google Gemini API format.
- [Delete file (Gemini format)](https://docs.getbifrost.ai/api-reference/genai-integration/delete-file-gemini-format.md): Deletes a file in Google Gemini API format.
- [Embed content (Gemini format)](https://docs.getbifrost.ai/api-reference/genai-integration/embed-content-gemini-format.md): Creates embeddings using Google Gemini API format.
- [Generate content (Gemini format)](https://docs.getbifrost.ai/api-reference/genai-integration/generate-content-gemini-format.md): Generates content using Google Gemini API format. The model is specified in the URL path.
- [Generate image (Gemini format)](https://docs.getbifrost.ai/api-reference/genai-integration/generate-image-gemini-format.md): For Imagen models, use the `:predict` suffix (e.g., `imagen-3.0-generate-001:predict`). For Gemini models, use `:generateContent` with `generationConfig.responseModalities: ["IMAGE"]` in the request body.
- [List files (Gemini format)](https://docs.getbifrost.ai/api-reference/genai-integration/list-files-gemini-format.md): Lists uploaded files in Google Gemini API format.
- [List models (Gemini format)](https://docs.getbifrost.ai/api-reference/genai-integration/list-models-gemini-format.md): Lists available models in Google Gemini API format.
- [Retrieve file (Gemini format)](https://docs.getbifrost.ai/api-reference/genai-integration/retrieve-file-gemini-format.md): Retrieves file metadata in Google Gemini API format.
- [Stream generate content (Gemini format)](https://docs.getbifrost.ai/api-reference/genai-integration/stream-generate-content-gemini-format.md): Streams content generation using Google Gemini API format. The model is specified in the URL path.
- [Upload file (Gemini format)](https://docs.getbifrost.ai/api-reference/genai-integration/upload-file-gemini-format.md): Uploads a file using Google Gemini API format.
- [Create customer](https://docs.getbifrost.ai/api-reference/governance/create-customer.md): Creates a new customer.
- [Create model config](https://docs.getbifrost.ai/api-reference/governance/create-model-config.md): Creates a new model configuration with budget and rate limit settings.
- [Create pricing override](https://docs.getbifrost.ai/api-reference/governance/create-pricing-override.md): Creates a new pricing override. The most specific matching scope always wins during cost resolution.
- [Create routing rule](https://docs.getbifrost.ai/api-reference/governance/create-routing-rule.md): Creates a new CEL-based routing rule for intelligent request routing. Provider and model can be left empty to use the incoming request values.
- [Create team](https://docs.getbifrost.ai/api-reference/governance/create-team.md): Creates a new team.
- [Create virtual key](https://docs.getbifrost.ai/api-reference/governance/create-virtual-key.md): Creates a new virtual key with the specified configuration.
- [Delete customer](https://docs.getbifrost.ai/api-reference/governance/delete-customer.md): Deletes a customer.
- [Delete model config](https://docs.getbifrost.ai/api-reference/governance/delete-model-config.md): Deletes a model configuration.
- [Delete pricing override](https://docs.getbifrost.ai/api-reference/governance/delete-pricing-override.md): Deletes a pricing override by ID.
- [Delete provider governance](https://docs.getbifrost.ai/api-reference/governance/delete-provider-governance.md): Removes governance settings (budget and rate limits) for a specific provider.
- [Delete routing rule](https://docs.getbifrost.ai/api-reference/governance/delete-routing-rule.md): Deletes a routing rule.
- [Delete team](https://docs.getbifrost.ai/api-reference/governance/delete-team.md): Deletes a team.
- [Delete virtual key](https://docs.getbifrost.ai/api-reference/governance/delete-virtual-key.md): Deletes a virtual key.
- [Get customer](https://docs.getbifrost.ai/api-reference/governance/get-customer.md): Returns a specific customer by ID.
- [Get model config](https://docs.getbifrost.ai/api-reference/governance/get-model-config.md): Returns a specific model configuration by ID.
- [Get routing rule](https://docs.getbifrost.ai/api-reference/governance/get-routing-rule.md): Returns a specific routing rule by ID.
- [Get team](https://docs.getbifrost.ai/api-reference/governance/get-team.md): Returns a specific team by ID.
- [Get virtual key](https://docs.getbifrost.ai/api-reference/governance/get-virtual-key.md): Returns a specific virtual key by ID.
- [Get virtual key quota](https://docs.getbifrost.ai/api-reference/governance/get-virtual-key-quota.md): Returns the budget and rate limit quota for the authenticated virtual key. This is a self-service endpoint — no admin authentication required. The virtual key value itself (provided via header) is the credential.
- [List budgets](https://docs.getbifrost.ai/api-reference/governance/list-budgets.md): Returns a list of all budgets. Use the `from_memory` query parameter to get data from in-memory cache.
- [List customers](https://docs.getbifrost.ai/api-reference/governance/list-customers.md): Returns a list of all customers.
- [List model configs](https://docs.getbifrost.ai/api-reference/governance/list-model-configs.md): Returns a list of all model configurations with their budget and rate limit settings.
- [List pricing overrides](https://docs.getbifrost.ai/api-reference/governance/list-pricing-overrides.md): Returns all pricing overrides, optionally filtered by scope.
- [List provider governance](https://docs.getbifrost.ai/api-reference/governance/list-provider-governance.md): Returns a list of all providers with their governance settings (budget and rate limits).
- [List rate limits](https://docs.getbifrost.ai/api-reference/governance/list-rate-limits.md): Returns a list of all rate limits. Use the `from_memory` query parameter to get data from in-memory cache.
- [List routing rules](https://docs.getbifrost.ai/api-reference/governance/list-routing-rules.md): Returns a list of all routing rules configured for intelligent request routing across providers.
- [List teams](https://docs.getbifrost.ai/api-reference/governance/list-teams.md): Returns a list of all teams.
- [List virtual keys](https://docs.getbifrost.ai/api-reference/governance/list-virtual-keys.md): Returns a list of all virtual keys with their configurations.
- [Update customer](https://docs.getbifrost.ai/api-reference/governance/update-customer.md): Updates an existing customer.
- [Update model config](https://docs.getbifrost.ai/api-reference/governance/update-model-config.md): Updates an existing model configuration's budget and rate limit settings.
- [Update pricing override](https://docs.getbifrost.ai/api-reference/governance/update-pricing-override.md): Updates an existing pricing override. Omitted fields are merged from the existing record. The `patch` field is always replaced in full when provided.
- [Update provider governance](https://docs.getbifrost.ai/api-reference/governance/update-provider-governance.md): Updates governance settings (budget and rate limits) for a specific provider.
- [Update routing rule](https://docs.getbifrost.ai/api-reference/governance/update-routing-rule.md): Updates an existing routing rule's configuration.
- [Update team](https://docs.getbifrost.ai/api-reference/governance/update-team.md): Updates an existing team.
- [Update virtual key](https://docs.getbifrost.ai/api-reference/governance/update-virtual-key.md): Updates an existing virtual key's configuration.
- [Health check](https://docs.getbifrost.ai/api-reference/health/health-check.md): Returns the health status of the Bifrost server. Checks connectivity to config store, log store, and vector store if configured.
- [Create Variation](https://docs.getbifrost.ai/api-reference/images/create-variation.md): Creates variations of an image. Request must be sent as multipart/form-data with `model` and `image` (or `image[]`). Does not support streaming.
- [Edit an image](https://docs.getbifrost.ai/api-reference/images/edit-an-image.md): Edits an image using a text prompt and optional mask. Request must be sent as multipart/form-data with at least `model`, `prompt` (unless `type` is `background_removal`), and `image` (or `image[]`).
- [Generate an image](https://docs.getbifrost.ai/api-reference/images/generate-an-image.md): Generates images from text prompts using the specified model.
- [MCP protocol message](https://docs.getbifrost.ai/api-reference/infrastructure/mcp-protocol-message.md): Receives a JSON-RPC 2.0 message for the MCP protocol server. Returns a JSON-RPC 2.0 response, or null for notifications.
- [MCP protocol SSE stream](https://docs.getbifrost.ai/api-reference/infrastructure/mcp-protocol-sse-stream.md): Opens a Server-Sent Events stream for the MCP protocol server. Returns `Content-Type: text/event-stream`.
- [Prometheus metrics](https://docs.getbifrost.ai/api-reference/infrastructure/prometheus-metrics.md): Returns Prometheus-formatted metrics for monitoring.
- [WebSocket connection](https://docs.getbifrost.ai/api-reference/infrastructure/websocket-connection.md): Upgrades to a WebSocket connection for real-time updates. Server pushes log events, MCP log events, and store update notifications. Heartbeat pings are sent every 30 seconds.
- [Chat completions (LangChain - OpenAI format)](https://docs.getbifrost.ai/api-reference/langchain-integration/chat-completions-langchain--openai-format.md): Creates a chat completion using OpenAI-compatible format via LangChain.
- [Chat with model (LangChain - Cohere format)](https://docs.getbifrost.ai/api-reference/langchain-integration/chat-with-model-langchain--cohere-format.md): Sends a chat request using Cohere-compatible format via LangChain.
- [Converse with model (LangChain - Bedrock format)](https://docs.getbifrost.ai/api-reference/langchain-integration/converse-with-model-langchain--bedrock-format.md): Sends messages using AWS Bedrock Converse-compatible format via LangChain.
- [Count input tokens (LangChain - OpenAI format)](https://docs.getbifrost.ai/api-reference/langchain-integration/count-input-tokens-langchain--openai-format.md): Counts the number of tokens in a Responses API request via LangChain.
- [Count tokens (LangChain - Anthropic format)](https://docs.getbifrost.ai/api-reference/langchain-integration/count-tokens-langchain--anthropic-format.md): Counts tokens using Anthropic-compatible format via LangChain.
- [Create embeddings (LangChain - Cohere format)](https://docs.getbifrost.ai/api-reference/langchain-integration/create-embeddings-langchain--cohere-format.md): Creates embeddings using Cohere-compatible format via LangChain.
- [Create embeddings (LangChain - OpenAI format)](https://docs.getbifrost.ai/api-reference/langchain-integration/create-embeddings-langchain--openai-format.md): Creates embeddings using OpenAI-compatible format via LangChain.
- [Create message (LangChain - Anthropic format)](https://docs.getbifrost.ai/api-reference/langchain-integration/create-message-langchain--anthropic-format.md): Creates a message using Anthropic-compatible format via LangChain.
- [Create response (LangChain - OpenAI Responses API)](https://docs.getbifrost.ai/api-reference/langchain-integration/create-response-langchain--openai-responses-api.md): Creates a response using OpenAI Responses API format via LangChain. Supports streaming via SSE.
- [Create speech (LangChain - OpenAI TTS)](https://docs.getbifrost.ai/api-reference/langchain-integration/create-speech-langchain--openai-tts.md): Generates audio from text using OpenAI TTS via LangChain.
- [Create transcription (LangChain - OpenAI Whisper)](https://docs.getbifrost.ai/api-reference/langchain-integration/create-transcription-langchain--openai-whisper.md): Transcribes audio into text using OpenAI Whisper via LangChain.
- [Generate content (LangChain - Gemini format)](https://docs.getbifrost.ai/api-reference/langchain-integration/generate-content-langchain--gemini-format.md): Generates content using Google Gemini-compatible format via LangChain.
- [List models (LangChain - Gemini format)](https://docs.getbifrost.ai/api-reference/langchain-integration/list-models-langchain--gemini-format.md): Lists available models in Google Gemini API format via LangChain.
- [List models (LangChain - OpenAI format)](https://docs.getbifrost.ai/api-reference/langchain-integration/list-models-langchain--openai-format.md): Lists available models using OpenAI-compatible format via LangChain.
- [Stream converse with model (LangChain - Bedrock format)](https://docs.getbifrost.ai/api-reference/langchain-integration/stream-converse-with-model-langchain--bedrock-format.md): Streams messages using AWS Bedrock Converse-compatible format via LangChain.
- [Stream generate content (LangChain - Gemini format)](https://docs.getbifrost.ai/api-reference/langchain-integration/stream-generate-content-langchain--gemini-format.md): Streams content generation using Google Gemini-compatible format via LangChain.
- [Text completions (LangChain - OpenAI format)](https://docs.getbifrost.ai/api-reference/langchain-integration/text-completions-langchain--openai-format.md): Creates a text completion using OpenAI-compatible format via LangChain. This is the legacy completions API.
