# Respan Docs

## Instructions for AI Agents

- For clean Markdown of any page, append `.md` to the page URL
- For section-specific indexes, append `/llms.txt` to any section URL
- For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://respan.ai/docs/_mcp/server

## Docs

- [Overview](https://respan.ai/docs/documentation/overview.md): Respan is the AI gateway with built-in observability, evals, and security testing.
- [MCP](https://respan.ai/docs/documentation/mcp.md): Connect your AI tool to Respan logs, traces, prompts, and monitors.
- [CLI](https://respan.ai/docs/documentation/cli.md): Query logs and traces, and manage Respan from your terminal.
- [Respan Agent](https://respan.ai/docs/documentation/agent.md): Ask questions about your LLM traffic, and let the agent set up prompts, monitors, and evaluations for you.
- [Tracing quickstart](https://respan.ai/docs/documentation/features/tracing/quickstart.md): Install the Respan SDK and see your first trace in Logs.
- [Overview](https://respan.ai/docs/integrations/overview.md): Trace your LLM stack with Respan.
- [OpenTelemetry (tracing)](https://respan.ai/docs/integrations/opentelemetry.md): Send traces from any OpenTelemetry-instrumented application to Respan.
- [OpenAI Agents (tracing)](https://respan.ai/docs/integrations/openai-agents-sdk.md): Trace OpenAI Agents SDK workflows with Respan — auto-instrumented spans, gateway routing, and full observability.
- [Claude Agent SDK (tracing)](https://respan.ai/docs/integrations/claude-agents-sdk.md): Trace Claude Agent SDK workflows with Respan using the Claude Agent SDK instrumentation plugin for Python and TypeScript.
- [Vercel AI SDK (tracing)](https://respan.ai/docs/integrations/vercel-ai-sdk.md): Trace Vercel AI SDK calls with Respan — model calls, tool execution, token usage, and workflow context.
- [Pydantic AI (tracing)](https://respan.ai/docs/integrations/pydantic-ai.md): Trace Pydantic AI agent runs with Respan — auto-instrumented spans, gateway routing, and full observability.
- [CrewAI (tracing)](https://respan.ai/docs/integrations/crewai.md): Trace CrewAI workflows with canonical task, agent, tool, and chat spans, including model and token usage.
- [Haystack (tracing)](https://respan.ai/docs/integrations/haystack.md): Trace Haystack pipelines with Respan - auto-instrumented pipeline, component, and LLM spans.
- [LangChain (tracing)](https://respan.ai/docs/integrations/langchain.md): Trace LangChain workflows with Respan — callback spans, gateway routing, and full observability.
- [LangGraph (tracing)](https://respan.ai/docs/integrations/langgraph.md): Trace LangGraph stateful agent workflows with Respan — callback spans, gateway routing, and full observability.
- [Langflow (tracing)](https://respan.ai/docs/integrations/langflow.md): Trace Langflow visual AI workflows with Respan — callback spans, gateway routing, and full observability.
- [Mirascope (tracing)](https://respan.ai/docs/integrations/mirascope.md): Trace Mirascope 2.x model calls, streams, context calls, and toolkit execution with Respan.
- [LlamaIndex (tracing)](https://respan.ai/docs/integrations/llama-index.md): Trace LlamaIndex Core and standalone Workflows with Respan using one native instrumentation package.
- [Temporal (tracing)](https://respan.ai/docs/integrations/temporal.md): Trace Temporal Python workflows, activities, signals, queries, and updates with Respan.
- [AgentOps (tracing)](https://respan.ai/docs/integrations/agentops.md): Export AgentOps Python decorator spans through Respan with AgentOps-native operation details.
- [OpenLIT (tracing)](https://respan.ai/docs/integrations/openlit.md): Send OpenLIT's native OpenTelemetry spans to Respan with canonical chat, embedding, tool, agent, and workflow fields.
- [Apache Burr (tracing)](https://respan.ai/docs/integrations/burr.md): Trace Apache Burr applications, state-machine actions, custom spans, streams, and failures with Respan.
- [Restate (tracing)](https://respan.ai/docs/integrations/restate.md): Trace Restate Python Services, Virtual Objects, Workflows, replay context, and terminal failures with Respan.
- [AutoGen (tracing)](https://respan.ai/docs/integrations/autogen.md): Trace AutoGen AgentChat workflows with Respan — auto-instrumented spans and full observability.
- [DSPy (tracing)](https://respan.ai/docs/integrations/dspy.md): Trace DSPy programs with Respan — native callback instrumentation, optional gateway routing, and full observability.
- [Google ADK (tracing)](https://respan.ai/docs/integrations/google-adk.md): Trace Google ADK agent workflows with Respan.
- [Microsoft Agent Framework (tracing)](https://respan.ai/docs/integrations/microsoft-agent-framework.md): Trace Microsoft Agent Framework agents, tools, chat completions, and workflows with Respan.
- [Semantic Kernel (tracing)](https://respan.ai/docs/integrations/semantic-kernel.md): Trace Microsoft Semantic Kernel functions, chat completions, plugin calls, and failures with Respan.
- [AgentScope (tracing)](https://respan.ai/docs/integrations/agentscope.md): Trace AgentScope agents, model calls, tool executions, streaming output, and failures with Respan.
