Integrations

Python SDK

Instrument any Python LLM application with two lines of code.

JS/TS SDK

Trace LLM calls in Node.js and TypeScript applications.

OpenAI SDK

Route OpenAI SDK calls through the Respan gateway for observability and fallbacks.

OpenAI Responses API

Route OpenAI Responses API calls through the Respan gateway for logging.

OpenAI Agents SDK

Trace multi-agent workflows built with the OpenAI Agents SDK.

OpenAI Agents SDK (JS)

Trace OpenAI agent workflows in JavaScript and TypeScript applications.

Vercel AI SDK

Add observability to Vercel AI SDK streaming and tool calls via gateway or tracing.

LangChain

Route LangChain LLM calls through the Respan gateway for observability.

LiteLLM

Route LiteLLM calls through Respan or export logs via callbacks.

LlamaIndex

Route LlamaIndex LLM calls through the Respan gateway for observability.

Google GenAI

Route Google GenAI SDK calls through Respan for Gemini observability.

Anthropic SDK

Route Anthropic SDK calls through the Respan gateway for Claude observability.

Haystack

Route Haystack pipeline LLM calls through Respan with full tracing.

RubyLLM

Access 250+ models from Ruby with the Respan gateway.

Mastra

Trace and monitor Mastra-powered AI agent workflows.

LangGraph

Trace LangGraph workflow executions with hierarchical spans.

BAML

Route BAML function calls through Respan with automatic tracing.

Instructor

Trace Instructor structured LLM outputs with automatic monitoring.

Agno

Trace Agno agent spans with OpenTelemetry and Respan.

Braintrust

Export Braintrust log records and spans to Respan for tracing.

Langfuse

Redirect Langfuse traces to Respan using OTEL instrumentation.

OpenAI

Monitor OpenAI API usage, cost, and performance.

Anthropic

Track Anthropic Claude API calls, cost, and latency.

OpenRouter

Monitor OpenRouter requests across multiple models.

Groq

Track Groq inference calls and ultra-low latency metrics.

Fireworks

Monitor Fireworks AI inference usage and performance.

Together AI

Track Together AI model requests and token usage.

Perplexity

Monitor Perplexity API calls and search-augmented responses.

Azure OpenAI

Track Azure OpenAI Service deployments and usage.

AWS Bedrock

Monitor AWS Bedrock model invocations and costs.

Google Vertex AI

Track Google Vertex AI model calls and performance.

Google Gemini

Monitor Google Gemini API requests and token usage.

Nebius AI

Track Nebius AI inference calls and usage metrics.

Novita AI

Monitor Novita AI model requests and performance.

AI21 Labs

Monitor AI21 Labs model requests and token usage.

AssemblyAI

Monitor AssemblyAI speech-to-text and audio intelligence calls.

Baseten

Monitor Baseten model deployments and inference calls.

Cohere

Track Cohere model requests, embeddings, and reranking calls.

DeepSeek

Monitor DeepSeek model requests and reasoning token usage.

Inference

Monitor Inference API calls and model performance.

Mistral

Track Mistral model requests and performance metrics.

Moonshot

Monitor Moonshot AI model requests and token usage.

Nextbit

Monitor Nextbit model requests and inference metrics.

Parasail

Monitor Parasail inference calls and model performance.

Reducto

Monitor Reducto document processing and extraction calls.

Replicate

Monitor Replicate model predictions and GPU usage.

xAI

Monitor xAI Grok model requests and performance.

Cursor

Trace Cursor AI agent conversations with thinking blocks and tool calls.

Claude Code

Trace Claude Code conversations with thinking blocks, tool calls, and token usage.

Mem0

Add a self-improving memory layer with full observability.

Cognee

Trace knowledge graph and semantic workflow interactions.

Linkup

Add web search to LLM requests with observability.

PostHog

Send LLM metrics to PostHog for product analytics.

Slack

Get LLM alerts and reports delivered to Slack channels.