- [Tokenize text (LangChain - Cohere format)](https://docs.getbifrost.ai/api-reference/langchain-integration/tokenize-text-langchain--cohere-format.md): Tokenizes text using Cohere-compatible format via LangChain.
- [Chat completions (LiteLLM - OpenAI format)](https://docs.getbifrost.ai/api-reference/litellm-integration/chat-completions-litellm--openai-format.md): Creates a chat completion using OpenAI-compatible format via LiteLLM.
- [Chat with model (LiteLLM - Cohere format)](https://docs.getbifrost.ai/api-reference/litellm-integration/chat-with-model-litellm--cohere-format.md): Sends a chat request using Cohere-compatible format via LiteLLM.
- [Converse with model (LiteLLM - Bedrock format)](https://docs.getbifrost.ai/api-reference/litellm-integration/converse-with-model-litellm--bedrock-format.md): Sends messages using AWS Bedrock Converse-compatible format via LiteLLM.
- [Count input tokens (LiteLLM - OpenAI format)](https://docs.getbifrost.ai/api-reference/litellm-integration/count-input-tokens-litellm--openai-format.md): Counts the number of tokens in a Responses API request via LiteLLM.
- [Create embeddings (LiteLLM - Cohere format)](https://docs.getbifrost.ai/api-reference/litellm-integration/create-embeddings-litellm--cohere-format.md): Creates embeddings using Cohere-compatible format via LiteLLM.
- [Create embeddings (LiteLLM - OpenAI format)](https://docs.getbifrost.ai/api-reference/litellm-integration/create-embeddings-litellm--openai-format.md): Creates embeddings using OpenAI-compatible format via LiteLLM.
- [Create message (LiteLLM - Anthropic format)](https://docs.getbifrost.ai/api-reference/litellm-integration/create-message-litellm--anthropic-format.md): Creates a message using Anthropic-compatible format via LiteLLM.
- [Create response (LiteLLM - OpenAI Responses API)](https://docs.getbifrost.ai/api-reference/litellm-integration/create-response-litellm--openai-responses-api.md): Creates a response using OpenAI Responses API format via LiteLLM. Supports streaming via SSE.
- [Create speech (LiteLLM - OpenAI TTS)](https://docs.getbifrost.ai/api-reference/litellm-integration/create-speech-litellm--openai-tts.md): Generates audio from text using OpenAI TTS via LiteLLM.
- [Create transcription (LiteLLM - OpenAI Whisper)](https://docs.getbifrost.ai/api-reference/litellm-integration/create-transcription-litellm--openai-whisper.md): Transcribes audio into text using OpenAI Whisper via LiteLLM.
- [Generate content (LiteLLM - Gemini format)](https://docs.getbifrost.ai/api-reference/litellm-integration/generate-content-litellm--gemini-format.md): Generates content using Google Gemini-compatible format via LiteLLM.
- [List models (LiteLLM - Gemini format)](https://docs.getbifrost.ai/api-reference/litellm-integration/list-models-litellm--gemini-format.md): Lists available models in Google Gemini API format via LiteLLM.
- [List models (LiteLLM - OpenAI format)](https://docs.getbifrost.ai/api-reference/litellm-integration/list-models-litellm--openai-format.md): Lists available models using OpenAI-compatible format via LiteLLM.
- [Stream converse with model (LiteLLM - Bedrock format)](https://docs.getbifrost.ai/api-reference/litellm-integration/stream-converse-with-model-litellm--bedrock-format.md): Streams messages using AWS Bedrock Converse-compatible format via LiteLLM.
- [Stream generate content (LiteLLM - Gemini format)](https://docs.getbifrost.ai/api-reference/litellm-integration/stream-generate-content-litellm--gemini-format.md): Streams content generation using Google Gemini-compatible format via LiteLLM.
- [Text completions (LiteLLM - OpenAI format)](https://docs.getbifrost.ai/api-reference/litellm-integration/text-completions-litellm--openai-format.md): Creates a text completion using OpenAI-compatible format via LiteLLM. This is the legacy completions API.
- [Tokenize text (LiteLLM - Cohere format)](https://docs.getbifrost.ai/api-reference/litellm-integration/tokenize-text-litellm--cohere-format.md): Tokenizes text using Cohere-compatible format via LiteLLM.
- [Delete logs](https://docs.getbifrost.ai/api-reference/logging/delete-logs.md): Deletes logs by their IDs.
- [Delete MCP tool logs](https://docs.getbifrost.ai/api-reference/logging/delete-mcp-tool-logs.md): Deletes MCP tool logs by their IDs.
- [Get a single log entry](https://docs.getbifrost.ai/api-reference/logging/get-a-single-log-entry.md): Retrieves a single log entry by its ID.
- [Get available filter data](https://docs.getbifrost.ai/api-reference/logging/get-available-filter-data.md): Returns all unique filter data from logs (models, keys, virtual keys).
- [Get available MCP log filter data](https://docs.getbifrost.ai/api-reference/logging/get-available-mcp-log-filter-data.md): Returns all unique filter data from MCP tool logs (tool names, server labels).
- [Get cost histogram](https://docs.getbifrost.ai/api-reference/logging/get-cost-histogram.md): Returns time-bucketed cost data with model breakdown.
- [Get cost histogram by provider](https://docs.getbifrost.ai/api-reference/logging/get-cost-histogram-by-provider.md): Returns time-bucketed cost data with provider breakdown.
- [Get dropped requests count](https://docs.getbifrost.ai/api-reference/logging/get-dropped-requests-count.md): Returns the number of dropped requests.
- [Get latency histogram](https://docs.getbifrost.ai/api-reference/logging/get-latency-histogram.md): Returns time-bucketed latency percentiles (avg, p90, p95, p99).
- [Get latency histogram by provider](https://docs.getbifrost.ai/api-reference/logging/get-latency-histogram-by-provider.md): Returns time-bucketed latency percentiles with provider breakdown.
- [Get log statistics](https://docs.getbifrost.ai/api-reference/logging/get-log-statistics.md): Returns statistics for logs matching the specified filters.
- [Get logs](https://docs.getbifrost.ai/api-reference/logging/get-logs.md): Retrieves logs with filtering, search, and pagination via query parameters.
- [Get MCP tool log statistics](https://docs.getbifrost.ai/api-reference/logging/get-mcp-tool-log-statistics.md): Returns statistics for MCP tool logs matching the specified filters.
- [Get MCP tool logs](https://docs.getbifrost.ai/api-reference/logging/get-mcp-tool-logs.md): Retrieves MCP tool execution logs with filtering, search, and pagination via query parameters.
- [Get model usage histogram](https://docs.getbifrost.ai/api-reference/logging/get-model-usage-histogram.md): Returns time-bucketed model usage with success/error breakdown.
- [Get request count histogram](https://docs.getbifrost.ai/api-reference/logging/get-request-count-histogram.md): Returns time-bucketed request counts. Bucket size is auto-calculated from the time range.
- [Get token histogram by provider](https://docs.getbifrost.ai/api-reference/logging/get-token-histogram-by-provider.md): Returns time-bucketed token usage with provider breakdown.
- [Get token usage histogram](https://docs.getbifrost.ai/api-reference/logging/get-token-usage-histogram.md): Returns time-bucketed token usage (prompt, completion, total).
- [Recalculate log costs](https://docs.getbifrost.ai/api-reference/logging/recalculate-log-costs.md): Recomputes missing costs in batches. Processes logs with missing cost values and updates them based on current pricing data.
- [Add MCP client](https://docs.getbifrost.ai/api-reference/mcp/add-mcp-client.md): Adds a new MCP client with the specified configuration. Note: tool_pricing is not available when creating a new client as tools are fetched after client creation.
- [Complete MCP client OAuth flow](https://docs.getbifrost.ai/api-reference/mcp/complete-mcp-client-oauth-flow.md): Completes the OAuth flow for an MCP client after the user has authorized the request. This endpoint should be called after the OAuth provider redirects back to the callback endpoint and the OAuth token has been stored. It retrieves the pending MCP client configuration and establishes the connection…
- [Edit MCP client](https://docs.getbifrost.ai/api-reference/mcp/edit-mcp-client.md): Updates an existing MCP client's configuration. Unlike client creation, tool_pricing can be included to set per-tool execution costs since tools are already fetched. Optionally provide vk_configs to manage which virtual keys have access to this MCP server and with which tools. When provided, this fu…
- [Execute MCP tool](https://docs.getbifrost.ai/api-reference/mcp/execute-mcp-tool.md): Executes an MCP tool and returns the result.
- [List MCP clients](https://docs.getbifrost.ai/api-reference/mcp/list-mcp-clients.md): Returns a list of all configured MCP clients with their tools and connection state.
- [Reconnect MCP client](https://docs.getbifrost.ai/api-reference/mcp/reconnect-mcp-client.md): Reconnects an MCP client that is in an error or disconnected state.
- [Remove MCP client](https://docs.getbifrost.ai/api-reference/mcp/remove-mcp-client.md): Removes an MCP client from the configuration.
- [List available models](https://docs.getbifrost.ai/api-reference/models/list-available-models.md): Lists available models. If provider is not specified, lists all models from all configured providers.
- [Authorization endpoint (OAuth 2.1)](https://docs.getbifrost.ai/api-reference/oauth/authorization-endpoint-oauth-21.md): OAuth 2.1 authorization endpoint. Validates the request parameters, creates a browser-bound `PendingFlow` record (15-minute TTL), and redirects the user to the Bifrost consent screen at `/oauth/consent?flow_id=xxx`.
- [Authorization Server Metadata (RFC 8414)](https://docs.getbifrost.ai/api-reference/oauth/authorization-server-metadata-rfc-8414.md): Returns the OAuth 2.0 Authorization Server Metadata document per RFC 8414.
- [Get OAuth config status](https://docs.getbifrost.ai/api-reference/oauth/get-oauth-config-status.md): Retrieves the current status of an OAuth configuration. Shows whether the OAuth flow is pending, authorized, or failed, and includes token expiration and scopes if authorized.
- [OAuth callback endpoint](https://docs.getbifrost.ai/api-reference/oauth/oauth-callback-endpoint.md): Handles the OAuth provider callback after user authorization. This endpoint processes the authorization code and exchanges it for an access token. On success, displays an HTML page that closes the authorization window.
- [Protected Resource Metadata (RFC 9728)](https://docs.getbifrost.ai/api-reference/oauth/protected-resource-metadata-rfc-9728.md): Returns the OAuth 2.0 Protected Resource Metadata document per RFC 9728.
- [Register OAuth client (RFC 7591)](https://docs.getbifrost.ai/api-reference/oauth/register-oauth-client-rfc-7591.md): Dynamic Client Registration per RFC 7591. MCP clients (Claude Code, Cursor, etc.) call this endpoint to obtain a `client_id` before initiating the authorization flow.
- [Revoke OAuth config](https://docs.getbifrost.ai/api-reference/oauth/revoke-oauth-config.md): Revokes an OAuth configuration and its associated access token. After revocation, the MCP client will no longer be able to use this OAuth token.
- [Token endpoint (OAuth 2.1)](https://docs.getbifrost.ai/api-reference/oauth/token-endpoint-oauth-21.md): OAuth 2.1 token endpoint. Exchanges a single-use authorization code (5-minute TTL) for a Bifrost-issued access token (24-hour TTL) using PKCE verification.
- [Upstream OAuth proxy — authorize with upstream service](https://docs.getbifrost.ai/api-reference/oauth/upstream-oauth-proxy-—-authorize-with-upstream-service.md): Initiates an OAuth flow with an upstream MCP service (Notion, GitHub, etc.) on behalf of the current user. Used during the consent flow (via "Connect" buttons on the MCPs page) and at runtime when a tool call is made to an unauthenticated service.
- [Perform OCR](https://docs.getbifrost.ai/api-reference/ocr/perform-ocr.md): Extracts text and content from documents or images using optical character recognition. Supports PDF URLs, base64-encoded documents, and image URLs.
- [Cancel batch job (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/cancel-batch-job-openai-format.md): Cancels a batch processing job.
- [Count input tokens](https://docs.getbifrost.ai/api-reference/openai-integration/count-input-tokens.md): Counts the number of tokens in a Responses API request.
- [Create batch job (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/create-batch-job-openai-format.md): Creates a batch processing job.
- [Create chat completion (Azure OpenAI)](https://docs.getbifrost.ai/api-reference/openai-integration/create-chat-completion-azure-openai.md): Creates a chat completion using Azure OpenAI deployment.