- [Watson Orchestrate ADK (tracing)](https://respan.ai/docs/integrations/watson-orchestrate-adk.md): Trace IBM watsonx Orchestrate ADK tools, run clients, and chat clients with Respan.
- [Smolagents (tracing)](https://respan.ai/docs/integrations/smolagents.md): Trace Smolagents workflows with Respan — auto-instrumented spans, gateway routing, and full observability.
- [Strands Agents (tracing)](https://respan.ai/docs/integrations/strands-agents.md): Trace Strands Agents workflows with Respan.
- [AgentSpec (tracing)](https://respan.ai/docs/integrations/agent-spec.md): Trace AgentSpec agent workflows with Respan — auto-instrumented spans, gateway routing, and full observability.
- [Guardrails (tracing)](https://respan.ai/docs/integrations/guardrails.md): Trace Guardrails AI validation workflows with Respan — auto-instrumented spans, gateway routing, and full observability.
- [Agno (tracing)](https://respan.ai/docs/integrations/agno.md): Trace Agno agents and teams with Respan using native respan-tracing instrumentation and optional gateway routing.
- [MCP (tracing)](https://respan.ai/docs/integrations/mcp.md): Trace MCP clients and servers with Respan, including tool calls, resources, prompts, and server handlers.
- [BeeAI (tracing)](https://respan.ai/docs/integrations/bee-ai.md): Trace BeeAI agent workflows with Respan — auto-instrumented spans, gateway routing, and full observability.
- [Flue (tracing)](https://respan.ai/docs/integrations/flue.md): Trace Flue TypeScript runtime workflows and agents with Respan including model turns, tools, tasks, shell operations, compaction, and structured logs.
- [Pipecat (tracing)](https://respan.ai/docs/integrations/pipecat.md): Trace Pipecat real-time voice and multimodal AI pipelines with Respan — auto-instrumented spans, gateway routing, and full observability.
- [Mastra (tracing)](https://respan.ai/docs/integrations/mastra.md): Trace Mastra TypeScript agents and workflows with Respan — agent spans, model generations, tool calls, gateway routing, and full observability.
- [Superagent (tracing)](https://respan.ai/docs/integrations/superagent.md): Trace Superagent safety-agent guardrails with Respan — auto-instrumented guardrail and tool spans, workflow context, and gateway routing.
- [BAML (tracing)](https://respan.ai/docs/integrations/baml.md): Trace BAML structured outputs with Respan.
- [Arize (tracing)](https://respan.ai/docs/integrations/arize.md): Trace Arize SDK operations with Respan and capture task-level telemetry in one stream.
- [Dify (tracing)](https://respan.ai/docs/integrations/dify.md): Trace official Dify Service API clients with Respan in Python and JavaScript.
- [LiveKit (tracing)](https://respan.ai/docs/integrations/livekit.md): Trace LiveKit Agents calls with Respan including agent sessions, turns, LLM nodes, function tools, and handoffs.
- [OpenRouter (tracing)](https://respan.ai/docs/integrations/openrouter-tracing.md): Trace OpenRouter calls made through the OpenAI-compatible Python client with Respan.
- [Codex SDK (tracing)](https://respan.ai/docs/integrations/codex-sdk.md): Trace OpenAI Codex SDK turns with Respan including streamed turns, command execution, MCP tool calls, file changes, and structured output.
- [Cursor SDK (tracing)](https://respan.ai/docs/integrations/cursor-sdk.md): Trace Cursor hook events and Cursor TypeScript SDK agent runs with Respan.
- [Pi Coding Agent SDK (tracing)](https://respan.ai/docs/integrations/pi-sdk.md): Trace pi coding-agent SDK sessions with Respan: every agent run, LLM call, tool execution, and compaction from @earendil-works/pi-coding-agent.
- [Eve (tracing)](https://respan.ai/docs/integrations/eve.md): Trace Eve agent turns, AI SDK model calls, tools, and delegated subagents with Respan.
- [OpenAI SDK (tracing)](https://respan.ai/docs/integrations/openai-sdk.md): Trace and observe OpenAI SDK calls with Respan — auto-instrumented spans, gateway routing, and prompt management.
- [Azure OpenAI (tracing)](https://respan.ai/docs/integrations/azure-openai-tracing.md): Trace Azure OpenAI SDK calls with Respan in Python and TypeScript.
- [Instructor (tracing)](https://respan.ai/docs/integrations/instructor.md): Trace Instructor structured-output LLM SDK calls with Respan.
- [Anthropic SDK (tracing)](https://respan.ai/docs/integrations/anthropic.md): Trace Anthropic SDK calls with Respan — auto-instrumented spans, gateway routing, and full observability.
- [Google GenAI (tracing)](https://respan.ai/docs/integrations/google-genai.md): Trace Google GenAI SDK calls with Respan — auto-instrumented spans, gateway routing, and full observability.
- [LiteLLM (tracing)](https://respan.ai/docs/integrations/litellm.md): Trace LiteLLM calls with Respan - native callback instrumentation, gateway routing, and full observability.
- [RubyLLM (tracing)](https://respan.ai/docs/integrations/ruby-llm.md): Use RubyLLM with Respan — gateway routing, model switching, and full observability.