- [Create chat completion (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/create-chat-completion-openai-format.md): Creates a chat completion using OpenAI-compatible format. Supports streaming via SSE.
- [Create container (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/create-container-openai-format.md): Creates a new container for storing files and data.
- [Create embeddings (Azure OpenAI)](https://docs.getbifrost.ai/api-reference/openai-integration/create-embeddings-azure-openai.md)
- [Create embeddings (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/create-embeddings-openai-format.md): Creates embedding vectors for the input text.
- [Create file in container (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/create-file-in-container-openai-format.md): Creates a new file in a container. You can either upload file content directly via multipart/form-data or reference an existing file by its ID.
- [Create image](https://docs.getbifrost.ai/api-reference/openai-integration/create-image.md): Generates images from text prompts using OpenAI-compatible format.
- [Create image (Azure OpenAI)](https://docs.getbifrost.ai/api-reference/openai-integration/create-image-azure-openai.md): Generates images from text prompts using Azure OpenAI deployment.
- [Create response (Azure OpenAI)](https://docs.getbifrost.ai/api-reference/openai-integration/create-response-azure-openai.md)
- [Create response (OpenAI Responses API)](https://docs.getbifrost.ai/api-reference/openai-integration/create-response-openai-responses-api.md): Creates a response using OpenAI Responses API format. Supports streaming via SSE.
- [Create speech (Azure OpenAI TTS)](https://docs.getbifrost.ai/api-reference/openai-integration/create-speech-azure-openai-tts.md)
- [Create speech (OpenAI TTS)](https://docs.getbifrost.ai/api-reference/openai-integration/create-speech-openai-tts.md): Generates audio from text using OpenAI TTS. Supports streaming via SSE when stream_format is set to 'sse'.
- [Create text completion (Azure OpenAI)](https://docs.getbifrost.ai/api-reference/openai-integration/create-text-completion-azure-openai.md)
- [Create text completion (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/create-text-completion-openai-format.md): Creates a text completion using OpenAI-compatible format. This is the legacy completions API.
- [Create transcription (Azure OpenAI)](https://docs.getbifrost.ai/api-reference/openai-integration/create-transcription-azure-openai.md)
- [Create transcription (OpenAI Whisper)](https://docs.getbifrost.ai/api-reference/openai-integration/create-transcription-openai-whisper.md): Transcribes audio into text using OpenAI Whisper.
- [Delete container (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/delete-container-openai-format.md): Deletes a container.
- [Delete file from container (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/delete-file-from-container-openai-format.md): Deletes a file from a container.
- [Delete file (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/delete-file-openai-format.md): Deletes an uploaded file.
- [Get file content from container (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/get-file-content-from-container-openai-format.md): Downloads the content of a file from a container.
- [Get file content (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/get-file-content-openai-format.md): Retrieves the content of an uploaded file.
- [List batch jobs (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/list-batch-jobs-openai-format.md): Lists batch processing jobs.
- [List containers (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/list-containers-openai-format.md): Lists containers for a provider.
- [List files in container (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/list-files-in-container-openai-format.md): Lists all files in a container.
- [List files (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/list-files-openai-format.md): Lists uploaded files.
- [List models (Azure OpenAI)](https://docs.getbifrost.ai/api-reference/openai-integration/list-models-azure-openai.md)
- [List models (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/list-models-openai-format.md): Lists available models in OpenAI format.
- [Retrieve batch job (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/retrieve-batch-job-openai-format.md): Retrieves details of a batch processing job.
- [Retrieve container (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/retrieve-container-openai-format.md): Retrieves a specific container by ID.
- [Retrieve file from container (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/retrieve-file-from-container-openai-format.md): Retrieves metadata for a specific file in a container.
- [Retrieve file metadata (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/retrieve-file-metadata-openai-format.md): Retrieves metadata for an uploaded file.
- [Upload file (OpenAI format)](https://docs.getbifrost.ai/api-reference/openai-integration/upload-file-openai-format.md): Uploads a file for use with batch processing or other features.
- [Consent identity selection page](https://docs.getbifrost.ai/api-reference/per-user-oauth/consent-identity-selection-page.md): Renders the identity selection screen where the user chooses how to identify themselves for the session: Virtual Key, User ID, or Skip (session-only auth).
- [Consent MCP services page](https://docs.getbifrost.ai/api-reference/per-user-oauth/consent-mcp-services-page.md): Renders the MCP services connection screen. Shows all per-user OAuth MCP servers available on the user's Virtual Key (or all servers if no VK was selected). Each service shows a "Connect" link or a "Connected ✓" badge.
- [Finalize consent flow](https://docs.getbifrost.ai/api-reference/per-user-oauth/finalize-consent-flow.md): Finalizes the consent flow atomically: 1. Creates a `TablePerUserOAuthSession` (24h Bifrost session token) 2. Transfers upstream tokens from the flow proxy to the session 3. Issues a single-use `TablePerUserOAuthCode` (5-minute TTL, PKCE-bound) 4. Deletes the `PendingFlow` 5. Redirects to the MCP cl…
- [Skip identity selection](https://docs.getbifrost.ai/api-reference/per-user-oauth/skip-identity-selection.md): Skips identity selection and proceeds directly to the MCPs page. Upstream service tokens will be stored against the session token only (not a persistent identity), so they will not carry over to other sessions or the LLM Gateway.
- [Submit User ID identity](https://docs.getbifrost.ai/api-reference/per-user-oauth/submit-user-id-identity.md): Links a self-declared User ID to the pending flow as the user's identity. On success, redirects to the MCPs page.
- [Submit Virtual Key identity](https://docs.getbifrost.ai/api-reference/per-user-oauth/submit-virtual-key-identity.md): Validates the submitted Virtual Key and links it to the pending flow as the user's identity. On success, redirects to the MCPs page. On failure, redirects back to the identity page with an error message.
- [Create a new plugin](https://docs.getbifrost.ai/api-reference/plugins/create-a-new-plugin.md): Creates a new plugin with the specified configuration.
- [Delete a plugin](https://docs.getbifrost.ai/api-reference/plugins/delete-a-plugin.md): Removes a plugin from the configuration and stops it if running.
- [Get a specific plugin](https://docs.getbifrost.ai/api-reference/plugins/get-a-specific-plugin.md): Returns the configuration for a specific plugin. The response includes the plugin status with types array showing which interfaces the plugin implements (llm, mcp, http). The `actualName` field shows the plugin name from GetName() (used as the map key), which may differ from the display name (`name`…
- [List all plugins](https://docs.getbifrost.ai/api-reference/plugins/list-all-plugins.md): Returns a list of all plugins with their configurations and status. The `actualName` field contains the plugin name from `GetName()` (used as the map key), while `name` contains the display name from the configuration. The `types` array in the status shows which interfaces the plugin implements (llm…
- [Update a plugin](https://docs.getbifrost.ai/api-reference/plugins/update-a-plugin.md): Updates a plugin's configuration. Will reload or stop the plugin based on enabled status. The response `actualName` field shows the plugin name from GetName() (used as the map key), which may differ from the display name (`name`).
- [Commit session as version](https://docs.getbifrost.ai/api-reference/prompt-repository/commit-session-as-version.md): Commits the current session state as a new prompt version.
- [Create folder](https://docs.getbifrost.ai/api-reference/prompt-repository/create-folder.md): Creates a new prompt folder.
- [Create prompt](https://docs.getbifrost.ai/api-reference/prompt-repository/create-prompt.md): Creates a new prompt.
- [Create prompt session](https://docs.getbifrost.ai/api-reference/prompt-repository/create-prompt-session.md): Creates a new playground session for a prompt.
- [Create prompt version](https://docs.getbifrost.ai/api-reference/prompt-repository/create-prompt-version.md): Creates a new version for a prompt.
- [Delete folder](https://docs.getbifrost.ai/api-reference/prompt-repository/delete-folder.md): Deletes a folder and cascades to contained prompts.
- [Delete prompt](https://docs.getbifrost.ai/api-reference/prompt-repository/delete-prompt.md): Deletes a prompt and all its versions and sessions.
- [Delete prompt session](https://docs.getbifrost.ai/api-reference/prompt-repository/delete-prompt-session.md): Deletes a specific session.
- [Delete prompt version](https://docs.getbifrost.ai/api-reference/prompt-repository/delete-prompt-version.md): Deletes a specific version.
- [Get folder](https://docs.getbifrost.ai/api-reference/prompt-repository/get-folder.md): Returns a folder by ID.
- [Get prompt](https://docs.getbifrost.ai/api-reference/prompt-repository/get-prompt.md): Returns a prompt by ID with its latest version.
- [Get prompt session](https://docs.getbifrost.ai/api-reference/prompt-repository/get-prompt-session.md): Returns a specific session by ID.
- [Get prompt version](https://docs.getbifrost.ai/api-reference/prompt-repository/get-prompt-version.md): Returns a specific version by ID.
- [List folders](https://docs.getbifrost.ai/api-reference/prompt-repository/list-folders.md): Returns all prompt folders.
- [List prompt sessions](https://docs.getbifrost.ai/api-reference/prompt-repository/list-prompt-sessions.md): Returns all sessions for a prompt.
- [List prompt versions](https://docs.getbifrost.ai/api-reference/prompt-repository/list-prompt-versions.md): Returns all versions for a prompt.
- [List prompts](https://docs.getbifrost.ai/api-reference/prompt-repository/list-prompts.md): Returns all prompts, optionally filtered by folder.
- [Rename prompt session](https://docs.getbifrost.ai/api-reference/prompt-repository/rename-prompt-session.md): Renames a session.
- [Update folder](https://docs.getbifrost.ai/api-reference/prompt-repository/update-folder.md): Updates a folder's name or description.
- [Update prompt](https://docs.getbifrost.ai/api-reference/prompt-repository/update-prompt.md): Updates a prompt's name or folder.
- [Update prompt session](https://docs.getbifrost.ai/api-reference/prompt-repository/update-prompt-session.md): Updates a session's messages, model params, etc.
- [Add a new provider](https://docs.getbifrost.ai/api-reference/providers/add-a-new-provider.md): Adds a new provider with the specified configuration.
- [Create a key for a provider](https://docs.getbifrost.ai/api-reference/providers/create-a-key-for-a-provider.md): Creates a new API key for the specified provider. The key `id` is auto-generated if omitted. `enabled` defaults to `true` if omitted. `value` is required and must not be empty. Keys cannot be created on keyless providers.
- [Delete a key from a provider](https://docs.getbifrost.ai/api-reference/providers/delete-a-key-from-a-provider.md): Deletes a key from the specified provider. Returns the deleted key.
- [Delete a provider](https://docs.getbifrost.ai/api-reference/providers/delete-a-provider.md): Removes a provider from the configuration.
- [Get a specific key for a provider](https://docs.getbifrost.ai/api-reference/providers/get-a-specific-key-for-a-provider.md): Returns a single key for the specified provider.
- [Get a specific provider](https://docs.getbifrost.ai/api-reference/providers/get-a-specific-provider.md): Returns the configuration for a specific provider.
- [Get model parameters](https://docs.getbifrost.ai/api-reference/providers/get-model-parameters.md): Returns the available parameter definitions for models.
- [List all keys](https://docs.getbifrost.ai/api-reference/providers/list-all-keys.md): Returns a list of all configured API keys across all providers.
- [List all providers](https://docs.getbifrost.ai/api-reference/providers/list-all-providers.md): Returns a list of all configured providers with their configurations and status.
- [List base models](https://docs.getbifrost.ai/api-reference/providers/list-base-models.md): Returns a list of base models from the model catalog.
- [List keys for a provider](https://docs.getbifrost.ai/api-reference/providers/list-keys-for-a-provider.md): Returns all keys configured for a specific provider.
- [List model details](https://docs.getbifrost.ai/api-reference/providers/list-model-details.md): Lists available models with capability metadata, when available from the model catalog, with optional filtering by query, provider, or keys.
- [List models](https://docs.getbifrost.ai/api-reference/providers/list-models.md): Lists available models with optional filtering by query, provider, or keys.
- [Update a key for a provider](https://docs.getbifrost.ai/api-reference/providers/update-a-key-for-a-provider.md): Updates an existing key. Send the full key object. Redacted values sent back unchanged are automatically preserved (the server merges them with the stored raw values).
- [Update a provider](https://docs.getbifrost.ai/api-reference/providers/update-a-provider.md): Updates a provider's configuration. Expects ALL fields to be provided, including both edited and non-edited fields. Partial updates are not supported.