- [Vertex AI (tracing)](https://respan.ai/docs/integrations/vertex-ai.md): Trace Vertex AI SDK calls with Respan.
- [AWS Bedrock (tracing)](https://respan.ai/docs/integrations/aws-bedrock.md): Trace Amazon Bedrock calls with Respan in Python or TypeScript.
- [Cohere (tracing)](https://respan.ai/docs/integrations/cohere.md): Trace Cohere SDK chat, streaming, embeddings, and rerank calls with Respan in Python or TypeScript.
- [Groq (tracing)](https://respan.ai/docs/integrations/groq-tracing.md): Trace Groq Python SDK chat, streaming, and tool calls with Respan.
- [Mistral AI (tracing)](https://respan.ai/docs/integrations/mistral-tracing.md): Trace Mistral AI Python SDK chat, multi-turn, and async calls with Respan.
- [Ollama (tracing)](https://respan.ai/docs/integrations/ollama.md): Trace Ollama Python SDK chat, generation, tool calls, and embeddings with Respan.
- [Portkey (tracing)](https://respan.ai/docs/integrations/portkey.md): Trace Portkey Python SDK chat and async calls with Respan.
- [Watsonx (tracing)](https://respan.ai/docs/integrations/watsonx.md): Trace IBM watsonx.ai SDK calls with Respan.
- [Together AI (tracing)](https://respan.ai/docs/integrations/together-ai.md): Trace Together AI SDK chat, streaming, async, embeddings, rerank, image generation, and tool calls with Respan in Python or TypeScript.
- [Aleph Alpha (tracing)](https://respan.ai/docs/integrations/aleph-alpha.md): Trace official Aleph Alpha Python SDK calls with Respan auto-instrumentation.
- [Hugging Face (tracing)](https://respan.ai/docs/integrations/huggingface.md): Trace Hugging Face Transformers text-generation pipelines with Respan auto-instrumentation.
- [Replicate (tracing)](https://respan.ai/docs/integrations/replicate.md): Trace Replicate model predictions with Respan — auto-instrumented spans and full observability.
- [SageMaker (tracing)](https://respan.ai/docs/integrations/sagemaker.md): Trace Amazon SageMaker endpoint invocations with Respan — auto-instrumented spans and full observability.
- [Writer (tracing)](https://respan.ai/docs/integrations/writer.md): Trace Writer SDK calls with Respan in Python or TypeScript.
- [Respan API (tracing)](https://respan.ai/docs/integrations/respan-api.md): Route LLM calls through the Respan gateway using the API directly — full observability, 1000+ models, prompt management.
- [Claude Code (tracing)](https://respan.ai/docs/integrations/claude-code.md): Trace Claude Code conversations with Respan — hook-based tracing, gateway routing, and full observability.
- [Codex CLI (tracing)](https://respan.ai/docs/integrations/codex-cli.md): Trace Codex CLI conversations with Respan — auto-instrumented spans, gateway routing, and full observability.
- [Gemini CLI (tracing)](https://respan.ai/docs/integrations/gemini-cli.md): Trace Gemini CLI conversations with Respan — auto-instrumented spans, gateway routing, and full observability.
- [OpenCode (tracing)](https://respan.ai/docs/integrations/open-code.md): Trace OpenCode conversations with Respan — auto-instrumented spans, gateway routing, and full observability.
- [Cursor (tracing)](https://respan.ai/docs/integrations/cursor.md): Trace Cursor AI agent conversations with Respan — hook-based tracing and full observability.
- [pi (tracing)](https://respan.ai/docs/integrations/pi.md): Trace interactive pi coding sessions with Respan using the @respan/instrumentation-pi package: turns, model calls, tool executions, and compactions.
- [Chroma (tracing)](https://respan.ai/docs/integrations/chroma.md): Trace Chroma vector operations with Respan — auto-instrumented spans and full observability.
- [Elasticsearch (tracing)](https://respan.ai/docs/integrations/elasticsearch.md): Trace synchronous and asynchronous Elasticsearch operations with Respan, including searches, indexing, bulk requests, responses, and failures.
- [LanceDB (tracing)](https://respan.ai/docs/integrations/lance-db.md): Trace LanceDB vector search operations with Respan — auto-instrumented spans and full observability.
- [Marqo (tracing)](https://respan.ai/docs/integrations/marqo.md): Trace Marqo tensor search operations with Respan — auto-instrumented spans and full observability.
- [Milvus (tracing)](https://respan.ai/docs/integrations/milvus.md): Trace Milvus vector search operations with Respan — auto-instrumented spans and full observability.
- [Pinecone (tracing)](https://respan.ai/docs/integrations/pinecone.md): Trace Pinecone vector search operations with Respan — auto-instrumented spans and full observability.
- [pgvector (tracing)](https://respan.ai/docs/integrations/pgvector.md): Trace pgvector registration, SQL execution, and fetched vector results with Respan.
- [Qdrant (tracing)](https://respan.ai/docs/integrations/qdrant.md): Trace Qdrant collection, point, payload, and vector-query operations with Respan.
- [Weaviate (tracing)](https://respan.ai/docs/integrations/weaviate.md): Trace Weaviate v4 collection, data, query, aggregate, and batch operations with Respan.
- [Pytest (tracing)](https://respan.ai/docs/integrations/pytest.md): Trace Pytest sessions and individual tests with Respan, including outcomes, phases, parametrization, nested application spans, and failures.
- [Ragas (tracing)](https://respan.ai/docs/integrations/ragas.md): Trace Ragas metrics, dataset evaluations, experiments, and experiment rows as canonical Respan task spans.
- [Mem0](https://respan.ai/docs/integrations/mem0.md): Use Mem0 with Respan — gateway routing for memory-backed LLM apps with full observability.
- [Hyperspell](https://respan.ai/docs/integrations/hyperspell.md): Trace Hyperspell memory operations with Respan — full observability over store, retrieve, and context management.
- [Cognee](https://respan.ai/docs/integrations/cognee.md): Trace Cognee semantic memory workflows with Respan — auto-instrumented spans and full observability.
- [Slack](https://respan.ai/docs/integrations/slack.md): Connect a Slack workspace to Respan to send monitor alerts and workflow notifications into Slack channels.
- [Microsoft Teams](https://respan.ai/docs/integrations/microsoft-teams.md): Connect Microsoft Teams to Respan to send monitor alerts and workflow notifications into Teams channels.
- [n8n](https://respan.ai/docs/integrations/n-8-n.md): Trace n8n's native OpenTelemetry spans or call Respan Gateway from an n8n workflow.
- [Exa (tracing)](https://respan.ai/docs/integrations/exa.md): Trace Exa search, contents, grounded answers, streaming, tool helpers, and Agent runs with Respan.
- [Linkup](https://respan.ai/docs/integrations/linkup.md): Use Linkup web search with Respan via the gateway — sourced answers as template variables, full observability.
- [PostHog](https://respan.ai/docs/integrations/posthog.md): Forward Respan LLM events to PostHog via the gateway for product analytics and observability.
- [Moda](https://respan.ai/docs/integrations/moda.md): Forward Respan LLM events to Moda via the gateway for product analytics and observability.
- [AssemblyAI](https://respan.ai/docs/integrations/assemblyai.md): Call and log AssemblyAI speech-to-text models through the Respan gateway with full observability.
- [Zapier](https://respan.ai/docs/integrations/zapier.md): Connect Zapier automations with Respan for LLM monitoring and event-driven workflows.
- [Braintrust](https://respan.ai/docs/integrations/braintrust.md): Trace Braintrust evaluation and logging workflows with Respan.
- [Helicone (tracing)](https://respan.ai/docs/integrations/helicone.md): Trace Helicone Manual Logger calls from Python and TypeScript with canonical Respan spans.
- [Langfuse](https://respan.ai/docs/integrations/langfuse.md): Redirect Langfuse traces to Respan — auto-instrumented spans, gateway routing, and full observability.
- [Metrics](https://respan.ai/docs/documentation/features/monitoring/metrics.md): Watch requests, cost, tokens, latency, and errors over time.
- [Logs](https://respan.ai/docs/documentation/features/observe/explore-spans.md): Search, filter and export every span, trace and thread your app sends to Respan.
- [Signals and errors](https://respan.ai/docs/documentation/features/pulse/errors.md): Spot error spikes above your logs and drill into the spans behind them.
- [Behaviors](https://respan.ai/docs/documentation/features/pulse/behaviors.md): Flag refusals, missed instructions, completed tasks, and your own definitions on every span.
- [Inspect spans and traces](https://respan.ai/docs/documentation/features/observe/view-debug-traces.md): Open a span, trace or thread to find what went wrong, then rerun it.
- [Export](https://respan.ai/docs/documentation/features/observe/export-retention.md): Export logs, traces, and users as CSV or JSONL, once or every 15 minutes.
- [Users](https://respan.ai/docs/documentation/features/customer-identifier.md): See requests, tokens, and cost for each of your end users, and cap their spend.
- [Custom IDs & attributes](https://respan.ai/docs/documentation/features/observe/custom-ids.md): Tag requests with your own record IDs, conversation threads, and custom properties, then group and filter by them.
- [Monitors & notifications](https://respan.ai/docs/documentation/features/monitoring/monitors.md): Get an alert in email, Slack, Microsoft Teams, or a webhook when a metric crosses a threshold.
- [Schedule usage reports](https://respan.ai/docs/documentation/features/monitoring/reports.md): Send a recurring digest of usage, cost, and performance.
- [SQL editor](https://respan.ai/docs/documentation/features/observe/sql-editor.md): Query your spans, traces, and scores with read-only ClickHouse SQL.
- [PII redaction](https://respan.ai/docs/documentation/pii-redaction.md): Mask personal data before it reaches a model provider, and hide it in logs and traces.
- [Run a red team campaign](https://respan.ai/docs/documentation/red-team/run-assessment.md): Attack your agent with adversarial messages and get a graded security report.
- [Review results and troubleshoot](https://respan.ai/docs/documentation/red-team/results.md): Read a campaign's report, work through its findings, and fix runs that stop early.
- [Project settings](https://respan.ai/docs/documentation/admin/projects.md): Create and switch projects, and manage a project's name, ID, and data retention.