- [Chat completions (PydanticAI - OpenAI format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/chat-completions-pydanticai--openai-format.md): Creates a chat completion using OpenAI-compatible format via PydanticAI.
- [Chat with model (PydanticAI - Cohere format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/chat-with-model-pydanticai--cohere-format.md): Sends a chat request using Cohere-compatible format via PydanticAI.
- [Converse with model (PydanticAI - Bedrock format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/converse-with-model-pydanticai--bedrock-format.md): Sends messages using AWS Bedrock Converse-compatible format via PydanticAI.
- [Count input tokens (PydanticAI - OpenAI format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/count-input-tokens-pydanticai--openai-format.md): Counts the number of tokens in a Responses API request via PydanticAI.
- [Create embeddings (PydanticAI - Cohere format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/create-embeddings-pydanticai--cohere-format.md): Creates embeddings using Cohere-compatible format via PydanticAI.
- [Create embeddings (PydanticAI - OpenAI format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/create-embeddings-pydanticai--openai-format.md): Creates embeddings using OpenAI-compatible format via PydanticAI.
- [Create message (PydanticAI - Anthropic format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/create-message-pydanticai--anthropic-format.md): Creates a message using Anthropic-compatible format via PydanticAI.
- [Create response (PydanticAI - OpenAI Responses API)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/create-response-pydanticai--openai-responses-api.md): Creates a response using OpenAI Responses API format via PydanticAI. Supports streaming via SSE.
- [Create speech (PydanticAI - OpenAI TTS)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/create-speech-pydanticai--openai-tts.md): Generates audio from text using OpenAI TTS via PydanticAI.
- [Create transcription (PydanticAI - OpenAI Whisper)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/create-transcription-pydanticai--openai-whisper.md): Transcribes audio into text using OpenAI Whisper via PydanticAI.
- [Generate content (PydanticAI - Gemini format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/generate-content-pydanticai--gemini-format.md): Generates content using Google Gemini-compatible format via PydanticAI.
- [List models (PydanticAI - Gemini format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/list-models-pydanticai--gemini-format.md): Lists available models in Google Gemini API format via PydanticAI.
- [List models (PydanticAI - OpenAI format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/list-models-pydanticai--openai-format.md): Lists available models using OpenAI-compatible format via PydanticAI.
- [Stream converse with model (PydanticAI - Bedrock format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/stream-converse-with-model-pydanticai--bedrock-format.md): Streams messages using AWS Bedrock Converse-compatible format via PydanticAI.
- [Stream generate content (PydanticAI - Gemini format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/stream-generate-content-pydanticai--gemini-format.md): Streams content generation using Google Gemini-compatible format via PydanticAI.
- [Text completions (PydanticAI - OpenAI format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/text-completions-pydanticai--openai-format.md): Creates a text completion using OpenAI-compatible format via PydanticAI. This is the legacy completions API.
- [Tokenize text (PydanticAI - Cohere format)](https://docs.getbifrost.ai/api-reference/pydanticai-integration/tokenize-text-pydanticai--cohere-format.md): Tokenizes text using Cohere v1 API format via PydanticAI.
- [Rerank documents](https://docs.getbifrost.ai/api-reference/rerank/rerank-documents.md): Reorders input documents by relevance to a query.
- [Create a response](https://docs.getbifrost.ai/api-reference/responses/create-a-response.md): Creates a response using the OpenAI Responses API format. Supports streaming via SSE.
- [Check if authentication is enabled](https://docs.getbifrost.ai/api-reference/session/check-if-authentication-is-enabled.md): Returns whether authentication is enabled and if the current token is valid.
- [Issue WebSocket ticket](https://docs.getbifrost.ai/api-reference/session/issue-websocket-ticket.md): Issues a short-lived ticket for authenticating WebSocket connections. The ticket can be used as a query parameter when upgrading to WebSocket.
- [Login](https://docs.getbifrost.ai/api-reference/session/login.md): Authenticates a user and returns a session token. Sets a cookie with the session token for subsequent requests.
- [Logout](https://docs.getbifrost.ai/api-reference/session/logout.md): Logs out the current user and invalidates the session token.
- [Add team member](https://docs.getbifrost.ai/api-reference/teams/add-team-member.md): Adds a user to a team. Both the team and user must exist.
- [Create team](https://docs.getbifrost.ai/api-reference/teams/create-team.md): Creates a new team. The team ID is derived from the name.
- [Delete team](https://docs.getbifrost.ai/api-reference/teams/delete-team.md): Permanently removes a team.
- [Get team](https://docs.getbifrost.ai/api-reference/teams/get-team.md): Returns details of a specific team including member count.
- [List team members](https://docs.getbifrost.ai/api-reference/teams/list-team-members.md): Returns all members of a team with their user details and membership source.
- [List teams](https://docs.getbifrost.ai/api-reference/teams/list-teams.md): Returns a paginated list of teams with optional search.
- [Remove team member](https://docs.getbifrost.ai/api-reference/teams/remove-team-member.md): Removes a user from a team.
- [Update team](https://docs.getbifrost.ai/api-reference/teams/update-team.md): Updates a team. Note that renaming teams is not allowed.
- [Create a text completion](https://docs.getbifrost.ai/api-reference/text-completions/create-a-text-completion.md): Creates a completion for the provided prompt. Supports streaming via SSE.
- [Assign role to user](https://docs.getbifrost.ai/api-reference/users/assign-role-to-user.md): Assigns an RBAC role to a user. This also auto-assigns the default access profile for the new role and reloads the RBAC permission cache.
- [Create user](https://docs.getbifrost.ai/api-reference/users/create-user.md): Manually creates a new user in the organization.
- [Delete user](https://docs.getbifrost.ai/api-reference/users/delete-user.md): Permanently removes a user from the organization. This cascades to delete the user's governance settings (budget/rate limits), team memberships, access profiles, and OIDC sessions. Cannot delete yourself.
- [Get current user permissions](https://docs.getbifrost.ai/api-reference/users/get-current-user-permissions.md): Returns the RBAC permissions for the authenticated user. When SCIM is not enabled, returns full permissions for all resources. Otherwise returns the permissions associated with the user's assigned role.
- [Get user's teams](https://docs.getbifrost.ai/api-reference/users/get-users-teams.md): Returns the list of teams a user belongs to, including the membership source.
- [List users](https://docs.getbifrost.ai/api-reference/users/list-users.md): Returns a paginated list of users with optional search.
- [Update user's team assignments](https://docs.getbifrost.ai/api-reference/users/update-users-team-assignments.md): Replaces the user's manual team assignments. Synced team memberships (from SCIM providers) are preserved and cannot be removed via this endpoint.
- [Delete a video generation job](https://docs.getbifrost.ai/api-reference/videos/delete-a-video-generation-job.md): Deletes a video generation job and its associated assets. This operation cannot be undone.
- [Download video content](https://docs.getbifrost.ai/api-reference/videos/download-video-content.md): Downloads the binary content of a generated video. The video must have a status of "completed" to be downloadable. Returns the raw video file (typically MP4 format).
- [Generate a video](https://docs.getbifrost.ai/api-reference/videos/generate-a-video.md): Creates a video generation job from a text prompt. This is an asynchronous operation that returns immediately with a job ID. Use the retrieve endpoint to check the status and get the video URL when generation is complete.
- [List video generation jobs](https://docs.getbifrost.ai/api-reference/videos/list-video-generation-jobs.md): Lists video generation jobs for a specific provider. Results are paginated and can be filtered using query parameters.
- [Remix a video](https://docs.getbifrost.ai/api-reference/videos/remix-a-video.md): Creates a new video generation job by remixing an existing video with a new prompt. The source video must have a status of "completed" to be remixed. Returns a new video generation job that can be polled for completion.
- [Retrieve a video generation job](https://docs.getbifrost.ai/api-reference/videos/retrieve-a-video-generation-job.md): Retrieves the status and metadata for a video generation job. Use this endpoint to poll for completion status after creating a video generation job. When the status is "completed", the response will include a URL to download the video.
- [Concurrency](https://docs.getbifrost.ai/architecture/core/concurrency.md): Deep dive into Bifrost's advanced concurrency architecture - worker pools, goroutine management, channel-based communication, and resource isolation patterns.
- [Model Context Protocol (MCP)](https://docs.getbifrost.ai/architecture/core/mcp.md): Deep dive into Bifrost's Model Context Protocol (MCP) integration - how external tool discovery, execution, and integration work internally.
- [Plugins](https://docs.getbifrost.ai/architecture/core/plugins.md): Deep dive into Bifrost's extensible plugin architecture - how plugins work internally, lifecycle management, execution model, and integration patterns.
- [Request Flow](https://docs.getbifrost.ai/architecture/core/request-flow.md): Deep dive into Bifrost's request processing pipeline - from transport layer ingestion through provider execution to response delivery.
- [Config Store](https://docs.getbifrost.ai/architecture/framework/config-store.md): A persistent and flexible configuration management system for Bifrost, supporting multiple database backends.
- [Log Store](https://docs.getbifrost.ai/architecture/framework/log-store.md): A robust and queryable system for persisting API request and response logs, with support for multiple database backends.
- [Model Catalog](https://docs.getbifrost.ai/architecture/framework/model-catalog.md): A centralized system for managing model information, pricing, and capabilities across all supported AI providers.
- [Streaming](https://docs.getbifrost.ai/architecture/framework/streaming.md): Framework utility for aggregating and processing real-time stream chunks from AI providers
- [Vector Store](https://docs.getbifrost.ai/architecture/framework/vector-store.md): Vector database implementations for semantic search, embeddings storage, and AI-powered features in Bifrost.
- [What is framework?](https://docs.getbifrost.ai/architecture/framework/what-is-framework.md): Framework is Bifrost's shared storage and utilities SDK package that provides common database interfaces and logic for the plugin ecosystem.
- [Getting Started](https://docs.getbifrost.ai/benchmarking/getting-started.md): Introduction to Bifrost's performance capabilities and how to choose the right instance size for your workload.
- [Run Your Own Benchmarks](https://docs.getbifrost.ai/benchmarking/run-your-own-benchmarks.md): Step-by-step guide to benchmark Bifrost in your own environment using the official benchmarking tool.
- [t3.medium](https://docs.getbifrost.ai/benchmarking/t3.medium.md): Detailed performance metrics and analysis for Bifrost running on AWS t3.medium instances (2 vCPUs, 4GB RAM).
- [t3.xlarge](https://docs.getbifrost.ai/benchmarking/t3.xl.md): Detailed performance metrics and analysis for Bifrost running on AWS t3.xlarge instances (4 vCPUs, 16GB RAM).