- [Members](https://respan.ai/docs/documentation/admin/collaborate.md): Invite teammates to a project and choose what each of them can do.
- [API keys](https://respan.ai/docs/documentation/admin/respan-api-keys.md): Create, scope, limit, and revoke the keys your apps use to call Respan.
- [Provider keys](https://respan.ai/docs/documentation/admin/llm-provider-keys.md): Use your own OpenAI, Anthropic, Azure, or other provider keys with the gateway.
- [Billing and credits](https://respan.ai/docs/documentation/admin/credits-billing.md): Add gateway credits, set up auto reload, and manage your plan and payments.
- [Data webhooks](https://respan.ai/docs/documentation/admin/webhooks.md): Send spans, traces, scores, and billing events to your own endpoint.
- [Get help](https://respan.ai/docs/documentation/support.md): Ask the Respan agent, the community, or the team.
- [Gateway quickstart](https://respan.ai/docs/documentation/features/gateway/gateway-quickstart.md): Send your model calls through Respan by changing one base URL.
- [Overview](https://respan.ai/docs/integrations/gateway/overview.md): Route calls from your agent framework, LLM SDK, or coding agent through the Respan gateway.
- [OpenAI Agents (gateway)](https://respan.ai/docs/integrations/gateway/open-ai-agents.md): Set up OpenAI Agents SDK with the Respan gateway.
- [Claude Agent SDK (gateway)](https://respan.ai/docs/integrations/gateway/claude-agent-sdk.md): Set up Claude Agent SDK with the Respan gateway.
- [Vercel AI SDK (gateway)](https://respan.ai/docs/integrations/gateway/vercel-ai-sdk.md): Set up Vercel AI SDK with the Respan gateway.
- [Pydantic AI (gateway)](https://respan.ai/docs/integrations/gateway/pydantic-ai.md): Set up Pydantic AI with the Respan gateway.
- [CrewAI (gateway)](https://respan.ai/docs/integrations/gateway/crew-ai.md): Set up CrewAI with the Respan gateway.
- [Haystack (gateway)](https://respan.ai/docs/integrations/gateway/haystack.md): Set up Haystack with the Respan gateway.
- [LangChain (gateway)](https://respan.ai/docs/integrations/gateway/lang-chain.md): Set up LangChain with the Respan gateway.
- [LangGraph (gateway)](https://respan.ai/docs/integrations/gateway/lang-graph.md): Set up LangGraph with the Respan gateway.
- [Langflow (gateway)](https://respan.ai/docs/integrations/gateway/langflow.md): Set up Langflow with the Respan gateway.
- [Dify (gateway)](https://respan.ai/docs/integrations/gateway/dify.md): Route Dify LLM calls through the Respan gateway with Dify's official OpenAI-compatible model provider.
- [n8n (gateway)](https://respan.ai/docs/integrations/gateway/n-8-n.md): Call the Respan gateway from an n8n workflow with the built-in HTTP Request node.
- [LlamaIndex (gateway)](https://respan.ai/docs/integrations/gateway/llama-index.md): Set up LlamaIndex with the Respan gateway.
- [AutoGen (gateway)](https://respan.ai/docs/integrations/gateway/auto-gen.md): Set up AutoGen with the Respan gateway.
- [DSPy (gateway)](https://respan.ai/docs/integrations/gateway/ds-py.md): Set up DSPy with the Respan gateway.
- [Google ADK (gateway)](https://respan.ai/docs/integrations/gateway/google-adk.md): Set up Google ADK with the Respan gateway.
- [Microsoft Agent Framework (gateway)](https://respan.ai/docs/integrations/gateway/microsoft-agent-framework.md): Set up Microsoft Agent Framework with the Respan gateway.
- [Semantic Kernel (gateway)](https://respan.ai/docs/integrations/gateway/semantic-kernel.md): Set up Semantic Kernel with the Respan gateway.
- [AgentScope (gateway)](https://respan.ai/docs/integrations/gateway/agent-scope.md): Set up AgentScope with the Respan gateway.
- [Smolagents (gateway)](https://respan.ai/docs/integrations/gateway/smolagents.md): Set up Smolagents with the Respan gateway.
- [Strands Agents (gateway)](https://respan.ai/docs/integrations/gateway/strands-agents.md): Set up Strands Agents with the Respan gateway.
- [AgentSpec (gateway)](https://respan.ai/docs/integrations/gateway/agent-spec.md): Set up AgentSpec with the Respan gateway.
- [Guardrails (gateway)](https://respan.ai/docs/integrations/gateway/guardrails.md): Set up Guardrails AI with the Respan gateway.
- [Agno (gateway)](https://respan.ai/docs/integrations/gateway/agno.md): Set up Agno with the Respan gateway.
- [BeeAI (gateway)](https://respan.ai/docs/integrations/gateway/bee-ai.md): Set up BeeAI with the Respan gateway.
- [Pipecat (gateway)](https://respan.ai/docs/integrations/gateway/pipecat.md): Set up Pipecat with the Respan gateway.
- [Superagent (gateway)](https://respan.ai/docs/integrations/gateway/superagent.md): Set up Superagent with the Respan gateway.
- [OpenRouter (gateway)](https://respan.ai/docs/integrations/gateway/openrouter.md): Route OpenRouter requests through the Respan gateway.
- [Codex SDK (gateway)](https://respan.ai/docs/integrations/gateway/codex-sdk.md): Set up OpenAI Codex SDK with the Respan gateway.
- [Eve (gateway)](https://respan.ai/docs/integrations/gateway/eve.md): Route Eve model calls through the Respan gateway with an AI SDK provider model.
- [OpenAI SDK (gateway)](https://respan.ai/docs/integrations/gateway/open-ai-sdk.md): Set up OpenAI SDK with the Respan gateway.
- [Azure OpenAI (gateway)](https://respan.ai/docs/integrations/gateway/azure-open-ai.md): Route Azure OpenAI code through the Respan gateway by switching to the OpenAI client.
- [Instructor (gateway)](https://respan.ai/docs/integrations/gateway/instructor.md): Set up Instructor with the Respan gateway.
- [Anthropic SDK (gateway)](https://respan.ai/docs/integrations/gateway/anthropic-sdk.md): Set up Anthropic SDK with the Respan gateway.
- [Google GenAI (gateway)](https://respan.ai/docs/integrations/gateway/google-gen-ai.md): Set up Google Gen AI with the Respan gateway.
- [LiteLLM (gateway)](https://respan.ai/docs/integrations/gateway/lite-llm.md): Set up LiteLLM with the Respan gateway.
- [RubyLLM (gateway)](https://respan.ai/docs/integrations/gateway/ruby-llm.md): Set up RubyLLM with the Respan gateway.
- [Vertex AI (gateway)](https://respan.ai/docs/integrations/gateway/vertex-ai.md): Set up Vertex AI through the Respan gateway.
- [AWS Bedrock (gateway)](https://respan.ai/docs/integrations/gateway/aws-bedrock.md): Set up Amazon Bedrock with the Respan gateway.
- [Cohere (gateway)](https://respan.ai/docs/integrations/gateway/cohere.md): Set up Cohere with the Respan gateway.
- [Groq (gateway)](https://respan.ai/docs/integrations/gateway/groq.md): Set up Groq model calls with the Respan gateway.
- [Mistral AI (gateway)](https://respan.ai/docs/integrations/gateway/mistral-ai.md): Set up Mistral AI model calls with the Respan gateway.
- [Ollama (gateway)](https://respan.ai/docs/integrations/gateway/ollama.md): Set up Ollama model calls with the Respan gateway.
- [Portkey (gateway)](https://respan.ai/docs/integrations/gateway/portkey.md): Replace Portkey Gateway routing with the Respan gateway.
- [Helicone (gateway)](https://respan.ai/docs/integrations/gateway/helicone.md): Replace Helicone Gateway routing with the OpenAI-compatible Respan Gateway.
- [Watsonx (gateway)](https://respan.ai/docs/integrations/gateway/watsonx.md): Set up IBM watsonx.ai with the Respan gateway.
- [Together AI (gateway)](https://respan.ai/docs/integrations/gateway/together-ai.md): Set up Together AI model calls with the Respan gateway.
- [Aleph Alpha (gateway)](https://respan.ai/docs/integrations/gateway/aleph-alpha.md): Set up Aleph Alpha with the Respan gateway.
- [Hugging Face (gateway)](https://respan.ai/docs/integrations/gateway/huggingface.md): Set up Hugging Face with the Respan gateway.
- [Replicate (gateway)](https://respan.ai/docs/integrations/gateway/replicate.md): Set up Replicate with the Respan gateway.
- [SageMaker (gateway)](https://respan.ai/docs/integrations/gateway/sage-maker.md): Set up Amazon SageMaker with the Respan gateway.
- [Respan API (gateway)](https://respan.ai/docs/integrations/gateway/respan-api.md): Set up Respan API with the Respan gateway.
- [Claude Code (gateway)](https://respan.ai/docs/integrations/gateway/claude-code.md): Set up Claude Code with the Respan gateway.
- [Codex CLI (gateway)](https://respan.ai/docs/integrations/gateway/codex-cli.md): Set up Codex CLI with the Respan gateway.
- [Gemini CLI (gateway)](https://respan.ai/docs/integrations/gateway/gemini-cli.md): Set up Gemini CLI with the Respan gateway.
- [OpenCode (gateway)](https://respan.ai/docs/integrations/gateway/open-code.md): Set up OpenCode with the Respan gateway.
- [Hermes Agent (gateway)](https://respan.ai/docs/integrations/gateway/hermes-agent.md): Set up Hermes Agent with the Respan gateway.
- [OpenClaw (gateway)](https://respan.ai/docs/integrations/gateway/open-claw.md): Set up OpenClaw with the Respan gateway.
- [Kilo Code (gateway)](https://respan.ai/docs/integrations/gateway/kilo-code.md): Set up Kilo Code with the Respan gateway.
- [Cline (gateway)](https://respan.ai/docs/integrations/gateway/cline.md): Set up Cline with the Respan gateway.
- [Roo Code (gateway)](https://respan.ai/docs/integrations/gateway/roo-code.md): Set up Roo Code with the Respan gateway.