- [v0.10.0](https://docs.getbifrost.ai/changelogs/cli-v0.10.0.md): v0.10.0 changelog
- [v0.10.1](https://docs.getbifrost.ai/changelogs/cli-v0.10.1.md): v0.10.1 changelog - 2026-03-13
- [v0.10.2](https://docs.getbifrost.ai/changelogs/cli-v0.10.2.md): v0.10.2 changelog - 2026-03-14
- [v0.10.3](https://docs.getbifrost.ai/changelogs/cli-v0.10.3.md): v0.10.3 changelog - 2026-03-27
- [v1.3.10](https://docs.getbifrost.ai/changelogs/ent-v1.3.10.md): v1.3.10 changelog
- [v1.3.11](https://docs.getbifrost.ai/changelogs/ent-v1.3.11.md): v1.3.11 changelog
- [v1.3.12](https://docs.getbifrost.ai/changelogs/ent-v1.3.12.md): v1.3.12 changelog
- [v1.3.13](https://docs.getbifrost.ai/changelogs/ent-v1.3.13.md): v1.3.13 changelog
- [v1.3.14](https://docs.getbifrost.ai/changelogs/ent-v1.3.14.md): v1.3.14 changelog
- [v1.3.15](https://docs.getbifrost.ai/changelogs/ent-v1.3.15.md): v1.3.15 changelog
- [v1.3.16](https://docs.getbifrost.ai/changelogs/ent-v1.3.16.md): v1.3.16 changelog
- [v1.3.17](https://docs.getbifrost.ai/changelogs/ent-v1.3.17.md): Enterprise v1.3.17 changelog
- [v1.3.8](https://docs.getbifrost.ai/changelogs/ent-v1.3.8.md): v1.3.8 changelog
- [v1.3.9](https://docs.getbifrost.ai/changelogs/ent-v1.3.9.md): v1.3.9 changelog
- [v1.4.0--prerelease1](https://docs.getbifrost.ai/changelogs/ent-v1.4.0-prerelease1.md): Enterprise v1.4.0-prerelease1
- [v1.4.0--prerelease2](https://docs.getbifrost.ai/changelogs/ent-v1.4.0-prerelease2.md): Enterprise v1.4.0-prerelease2
- [v1.2.21](https://docs.getbifrost.ai/changelogs/v1.2.21.md): v1.2.21 changelog
- [v1.2.22](https://docs.getbifrost.ai/changelogs/v1.2.22.md): v1.2.22 changelog
- [v1.2.23](https://docs.getbifrost.ai/changelogs/v1.2.23.md): v1.2.23 changelog
- [v1.2.24](https://docs.getbifrost.ai/changelogs/v1.2.24.md): v1.2.24 changelog
- [v1.3.0](https://docs.getbifrost.ai/changelogs/v1.3.0.md): v1.3.0 changelog
- [v1.3.0-prerelease1](https://docs.getbifrost.ai/changelogs/v1.3.0-prerelease1.md): v1.3.0-prerelease1 changelog
- [v1.3.0-prerelease2](https://docs.getbifrost.ai/changelogs/v1.3.0-prerelease2.md): v1.3.0-prerelease2 changelog
- [v1.3.0-prerelease3](https://docs.getbifrost.ai/changelogs/v1.3.0-prerelease3.md): v1.3.0-prerelease3 changelog
- [v1.3.0-prerelease4](https://docs.getbifrost.ai/changelogs/v1.3.0-prerelease4.md): v1.3.0-prerelease4 changelog
- [v1.3.0-prerelease5](https://docs.getbifrost.ai/changelogs/v1.3.0-prerelease5.md): v1.3.0-prerelease5 changelog
- [v1.3.0-prerelease6](https://docs.getbifrost.ai/changelogs/v1.3.0-prerelease6.md): v1.3.0-prerelease6 changelog
- [v1.3.0-prerelease7](https://docs.getbifrost.ai/changelogs/v1.3.0-prerelease7.md): v1.3.0-prerelease7 changelog
- [v1.3.1](https://docs.getbifrost.ai/changelogs/v1.3.1.md): v1.3.1 changelog
- [v1.3.10](https://docs.getbifrost.ai/changelogs/v1.3.10.md): v1.3.10 changelog
- [v1.3.11](https://docs.getbifrost.ai/changelogs/v1.3.11.md): v1.3.11 changelog
- [v1.3.12](https://docs.getbifrost.ai/changelogs/v1.3.12.md): v1.3.12 changelog
- [v1.3.13](https://docs.getbifrost.ai/changelogs/v1.3.13.md): v1.3.13 changelog
- [v1.3.14](https://docs.getbifrost.ai/changelogs/v1.3.14.md): v1.3.14 changelog
- [v1.3.15](https://docs.getbifrost.ai/changelogs/v1.3.15.md): v1.3.15 changelog
- [v1.3.16](https://docs.getbifrost.ai/changelogs/v1.3.16.md): v1.3.16 changelog
- [v1.3.17](https://docs.getbifrost.ai/changelogs/v1.3.17.md): v1.3.17 changelog
- [v1.3.18](https://docs.getbifrost.ai/changelogs/v1.3.18.md): v1.3.18 changelog
- [v1.3.19](https://docs.getbifrost.ai/changelogs/v1.3.19.md): v1.3.19 changelog
- [v1.3.2](https://docs.getbifrost.ai/changelogs/v1.3.2.md): v1.3.2 changelog
- [v1.3.20](https://docs.getbifrost.ai/changelogs/v1.3.20.md): v1.3.20 changelog
- [v1.3.21](https://docs.getbifrost.ai/changelogs/v1.3.21.md): v1.3.21 changelog
- [v1.3.22](https://docs.getbifrost.ai/changelogs/v1.3.22.md): v1.3.22 changelog - 2025-11-09
- [v1.3.23](https://docs.getbifrost.ai/changelogs/v1.3.23.md): v1.3.23 changelog - 2025-11-10
- [v1.3.24](https://docs.getbifrost.ai/changelogs/v1.3.24.md): v1.3.24 changelog - 2025-11-11
- [v1.3.25](https://docs.getbifrost.ai/changelogs/v1.3.25.md): v1.3.25 changelog - 2025-11-14
- [v1.3.26](https://docs.getbifrost.ai/changelogs/v1.3.26.md): v1.3.26 changelog - 2025-11-16
- [v1.3.27](https://docs.getbifrost.ai/changelogs/v1.3.27.md): v1.3.27 changelog - 2025-11-17
- [v1.3.28](https://docs.getbifrost.ai/changelogs/v1.3.28.md): v1.3.28 changelog - 2025-11-18
- [v1.3.29](https://docs.getbifrost.ai/changelogs/v1.3.29.md): v1.3.29 changelog - 2025-11-18
- [v1.3.3](https://docs.getbifrost.ai/changelogs/v1.3.3.md): v1.3.3 changelog
- [v1.3.30](https://docs.getbifrost.ai/changelogs/v1.3.30.md): v1.3.30 changelog - 2025-11-18
- [v1.3.31](https://docs.getbifrost.ai/changelogs/v1.3.31.md): v1.3.31 changelog - 2025-11-19
- [v1.3.32](https://docs.getbifrost.ai/changelogs/v1.3.32.md): v1.3.32 changelog - 2025-11-20
- [v1.3.33](https://docs.getbifrost.ai/changelogs/v1.3.33.md): v1.3.33 changelog - 2025-11-21
- [v1.3.34](https://docs.getbifrost.ai/changelogs/v1.3.34.md): v1.3.34 changelog - 2025-11-21
- [v1.3.35](https://docs.getbifrost.ai/changelogs/v1.3.35.md): v1.3.35 changelog - 2025-11-24
- [v1.3.36](https://docs.getbifrost.ai/changelogs/v1.3.36.md): v1.3.36 changelog - 2025-11-25
- [v1.3.37](https://docs.getbifrost.ai/changelogs/v1.3.37.md): v1.3.37 changelog - 2025-11-28
- [v1.3.38](https://docs.getbifrost.ai/changelogs/v1.3.38.md): v1.3.38 changelog - 2025-12-01
- [v1.3.39](https://docs.getbifrost.ai/changelogs/v1.3.39.md): v1.3.39 changelog - 2025-12-04
- [v1.3.4](https://docs.getbifrost.ai/changelogs/v1.3.4.md): v1.3.4 changelog
- [v1.3.40](https://docs.getbifrost.ai/changelogs/v1.3.40.md): v1.3.40 changelog - 2025-12-04
- [v1.3.41](https://docs.getbifrost.ai/changelogs/v1.3.41.md): v1.3.41 changelog - 2025-12-05
- [v1.3.42](https://docs.getbifrost.ai/changelogs/v1.3.42.md): v1.3.42 changelog - 2025-12-05
- [v1.3.43](https://docs.getbifrost.ai/changelogs/v1.3.43.md): v1.3.43 changelog - 2025-12-09
- [v1.3.44](https://docs.getbifrost.ai/changelogs/v1.3.44.md): v1.3.44 changelog - 2025-12-10
- [v1.3.45](https://docs.getbifrost.ai/changelogs/v1.3.45.md): v1.3.45 changelog - 2025-12-11
- [v1.3.46](https://docs.getbifrost.ai/changelogs/v1.3.46.md): v1.3.46 changelog - 2025-12-12
- [v1.3.47](https://docs.getbifrost.ai/changelogs/v1.3.47.md): v1.3.47 changelog - 2025-12-12
- [v1.3.48](https://docs.getbifrost.ai/changelogs/v1.3.48.md): v1.3.48 changelog - 2025-12-12
- [v1.3.49](https://docs.getbifrost.ai/changelogs/v1.3.49.md): v1.3.49 changelog - 2025-12-16
- [v1.3.5](https://docs.getbifrost.ai/changelogs/v1.3.5.md): v1.3.5 changelog
- [v1.3.50](https://docs.getbifrost.ai/changelogs/v1.3.50.md): v1.3.50 changelog - 2025-12-17
- [v1.3.51](https://docs.getbifrost.ai/changelogs/v1.3.51.md): v1.3.51 changelog - 2025-12-19
- [v1.3.52](https://docs.getbifrost.ai/changelogs/v1.3.52.md): v1.3.52 changelog - 2025-12-22
- [v1.3.53](https://docs.getbifrost.ai/changelogs/v1.3.53.md): v1.3.53 changelog - 2025-12-23
- [v1.3.54](https://docs.getbifrost.ai/changelogs/v1.3.54.md): v1.3.54 changelog - 2025-12-29
- [v1.3.56](https://docs.getbifrost.ai/changelogs/v1.3.56.md): v1.3.56 changelog - 2026-01-01
- [v1.3.57](https://docs.getbifrost.ai/changelogs/v1.3.57.md): v1.3.57 changelog - 2026-01-01
- [v1.3.58](https://docs.getbifrost.ai/changelogs/v1.3.58.md): v1.3.58 changelog - 2026-01-02
- [v1.3.59](https://docs.getbifrost.ai/changelogs/v1.3.59.md): v1.3.59 changelog - 2026-01-05
- [v1.3.6](https://docs.getbifrost.ai/changelogs/v1.3.6.md): v1.3.6 changelog
- [v1.3.60](https://docs.getbifrost.ai/changelogs/v1.3.60.md): v1.3.60 changelog - 2026-01-07
- [v1.3.61](https://docs.getbifrost.ai/changelogs/v1.3.61.md): v1.3.61 changelog - 2026-01-07
- [v1.3.62](https://docs.getbifrost.ai/changelogs/v1.3.62.md): v1.3.62 changelog - 2026-01-07
- [v1.3.63](https://docs.getbifrost.ai/changelogs/v1.3.63.md): v1.3.63 changelog - 2026-01-07
- [v1.3.7](https://docs.getbifrost.ai/changelogs/v1.3.7.md): v1.3.7 changelog
- [v1.3.8](https://docs.getbifrost.ai/changelogs/v1.3.8.md): v1.3.8 changelog
- [v1.3.9](https://docs.getbifrost.ai/changelogs/v1.3.9.md): v1.3.9 changelog
- [v1.4.0](https://docs.getbifrost.ai/changelogs/v1.4.0.md): v1.4.0 changelog - 2026-01-18
- [v1.4.0-prerelease1](https://docs.getbifrost.ai/changelogs/v1.4.0-prerelease1.md): v1.4.0-prerelease1 changelog - 2025-12-29
- [v1.4.0-prerelease10](https://docs.getbifrost.ai/changelogs/v1.4.0-prerelease10.md): v1.4.0-prerelease10 changelog - 2026-01-15
- [v1.4.0-prerelease2](https://docs.getbifrost.ai/changelogs/v1.4.0-prerelease2.md): v1.4.0-prerelease2 changelog - 2025-12-30
- [v1.4.0-prerelease3](https://docs.getbifrost.ai/changelogs/v1.4.0-prerelease3.md): v1.4.0-prerelease3 changelog - 2026-01-02
- [v1.4.0-prerelease4](https://docs.getbifrost.ai/changelogs/v1.4.0-prerelease4.md): v1.4.0-prerelease4 changelog - 2026-01-05
- [v1.4.0-prerelease5](https://docs.getbifrost.ai/changelogs/v1.4.0-prerelease5.md): v1.4.0-prerelease5 changelog - 2026-01-05
- [v1.4.0-prerelease6](https://docs.getbifrost.ai/changelogs/v1.4.0-prerelease6.md): v1.4.0-prerelease6 changelog - 2026-01-07
- [v1.4.0-prerelease7](https://docs.getbifrost.ai/changelogs/v1.4.0-prerelease7.md): v1.4.0-prerelease7 changelog - 2026-01-08
- [v1.4.0-prerelease8](https://docs.getbifrost.ai/changelogs/v1.4.0-prerelease8.md): v1.4.0-prerelease8 changelog - 2026-01-09
- [v1.4.0-prerelease9](https://docs.getbifrost.ai/changelogs/v1.4.0-prerelease9.md): v1.4.0-prerelease9 changelog - 2026-01-11
- [v1.4.1](https://docs.getbifrost.ai/changelogs/v1.4.1.md): v1.4.1 changelog - 2026-01-19
- [v1.4.10](https://docs.getbifrost.ai/changelogs/v1.4.10.md): v1.4.10 changelog - 2026-03-03
- [v1.4.11](https://docs.getbifrost.ai/changelogs/v1.4.11.md): v1.4.11 changelog - 2026-03-06
- [v1.4.12](https://docs.getbifrost.ai/changelogs/v1.4.12.md): v1.4.12 changelog - 2026-03-15
- [v1.4.13](https://docs.getbifrost.ai/changelogs/v1.4.13.md): v1.4.13 changelog - 2026-03-17
- [v1.4.14](https://docs.getbifrost.ai/changelogs/v1.4.14.md): v1.4.14 changelog - 2026-03-18
- [v1.4.15](https://docs.getbifrost.ai/changelogs/v1.4.15.md): v1.4.15 changelog - 2026-03-23
- [v1.4.16](https://docs.getbifrost.ai/changelogs/v1.4.16.md): v1.4.16 changelog - 2026-03-23
- [v1.4.17](https://docs.getbifrost.ai/changelogs/v1.4.17.md): v1.4.17 changelog - 2026-03-26
- [v1.4.18](https://docs.getbifrost.ai/changelogs/v1.4.18.md): v1.4.18 changelog - 2026-03-29