- [Aider (gateway)](https://respan.ai/docs/integrations/gateway/aider.md): Set up Aider with the Respan gateway.
- [pi (gateway)](https://respan.ai/docs/integrations/gateway/pi.md): Set up pi with the Respan gateway.
- [Cursor (gateway)](https://respan.ai/docs/integrations/gateway/cursor.md): Set up Cursor with the Respan gateway.
- [OpenHands (gateway)](https://respan.ai/docs/integrations/gateway/open-hands.md): Set up OpenHands with the Respan gateway.
- [omp (gateway)](https://respan.ai/docs/integrations/gateway/omp.md): Set up omp (oh-my-pi) with the Respan gateway.
- [Qwen Code (gateway)](https://respan.ai/docs/integrations/gateway/qwen-code.md): Set up Qwen Code with the Respan gateway.
- [goose (gateway)](https://respan.ai/docs/integrations/gateway/goose.md): Set up goose with the Respan gateway.
- [Zed (gateway)](https://respan.ai/docs/integrations/gateway/zed.md): Set up the Zed editor's agent with the Respan gateway.
- [DeepSeek Harness (gateway)](https://respan.ai/docs/integrations/gateway/deep-seek-harness.md): Set up DeepSeek Harness (dsh) with the Respan gateway.
- [Quickstart](https://respan.ai/docs/documentation/span-02/quickstart.md): Answer typed questions about a state with one API call.
- [Question types](https://respan.ai/docs/documentation/span-02/question-types.md): Ask for a choice, a yes/no, a score or a number, and read each answer.
- [span-02](https://respan.ai/docs/documentation/span-02/concept.md): span-02 is Respan's decision model. Send a state and typed questions (choice, yes/no, score, number); set a thinking deadline in milliseconds, and span-02 answers by then with its best decision so far.
- [Quickstart](https://respan.ai/docs/documentation/span-01/quickstart.md): Score a conversation for escalation with one API call.
- [span-01](https://respan.ai/docs/documentation/span-01/concept.md): span-01 is Respan's reasoning classifier. It applies plain-language behavior definitions to agent traces and returns present, absent, and not-observable probabilities in a single forward pass.
- [Quickstart](https://respan.ai/docs/documentation/features/gateway/span-router/quickstart.md): Send your first request to span-router.
- [span-router](https://respan.ai/docs/documentation/features/gateway/span-router/concept.md): One model ID that picks the model for each task, with context, capabilities, and cache-aware cost in mind.
- [Provider: OpenAI](https://respan.ai/docs/integrations/gateway/model-providers/openai.md): Call OpenAI models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Anthropic](https://respan.ai/docs/integrations/gateway/model-providers/anthropic.md): Call Anthropic models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Google Gemini](https://respan.ai/docs/integrations/gateway/model-providers/gemini.md): Call Google Gemini models through Respan Gateway with unified logs, cost, and latency.
- [Provider: xAI](https://respan.ai/docs/integrations/gateway/model-providers/xAI.md): Call xAI models through Respan Gateway with unified logs, cost, and latency.
- [Provider: AWS Bedrock](https://respan.ai/docs/integrations/gateway/model-providers/bedrock.md): Call AWS Bedrock models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Google Vertex AI](https://respan.ai/docs/integrations/gateway/model-providers/vertex.md): Call Google Vertex AI models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Azure OpenAI](https://respan.ai/docs/integrations/gateway/model-providers/azure.md): Call Azure OpenAI models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Mistral AI](https://respan.ai/docs/integrations/gateway/model-providers/mistral.md): Call Mistral AI models through Respan Gateway with unified logs, cost, and latency.
- [Provider: DeepSeek](https://respan.ai/docs/integrations/gateway/model-providers/deepseek.md): Call DeepSeek models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Groq](https://respan.ai/docs/integrations/gateway/model-providers/groq.md): Call Groq models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Cohere](https://respan.ai/docs/integrations/gateway/model-providers/cohere.md): Call Cohere models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Perplexity](https://respan.ai/docs/integrations/gateway/model-providers/perplexity.md): Call Perplexity models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Together AI](https://respan.ai/docs/integrations/gateway/model-providers/together.md): Call Together AI models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Fireworks AI](https://respan.ai/docs/integrations/gateway/model-providers/fireworks.md): Call Fireworks AI models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Cerebras](https://respan.ai/docs/integrations/gateway/model-providers/cerebras.md): Call Cerebras models through Respan Gateway with unified logs, cost, and latency.
- [Provider: OpenRouter](https://respan.ai/docs/integrations/gateway/model-providers/openrouter.md): Call OpenRouter models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Replicate](https://respan.ai/docs/integrations/gateway/model-providers/replicate.md): Configure Replicate credentials and check Gateway model availability.
- [Provider: Baseten](https://respan.ai/docs/integrations/gateway/model-providers/baseten.md): Call Baseten models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Moonshot AI](https://respan.ai/docs/integrations/gateway/model-providers/moonshot.md): Call Moonshot AI models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Nebius](https://respan.ai/docs/integrations/gateway/model-providers/nebius.md): Call Nebius models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Novita](https://respan.ai/docs/integrations/gateway/model-providers/novita.md): Call Novita models through Respan Gateway with unified logs, cost, and latency.