- [v1.4.19](https://docs.getbifrost.ai/changelogs/v1.4.19.md): v1.4.19 changelog - 2026-03-31
- [v1.4.2](https://docs.getbifrost.ai/changelogs/v1.4.2.md): v1.4.2 changelog - 2026-01-22
- [v1.4.20](https://docs.getbifrost.ai/changelogs/v1.4.20.md): v1.4.20 changelog - 2026-04-06
- [v1.4.21](https://docs.getbifrost.ai/changelogs/v1.4.21.md): v1.4.21 changelog - 2026-04-10
- [v1.4.22](https://docs.getbifrost.ai/changelogs/v1.4.22.md): v1.4.22 changelog - 2026-04-11
- [v1.4.23](https://docs.getbifrost.ai/changelogs/v1.4.23.md): v1.4.23 changelog - 2026-04-18
- [v1.4.3](https://docs.getbifrost.ai/changelogs/v1.4.3.md): v1.4.3 changelog - 2026-01-26
- [v1.4.4](https://docs.getbifrost.ai/changelogs/v1.4.4.md): v1.4.4 changelog - 2026-02-02
- [v1.4.5](https://docs.getbifrost.ai/changelogs/v1.4.5.md): v1.4.5 changelog - 2026-02-10
- [v1.4.6](https://docs.getbifrost.ai/changelogs/v1.4.6.md): v1.4.6 changelog - 2026-02-12
- [v1.4.7](https://docs.getbifrost.ai/changelogs/v1.4.7.md): v1.4.7 changelog - 2026-02-18
- [v1.4.8](https://docs.getbifrost.ai/changelogs/v1.4.8.md): v1.4.8 changelog - 2026-02-25
- [v1.4.9](https://docs.getbifrost.ai/changelogs/v1.4.9.md): v1.4.9 changelog - 2026-02-26
- [v1.5.0-prerelease1](https://docs.getbifrost.ai/changelogs/v1.5.0-prerelease1.md): v1.5.0-prerelease1 changelog - 2026-04-01
- [v1.5.0-prerelease2](https://docs.getbifrost.ai/changelogs/v1.5.0-prerelease2.md): v1.5.0-prerelease2 changelog - 2026-04-08
- [v1.5.0-prerelease3](https://docs.getbifrost.ai/changelogs/v1.5.0-prerelease3.md): v1.5.0-prerelease3 changelog - 2026-04-13
- [v1.5.0-prerelease4](https://docs.getbifrost.ai/changelogs/v1.5.0-prerelease4.md): v1.5.0-prerelease4 changelog - 2026-04-21
- [v1.5.0-prerelease5](https://docs.getbifrost.ai/changelogs/v1.5.0-prerelease5.md): v1.5.0-prerelease5 changelog - 2026-04-21
- [v1.5.0-prerelease6](https://docs.getbifrost.ai/changelogs/v1.5.0-prerelease6.md): v1.5.0-prerelease6 changelog - 2026-04-24
- [Claude Code](https://docs.getbifrost.ai/cli-agents/claude-code.md): Use Claude Code with Bifrost to route through any provider and unlock advanced features like MCP tools and observability.
- [Claude for Office](https://docs.getbifrost.ai/cli-agents/claude-for-office.md): Use Claude for Office (Microsoft 365 add-in) with Bifrost to route requests through any provider with virtual keys, budget controls, and observability.
- [Codex CLI](https://docs.getbifrost.ai/cli-agents/codex-cli.md): Use OpenAI's Codex CLI with Bifrost for powerful code generation with any provider.
- [Cursor](https://docs.getbifrost.ai/cli-agents/cursor.md): Add Bifrost as a custom model in Cursor, configure MCP tools, and use virtual keys for team access control.
- [Gemini CLI](https://docs.getbifrost.ai/cli-agents/gemini-cli.md): Use Google's Gemini CLI with Bifrost for advanced reasoning capabilities with any provider.
- [LibreChat](https://docs.getbifrost.ai/cli-agents/librechat.md): Integrate LibreChat with Bifrost to access any AI provider through a modern open-source chat interface with virtual keys and observability.
- [Open WebUI](https://docs.getbifrost.ai/cli-agents/open-webui.md): Integrate Open WebUI with Bifrost to access any AI provider through a modern open-source chat interface with virtual keys and observability.
- [Opencode](https://docs.getbifrost.ai/cli-agents/opencode.md): Use Opencode with Bifrost to access any AI provider through a terminal-based coding assistant with virtual keys and observability.
- [Overview](https://docs.getbifrost.ai/cli-agents/overview.md): Use Bifrost with LibreChat, Claude Code, Codex CLI, Gemini CLI, Qwen Code, and more by pointing each tool at the correct Bifrost endpoint.
- [Qwen Code](https://docs.getbifrost.ai/cli-agents/qwen-code.md): Use Alibaba's Qwen Code with Bifrost for AI-powered coding with any provider, virtual keys, and observability.
- [Roo Code](https://docs.getbifrost.ai/cli-agents/roo-code.md): Use Roo Code with Bifrost to access any AI provider through a powerful VS Code extension with virtual keys and observability.
- [Zed Editor](https://docs.getbifrost.ai/cli-agents/zed-editor.md): Integrate Zed editor with Bifrost to use any AI provider for code assistance with virtual keys and observability.
- [Adding config store](https://docs.getbifrost.ai/contributing/adding-a-configstore.md): Learn how to contribute a backend for the config store in Bifrost
- [Adding a log store](https://docs.getbifrost.ai/contributing/adding-a-logstore.md): Learn how to contribute a backend for the log store in Bifrost
- [Adding a new provider](https://docs.getbifrost.ai/contributing/adding-a-provider.md): Learn how to contribute a new provider to Bifrost.
- [Adding a vector store](https://docs.getbifrost.ai/contributing/adding-a-vectorstore.md): Learn how to contribute a backend for the vector store in Bifrost
- [Code Conventions](https://docs.getbifrost.ai/contributing/code-conventions.md): Code style and convention guidelines for contributing to Bifrost.
- [Raising a Pull Request](https://docs.getbifrost.ai/contributing/raising-a-pr.md): Guidelines for submitting high-quality pull requests to Bifrost.
- [Setting up the repository](https://docs.getbifrost.ai/contributing/setting-up-repo.md): Complete guide to setting up the Bifrost repository for local development.
- [Quick Start](https://docs.getbifrost.ai/deployment-guides/config-json.md): Configure Bifrost using a config.json file — GitOps-friendly, no-UI deployments, and multinode OSS setups
- [Client Configuration](https://docs.getbifrost.ai/deployment-guides/config-json/client.md): Configure the Bifrost client in config.json — connection pool, logging, CORS, header filtering, compat shims, and MCP settings
- [Cluster](https://docs.getbifrost.ai/deployment-guides/config-json/cluster.md): Configure enterprise cluster mode in config.json using peers or automatic discovery
- [Governance](https://docs.getbifrost.ai/deployment-guides/config-json/governance.md): Seed virtual keys, budgets, rate limits, routing rules, and admin auth in config.json
- [Guardrails](https://docs.getbifrost.ai/deployment-guides/config-json/guardrails.md): Configure content moderation and policy enforcement in config.json using guardrails_config
- [Plugins](https://docs.getbifrost.ai/deployment-guides/config-json/plugins.md): Configure Bifrost plugins in config.json — semantic cache, OpenTelemetry, Maxim, Datadog, and custom plugins
- [Provider Setup](https://docs.getbifrost.ai/deployment-guides/config-json/providers.md): Configure LLM providers in config.json — API keys, cloud-native auth, per-provider network settings, and self-hosted endpoints
- [Schema Reference](https://docs.getbifrost.ai/deployment-guides/config-json/schema-reference.md): All top-level keys available in config.json, their types, and where each is documented
- [Storage](https://docs.getbifrost.ai/deployment-guides/config-json/storage.md): Configure Bifrost storage backends in config.json — config_store, logs_store, vector_store, and object storage for logs
- [Docker Performance Tuning](https://docs.getbifrost.ai/deployment-guides/docker-tuning.md): Optimize Bifrost container performance with Go runtime tuning, resource limits, and system configuration
- [ECS](https://docs.getbifrost.ai/deployment-guides/ecs.md): Deploy Bifrost as a service in ECS AWS clusters
- [AWS Deployment](https://docs.getbifrost.ai/deployment-guides/enterprise/aws.md): Deploy Bifrost Enterprise on AWS using ECR with IRSA or IAM Task Roles
- [Azure Deployment](https://docs.getbifrost.ai/deployment-guides/enterprise/azure.md): Deploy Bifrost Enterprise on Azure AKS using Workload Identity Federation to GCP Artifact Registry
- [GCP Deployment](https://docs.getbifrost.ai/deployment-guides/enterprise/gcp.md): Deploy Bifrost Enterprise on GCP using Artifact Registry with Workload Identity
- [On-Premise Deployment](https://docs.getbifrost.ai/deployment-guides/enterprise/on-premise.md): Deploy Bifrost Enterprise in on-premise or air-gapped environments using Docker credentials
- [Overview](https://docs.getbifrost.ai/deployment-guides/enterprise/overview.md): Deploy Bifrost Enterprise in your cloud environment with secure, private container image distribution
- [fly.io](https://docs.getbifrost.ai/deployment-guides/fly.md): This guide explains how to deploy Bifrost on fly.io
- [Quick Start](https://docs.getbifrost.ai/deployment-guides/helm.md): Deploy Bifrost on Kubernetes using the official Helm chart — quickstart for OSS and Enterprise
- [Client Configuration](https://docs.getbifrost.ai/deployment-guides/helm/client.md): Configure the Bifrost client: connection pool, logging, CORS, header filtering, compat shims, and MCP settings
- [Cluster Mode & HA](https://docs.getbifrost.ai/deployment-guides/helm/cluster.md): Run Bifrost in a multi-replica cluster with gossip-based peer discovery, distributed state sync, and high-availability configuration
- [Governance](https://docs.getbifrost.ai/deployment-guides/helm/governance.md): Configure Bifrost governance in Helm — budgets, rate limits, virtual keys, routing rules, and admin authentication
- [Guardrails](https://docs.getbifrost.ai/deployment-guides/helm/guardrails.md): Configure guardrails providers and rules in Bifrost Helm deployments
- [Plugins](https://docs.getbifrost.ai/deployment-guides/helm/plugins.md): Configure Bifrost plugins in Helm — telemetry, logging, semantic cache, OpenTelemetry, Datadog, governance, and custom plugins
- [Provider Setup](https://docs.getbifrost.ai/deployment-guides/helm/providers.md): Configure LLM providers in the Bifrost Helm chart — API keys, cloud-native auth, and self-hosted endpoints
- [Storage](https://docs.getbifrost.ai/deployment-guides/helm/storage.md): Configure Bifrost storage backends in Helm — SQLite, PostgreSQL (embedded and external), per-store overrides, and S3/GCS object storage for logs
- [Troubleshooting](https://docs.getbifrost.ai/deployment-guides/helm/troubleshooting.md): Diagnose and fix common issues with Bifrost Helm deployments — pods, database, ingress, secrets, PVCs, and performance
- [Values Reference](https://docs.getbifrost.ai/deployment-guides/helm/values.md): Complete reference for Bifrost Helm chart values — key parameters, how to supply them, and links to example files
- [Install make command](https://docs.getbifrost.ai/deployment-guides/how-to/install-make.md): This guide explains how to install make command.
- [Multinode Deployment](https://docs.getbifrost.ai/deployment-guides/how-to/multinode.md): Deploy multiple Bifrost nodes with shared configuration for high availability in OSS deployments
- [Nginx reverse proxy](https://docs.getbifrost.ai/deployment-guides/how-to/nginx-reverse-proxy.md): Run Bifrost behind NGINX with streaming-safe settings for SSE and WebSocket traffic
- [Terraform + k8s](https://docs.getbifrost.ai/deployment-guides/k8s.md): Deploy Bifrost as a service in Kubernetes clusters across AWS, Azure, and GCP using Terraform
- [Adaptive Load Balancing](https://docs.getbifrost.ai/enterprise/adaptive-load-balancing.md): Advanced load balancing algorithms with predictive scaling, health monitoring, and performance optimization for enterprise-grade traffic distribution.
- [Getting started](https://docs.getbifrost.ai/enterprise/advanced-governance.md): Advanced governance features with enhanced security, compliance reporting, audit trails, and enterprise-grade access controls for large-scale deployments.
- [Audit Logs](https://docs.getbifrost.ai/enterprise/audit-logs.md): Comprehensive security and compliance audit logging with detailed tracking of authentication, authorization, configuration changes, and data access for enterprise governance and regulatory requirements.
- [Clustering](https://docs.getbifrost.ai/enterprise/clustering.md): Enterprise-grade high-availability clustering with automatic service discovery, intelligent traffic distribution, and gossip-based state synchronization for production deployments.
- [Custom Plugins](https://docs.getbifrost.ai/enterprise/custom-plugins.md): Build and deploy enterprise-specific plugins to extend Bifrost's functionality with custom business logic, integrations, and workflow automation.
- [Datadog](https://docs.getbifrost.ai/enterprise/datadog-connector.md): Native Datadog integration for APM traces, LLM Observability, and metrics
- [Guardrails](https://docs.getbifrost.ai/enterprise/guardrails.md): Enterprise-grade content safety and security validation with support for AWS Bedrock Guardrails, Azure Content Safety, GraySwan Cygnal, and Patronus AI for real-time input and output protection.
- [In-VPC Deployments](https://docs.getbifrost.ai/enterprise/invpc-deployments.md): Deploy Bifrost within your private cloud infrastructure with VPC isolation, custom networking, and enhanced security controls for enterprise environments.
- [Log Exports](https://docs.getbifrost.ai/enterprise/log-exports.md): Export and analyze request logs, traces, and telemetry data from Bifrost with enterprise-grade data export capabilities for compliance, monitoring, and analytics.
- [MCP with Federated Auth](https://docs.getbifrost.ai/enterprise/mcp-with-fa.md): Transform your existing private enterprise APIs into LLM-ready MCP tools using federated authentication without writing a single line of code
- [Role-Based Access Control](https://docs.getbifrost.ai/enterprise/rbac.md): Manage user access with fine-grained permissions across Bifrost resources using roles and permissions.
- [Setting up Microsoft Entra](https://docs.getbifrost.ai/enterprise/setting-up-entra.md): Step-by-step guide to configure Microsoft Entra ID (Azure AD) as your identity provider for Bifrost Enterprise SSO authentication.
- [Setting up Google Workspace](https://docs.getbifrost.ai/enterprise/setting-up-google-workspace.md): Step-by-step guide to configure Google Workspace as your identity provider for Bifrost Enterprise SSO and Directory-based user provisioning.
- [Setting up Okta](https://docs.getbifrost.ai/enterprise/setting-up-okta.md): Step-by-step guide to configure Okta as your identity provider for Bifrost Enterprise SSO authentication.
- [Setting up Zitadel](https://docs.getbifrost.ai/enterprise/setting-up-zitadel.md): Step-by-step guide to configure Zitadel (cloud or self-hosted) as your identity provider for Bifrost Enterprise SSO and user provisioning.
- [User Provisioning (SCIM)](https://docs.getbifrost.ai/enterprise/user-provisioning.md): Authenticate users, sync teams, and provision roles and business units from your identity provider using SCIM-backed OAuth 2.0 / OIDC flows.
- [Async Inference](https://docs.getbifrost.ai/features/async-inference.md): Submit inference requests asynchronously and poll for results later.
- [Compatibility Plugin](https://docs.getbifrost.ai/features/compat-plugin.md): Request and response transformations for LiteLLM proxy/SDK compatibility.
- [Drop-in Replacement](https://docs.getbifrost.ai/features/drop-in-replacement.md): Replace your existing AI SDK connections with Bifrost by changing just the base URL. Keep your code, gain advanced features like fallbacks, load balancing, and governance.
- [Budget and Limits](https://docs.getbifrost.ai/features/governance/budget-and-limits.md): Enterprise-grade budget management and cost control with hierarchical budget allocation through virtual keys, teams, and customers.
- [MCP Tool Filtering](https://docs.getbifrost.ai/features/governance/mcp-tools.md): Control which MCP tools are available for each Virtual Key.
- [Required Headers](https://docs.getbifrost.ai/features/governance/required-headers.md): Enforce mandatory headers on every request through governance.
- [Routing](https://docs.getbifrost.ai/features/governance/routing.md): Direct requests to specific AI models, providers, and keys using Virtual Keys.
- [Virtual Keys](https://docs.getbifrost.ai/features/governance/virtual-keys.md): Virtual keys are a way to manage access to your AI models.
- [Load Balance](https://docs.getbifrost.ai/features/keys-management.md): Intelligent API key management with weighted load balancing, model-specific filtering, and automatic failover. Distribute traffic across multiple keys for optimal performance and reliability.
- [Built-in Observability](https://docs.getbifrost.ai/features/observability/default.md): Monitor and analyze every AI request and response in real-time. Track performance, debug issues, and gain insights into your AI application's behavior with comprehensive request tracing.
- [Maxim AI](https://docs.getbifrost.ai/features/observability/maxim.md): Integrate Maxim SDK for comprehensive LLM observability, tracing, and evaluation.
- [OpenTelemetry (OTel)](https://docs.getbifrost.ai/features/observability/otel.md): Integrate with OpenTelemetry collectors for enterprise observability and distributed tracing
- [Prometheus](https://docs.getbifrost.ai/features/observability/prometheus.md): Monitor Bifrost metrics with Prometheus scraping or Push Gateway for multi-node deployments
- [JSON Parser](https://docs.getbifrost.ai/features/plugins/jsonparser.md): A simple Bifrost plugin that handles partial JSON chunks in streaming responses by making them valid JSON objects.
- [Mocker](https://docs.getbifrost.ai/features/plugins/mocker.md): Mock AI provider responses for testing, development, and simulation purposes.
- [Playground](https://docs.getbifrost.ai/features/prompt-repository/playground.md): Create, test, and version prompts in an interactive playground.
- [Prompts plugin](https://docs.getbifrost.ai/features/prompt-repository/prompts-plugin.md): Use committed prompt templates from the Prompt Repository on inference requests via HTTP headers or custom resolvers.
- [Retries & Fallbacks](https://docs.getbifrost.ai/features/retries-and-fallbacks.md): Automatic retry with exponential backoff and provider failover. Retries handle transient errors within a provider; fallbacks switch to a different provider when all retries are exhausted.
- [Semantic Caching](https://docs.getbifrost.ai/features/semantic-caching.md): Intelligent response caching based on semantic similarity. Reduce costs and latency by serving cached responses for semantically similar requests.
- [Telemetry](https://docs.getbifrost.ai/features/telemetry.md): Comprehensive Prometheus-based monitoring for Bifrost Gateway with custom metrics and labels.
- [Files and Batch API](https://docs.getbifrost.ai/integrations/anthropic-sdk/files-and-batch.md): Upload files and create batch jobs for asynchronous processing using the Anthropic SDK through Bifrost across multiple providers.
- [Overview](https://docs.getbifrost.ai/integrations/anthropic-sdk/overview.md): Use Bifrost as a drop-in replacement for Anthropic API with full compatibility and enhanced features.
- [Files and Batch API](https://docs.getbifrost.ai/integrations/bedrock-sdk/files-and-batch.md): Manage S3-based files and batch inference jobs using the AWS Bedrock SDK (boto3) through Bifrost across multiple providers.
- [Overview](https://docs.getbifrost.ai/integrations/bedrock-sdk/overview.md): Use Bifrost as a Bedrock-compatible gateway for the Converse and Invoke APIs, with Bifrost features on top.
- [Overview](https://docs.getbifrost.ai/integrations/genai-sdk/overview.md): Use Bifrost as a drop-in replacement for Google GenAI API with full compatibility and enhanced features.
- [AWS Bedrock Guardrails](https://docs.getbifrost.ai/integrations/guardrails/aws-bedrock.md): Integrate AWS Bedrock Guardrails with Bifrost for enterprise-grade content filtering, PII protection, prompt attack detection, and image content analysis.
- [Azure Content Safety](https://docs.getbifrost.ai/integrations/guardrails/azure-content-safety.md): Integrate Azure AI Content Safety with Bifrost for multi-modal content moderation, severity-based filtering, prompt shield, and custom blocklist support.
- [GraySwan Cygnal](https://docs.getbifrost.ai/integrations/guardrails/grayswan.md): Integrate GraySwan Cygnal Monitor with Bifrost for AI safety monitoring with natural language rule definitions, violation scoring, and advanced threat detection.
- [Patronus AI](https://docs.getbifrost.ai/integrations/guardrails/patronus-ai.md): Integrate Patronus AI with Bifrost for LLM security and safety including hallucination detection, PII identification, toxicity screening, and custom evaluators.
- [Langchain SDK](https://docs.getbifrost.ai/integrations/langchain-sdk.md): Use Bifrost as a drop-in proxy for Langchain applications with zero code changes.
- [LiteLLM SDK](https://docs.getbifrost.ai/integrations/litellm-sdk.md): Use Bifrost as a drop-in proxy for LiteLLM applications with zero code changes.
- [Files and Batch API](https://docs.getbifrost.ai/integrations/openai-sdk/files-and-batch.md): Upload files and create batch jobs for asynchronous processing using the OpenAI SDK through Bifrost across multiple providers.
- [Overview](https://docs.getbifrost.ai/integrations/openai-sdk/overview.md): Use Bifrost as a drop-in replacement for OpenAI API with full compatibility and enhanced features.
- [Passthrough](https://docs.getbifrost.ai/integrations/passthrough.md): Forward provider-native requests through Bifrost with full core pipeline processing, including logs and observability.
- [Pydantic AI SDK](https://docs.getbifrost.ai/integrations/pydanticai-sdk.md): Use Bifrost as a drop-in proxy for Pydantic AI agents with zero code changes.
- [Pinecone](https://docs.getbifrost.ai/integrations/vector-databases/pinecone.md): Pinecone vector database integration for semantic caching in Bifrost.
- [Qdrant](https://docs.getbifrost.ai/integrations/vector-databases/qdrant.md): Qdrant vector database integration for semantic caching in Bifrost.
- [Redis / Valkey](https://docs.getbifrost.ai/integrations/vector-databases/redis.md): Redis and Valkey vector store integration for semantic caching in Bifrost.
- [Weaviate](https://docs.getbifrost.ai/integrations/vector-databases/weaviate.md): Weaviate vector database integration for semantic caching in Bifrost.
- [What is an integration?](https://docs.getbifrost.ai/integrations/what-is-an-integration.md): Protocol adapters that translate between Bifrost's unified API and provider-specific API formats like OpenAI, Anthropic, and Google GenAI.
- [Agent Mode (Auto-Execution)](https://docs.getbifrost.ai/mcp/agent-mode.md): Enable autonomous tool execution with configurable auto-approval for building AI agents.
- [Code Mode](https://docs.getbifrost.ai/mcp/code-mode.md): AI writes Python to orchestrate tools. Reduces token usage by 50%+ when using multiple MCP servers.
- [Connecting to MCP Servers](https://docs.getbifrost.ai/mcp/connecting-to-servers.md): Connect Bifrost to external MCP servers via STDIO, HTTP, or SSE protocols.
- [Tool Filtering](https://docs.getbifrost.ai/mcp/filtering.md): Control which MCP tools are available at the client, request, and virtual key levels.
- [MCP Gateway URL](https://docs.getbifrost.ai/mcp/gateway-url.md): Expose Bifrost as an MCP server for Claude Desktop and other MCP clients.
- [OAuth 2.0 Authentication](https://docs.getbifrost.ai/mcp/oauth.md): Configure OAuth 2.0 authentication for MCP HTTP and SSE connections. Support for automatic token refresh, PKCE, and dynamic client registration.
- [Overview](https://docs.getbifrost.ai/mcp/overview.md): Enable AI models to discover and execute external tools dynamically. Transform static chat models into action-capable agents.
- [Per-User OAuth](https://docs.getbifrost.ai/mcp/per-user-oauth.md): Let each end-user authenticate with upstream MCP services under their own credentials. Works with both the MCP Gateway and LLM Gateway.
- [Tool Execution](https://docs.getbifrost.ai/mcp/tool-execution.md): Execute MCP tools with full control over approval and conversation flow.
- [Tool Hosting](https://docs.getbifrost.ai/mcp/tool-hosting.md): Register custom tools directly in your Go application without external MCP servers.
- [Migrating to v1.5.0](https://docs.getbifrost.ai/migration-guides/v1.5.0.md): Breaking changes and migration instructions for the v1.5.0 release
- [Bifrost AI Gateway](https://docs.getbifrost.ai/overview.md): The fastest way to build AI applications that never go down. A high-performance AI gateway unifying 20+ providers through a single OpenAI-compatible API.
- [Building Dynamically Linked Bifrost Binary](https://docs.getbifrost.ai/plugins/building-dynamic-binary.md): Learn how to build a dynamically linked Bifrost binary required for custom plugin support
- [Getting Started](https://docs.getbifrost.ai/plugins/getting-started.md): Learn how to extend Bifrost's functionality by creating custom plugins that intercept and modify requests and responses.
- [Plugin Migration Guide](https://docs.getbifrost.ai/plugins/migration-guide.md): How to migrate your Bifrost plugins from v1.3.x to v1.4.x
- [Plugin Sequencing](https://docs.getbifrost.ai/plugins/sequencing.md): Control the execution order of custom plugins relative to Bifrost's built-in plugins using placement groups and ordering.
- [Writing Go Plugins](https://docs.getbifrost.ai/plugins/writing-go-plugin.md): Step-by-step guide to creating native Go plugins for Bifrost using shared object (.so) files
- [Writing WASM Plugins](https://docs.getbifrost.ai/plugins/writing-wasm-plugin.md): Build cross-platform Bifrost plugins using WebAssembly with TypeScript, Go, or Rust
- [Aliasing Models](https://docs.getbifrost.ai/providers/aliasing-models.md): Map arbitrary model names to any target identifier using static key-level aliases or dynamic routing rules.
- [Custom Pricing](https://docs.getbifrost.ai/providers/custom-pricing.md): Set custom rates for any model across global or virtual key scopes, optionally narrowed to a specific provider or key.
- [Custom Providers](https://docs.getbifrost.ai/providers/custom-providers.md): Create custom provider configurations with specific request type restrictions, custom naming, and controlled access patterns.
- [Performance Tuning](https://docs.getbifrost.ai/providers/performance.md): Optimize Bifrost for high throughput with concurrency, buffer sizing, and memory pool configuration
- [Provider Routing](https://docs.getbifrost.ai/providers/provider-routing.md): Understand how Bifrost routes requests across AI providers using governance rules and adaptive load balancing.
- [Reasoning](https://docs.getbifrost.ai/providers/reasoning.md): Cross-provider reference for reasoning and thinking capabilities in AI models
- [Request Options](https://docs.getbifrost.ai/providers/request-options.md): Complete reference of all request options supported by Bifrost, including HTTP headers for the gateway and context keys for the Go SDK.
- [Routing Rules](https://docs.getbifrost.ai/providers/routing-rules.md): Configure dynamic, expression-based routing decisions using CEL expressions to control how requests are routed across providers.
- [Anthropic](https://docs.getbifrost.ai/providers/supported-providers/anthropic.md): Anthropic API conversion guide - structural differences, message handling, thinking/reasoning, and tool conversion
- [Azure](https://docs.getbifrost.ai/providers/supported-providers/azure.md): Azure OpenAI Service API conversion guide - deployment management, authentication, multi-model support
- [AWS Bedrock](https://docs.getbifrost.ai/providers/supported-providers/bedrock.md): AWS Bedrock API conversion guide - model families, parameter mapping, message handling, reasoning/thinking, tool conversion, and AWS authentication
- [Cerebras](https://docs.getbifrost.ai/providers/supported-providers/cerebras.md): Cerebras API conversion guide - OpenAI-compatible format, full feature support, streaming, tool calling, and parameter handling
- [Cohere](https://docs.getbifrost.ai/providers/supported-providers/cohere.md): Cohere API conversion guide - parameter mapping, message handling, reasoning/thinking, and tool conversion
- [Databricks AI Gateway](https://docs.getbifrost.ai/providers/supported-providers/databricks.md): Route requests through Databricks AI Gateway using Unified (MLflow) or Native (Anthropic Messages) APIs as custom providers in Bifrost
- [ElevenLabs](https://docs.getbifrost.ai/providers/supported-providers/elevenlabs.md): ElevenLabs API conversion guide - text-to-speech, speech-to-text, voice settings, and model management
- [Fireworks](https://docs.getbifrost.ai/providers/supported-providers/fireworks.md): Fireworks API conversion guide covering native chat, responses, completions, embeddings, streaming, and Fireworks-specific parameter handling
- [Google Gemini](https://docs.getbifrost.ai/providers/supported-providers/gemini.md): Google Gemini API conversion guide - request/response transformation, message conversion, tool handling, and streaming behavior
- [Groq](https://docs.getbifrost.ai/providers/supported-providers/groq.md): Groq API conversion guide - OpenAI-compatible format, parameter handling, text completion fallback, streaming, and tool support
- [Hugging Face](https://docs.getbifrost.ai/providers/supported-providers/huggingface.md): Detailed guide on Hugging Face provider implementation specifics, including model aliases and unique request handling.
- [Mistral](https://docs.getbifrost.ai/providers/supported-providers/mistral.md): Mistral API conversion guide - parameter mapping, message handling, tool support, transcription, OCR, and streaming behavior
- [Nebius](https://docs.getbifrost.ai/providers/supported-providers/nebius.md): Nebius API conversion guide - OpenAI-compatible format, parameter handling, streaming, embeddings, and special features
- [Ollama](https://docs.getbifrost.ai/providers/supported-providers/ollama.md): Ollama API conversion guide - local inference, OpenAI-compatible format, streaming, tool calling, and embeddings
- [OpenAI](https://docs.getbifrost.ai/providers/supported-providers/openai.md): OpenAI API conversion guide - what to know when using OpenAI through Bifrost
- [OpenRouter](https://docs.getbifrost.ai/providers/supported-providers/openrouter.md): OpenRouter API conversion guide - routing to multiple providers, reasoning support, parameter handling, and streaming
- [Overview](https://docs.getbifrost.ai/providers/supported-providers/overview.md): Bifrost supports multiple AI providers with consistent OpenAI-compatible response formats, enabling seamless provider switching without code changes.
- [Parasail](https://docs.getbifrost.ai/providers/supported-providers/parasail.md): Parasail API conversion guide - OpenAI-compatible format, streaming support, tool calling, and parameter handling
- [Perplexity](https://docs.getbifrost.ai/providers/supported-providers/perplexity.md): Perplexity API conversion guide - OpenAI-compatible with web search integration, parameter mapping, and reasoning support
- [Replicate](https://docs.getbifrost.ai/providers/supported-providers/replicate.md): Replicate API conversion guide - prediction-based architecture, model-specific parameters, and async/sync modes
- [Runway ML](https://docs.getbifrost.ai/providers/supported-providers/runway.md): Runway ML API conversion guide - text-to-video, image-to-video, and video-to-video generation
- [SGLang](https://docs.getbifrost.ai/providers/supported-providers/sgl.md): SGL/SGLang API conversion guide - OpenAI-compatible format, parameter handling, streaming, tool support
- [Vertex AI](https://docs.getbifrost.ai/providers/supported-providers/vertex.md): Google Vertex AI API conversion guide - multi-model support, OAuth2 authentication, project/region configuration
- [vLLM](https://docs.getbifrost.ai/providers/supported-providers/vllm.md): vLLM API guide - OpenAI-compatible self-hosted inference, chat, text, embeddings, rerank, and streaming
- [xAI](https://docs.getbifrost.ai/providers/supported-providers/xai.md): xAI API conversion guide - OpenAI-compatible format, Grok models, vision support, reasoning, and parameter handling
- [Bifrost CLI](https://docs.getbifrost.ai/quickstart/cli/getting-started.md): Launch any coding agent through Bifrost with a single command. Automatic configuration, model selection, and MCP integration — no environment variables needed.
- [Integrations](https://docs.getbifrost.ai/quickstart/gateway/integrations.md): Use Bifrost as a drop-in replacement for existing AI provider SDKs with zero code changes. Just change the base URL and unlock advanced features.
- [Multimodal Support](https://docs.getbifrost.ai/quickstart/gateway/multimodal.md): Process multiple types of content including images, audio, and text with AI models. Bifrost supports vision analysis, image generation, speech synthesis, and audio transcription across various providers.
- [Provider Configuration](https://docs.getbifrost.ai/quickstart/gateway/provider-configuration.md): Configure multiple AI providers for custom concurrency, queue sizes, proxy settings, and more.
- [Reranking](https://docs.getbifrost.ai/quickstart/gateway/reranking.md): Reorder documents by relevance to a query using /v1/rerank.
- [Setting Up](https://docs.getbifrost.ai/quickstart/gateway/setting-up.md): Get Bifrost running as an HTTP API gateway in 30 seconds with zero configuration. Perfect for any programming language.
- [Setting up auth](https://docs.getbifrost.ai/quickstart/gateway/setting-up-auth.md): Learn how to enable basic authentication for the Bifrost dashboard to secure your admin interface and API endpoints.
- [Streaming Responses](https://docs.getbifrost.ai/quickstart/gateway/streaming.md): Receive AI responses in real-time via Server-Sent Events. Perfect for chat applications, audio processing, and real-time transcription where you want immediate results.
- [Tool Calling](https://docs.getbifrost.ai/quickstart/gateway/tool-calling.md): Enable AI models to use external functions and services by defining tool schemas or connecting to Model Context Protocol (MCP) servers. This allows AI to interact with databases, APIs, file systems, and more.
- [Context Keys](https://docs.getbifrost.ai/quickstart/go-sdk/context-keys.md): Use context keys to configure request behavior, pass metadata, and access response information throughout the request lifecycle.
- [Logging](https://docs.getbifrost.ai/quickstart/go-sdk/logger.md): Configure logging for debugging, monitoring, and troubleshooting your Bifrost integration.
- [Multimodal Support](https://docs.getbifrost.ai/quickstart/go-sdk/multimodal.md): Process multiple types of content including images, audio, and text with AI models. Bifrost supports vision analysis, image generation, speech synthesis, and audio transcription across various providers.
- [Provider Configuration](https://docs.getbifrost.ai/quickstart/go-sdk/provider-configuration.md): Configure multiple AI providers for custom concurrency, queue sizes, proxy settings, and more.
- [Reranking](https://docs.getbifrost.ai/quickstart/go-sdk/reranking.md): Rerank documents with Bifrost Go SDK using client.RerankRequest.
- [Setting Up](https://docs.getbifrost.ai/quickstart/go-sdk/setting-up.md): Get Bifrost running in your Go application in 30 seconds with minimal setup and direct code integration.
- [Streaming Responses](https://docs.getbifrost.ai/quickstart/go-sdk/streaming.md): Receive AI responses in real-time as they're generated. Perfect for chat applications, audio processing, and real-time transcription where you want immediate results.
- [Tool Calling](https://docs.getbifrost.ai/quickstart/go-sdk/tool-calling.md): Enable AI models to use external functions and services by defining tool schemas or connecting to Model Context Protocol (MCP) servers. This allows AI to interact with databases, APIs, file systems, and more.
- [Security at Bifrost](https://docs.getbifrost.ai/security.md): Overview of security practices across Bifrost's CI/CD pipelines, container images, supply chain, and deployment infrastructure.

## OpenAPI Specs

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

## Optional

- [Discord](https://discord.gg/exN5KAydbU)
- [Try Enterprise](https://www.getmaxim.ai/bifrost/enterprise)