- [Provider: FriendliAI](https://respan.ai/docs/integrations/gateway/model-providers/friendli.md): Call FriendliAI models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Parasail](https://respan.ai/docs/integrations/gateway/model-providers/parasail.md): Call Parasail models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Tera](https://respan.ai/docs/integrations/gateway/model-providers/tera.md): Call Tera models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Inference.net](https://respan.ai/docs/integrations/gateway/model-providers/inference.md): Call Inference.net models through Respan Gateway with unified logs, cost, and latency.
- [Provider: AI21 Labs](https://respan.ai/docs/integrations/gateway/model-providers/ai21labs.md): Configure AI21 Labs credentials and check Gateway model availability.
- [Provider: Reducto](https://respan.ai/docs/integrations/gateway/model-providers/reducto.md): Reducto availability and provider billing.
- [Provider: Wafer](https://respan.ai/docs/integrations/gateway/model-providers/wafer.md): Call Wafer models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Nextbit](https://respan.ai/docs/integrations/gateway/model-providers/nextbit.md): Call Nextbit models through Respan Gateway with unified logs, cost, and latency.
- [Provider: TypeSafe](https://respan.ai/docs/integrations/gateway/model-providers/typesafe.md): Call TypeSafe Jev through Respan Gateway with unified logs and latency.
- [Provider: Azure DeepSeek](https://respan.ai/docs/integrations/gateway/model-providers/azure-deepseek.md): Call Azure DeepSeek models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Google PaLM](https://respan.ai/docs/integrations/gateway/model-providers/google-palm.md): Call Google PaLM models through Respan Gateway with unified logs, cost, and latency.
- [Provider: Custom / Self-hosted](https://respan.ai/docs/integrations/gateway/model-providers/custom.md): Call your own self-hosted or custom LLM endpoint through Respan Gateway.
- [Respan params & metadata](https://respan.ai/docs/documentation/features/gateway/respan-params.md): Tag gateway requests with a customer, a thread, and your own properties.
- [Model catalog](https://respan.ai/docs/documentation/features/gateway/models-catalog.md): Find a model, check its price and providers, and add models that aren't listed.
- [Routing & passthrough](https://respan.ai/docs/documentation/features/gateway/routing-and-passthrough.md): Pick an endpoint, and see how Respan chooses the model, provider, and key for each request.
- [Retries and fallback](https://respan.ai/docs/documentation/features/gateway/retries.md): Retry a failed call on the same model, then try other models in order.
- [Load balancing](https://respan.ai/docs/documentation/features/gateway/load-balancing.md): Split traffic across your provider keys, or across models, by weight.
- [Caching](https://respan.ai/docs/documentation/features/gateway/caching.md): Answer repeated requests from a stored response, and track your provider's prompt caching.
- [Limits](https://respan.ai/docs/documentation/features/gateway/limits.md): Cap spend, requests, and tokens per API key, and set budgets and rate limits for your customers.
- [Guardrails](https://respan.ai/docs/documentation/features/gateway/guardrails.md): Block prompt injections, jailbreaks, and unsafe content at the gateway, before they reach your model. Powered by span-01 and free with the Respan gateway.
- [Quickstart](https://respan.ai/docs/documentation/features/prompt-management/prompt-management-quickstart.md): Create a prompt, deploy it, and call it by ID through the gateway.
- [Structured output](https://respan.ai/docs/documentation/features/prompt-management/structured-output.md): Make a prompt return JSON that matches a schema.
- [Tool calling](https://respan.ai/docs/documentation/features/prompt-management/tool-calling.md): Save tools on a prompt and run the tool loop from your code.
- [Prompt composition](https://respan.ai/docs/documentation/features/prompt-management/prompt-composition.md): Reuse one prompt's text inside another through a variable.
- [Advanced configurations](https://respan.ai/docs/documentation/features/prompt-management/advanced.md): How a prompt call merges with your request, which version runs, fallbacks, streaming, and templates.
- [Playground](https://respan.ai/docs/documentation/features/prompt-management/playground.md): Run a prompt on several models or settings side by side.
- [Changelog](https://respan.ai/docs/changelog/changelog/llms.txt)

## API Docs

- API Reference > Gateway [Create a chat completion](https://respan.ai/docs/apis/gateway/create-chat-completion.md)
- API Reference > Gateway [Create a response](https://respan.ai/docs/apis/gateway/create-response.md)
- API Reference > Gateway [Run span-02](https://respan.ai/docs/apis/gateway/run-span-02.md)
- API Reference > Gateway [Run span-01](https://respan.ai/docs/apis/gateway/run-span-01.md)
- API Reference > Gateway > Passthrough [Create an Anthropic message](https://respan.ai/docs/apis/gateway/create-anthropic-message.md)
- API Reference > Gateway > Passthrough [Generate Google model content](https://respan.ai/docs/apis/gateway/generate-google-model-content.md)
- API Reference > Gateway > Passthrough [Create an OpenAI-format chat completion](https://respan.ai/docs/apis/gateway/create-openai-format-chat-completion.md)
- API Reference > Gateway > Passthrough [Create an OpenRouter chat completion](https://respan.ai/docs/apis/gateway/create-openrouter-chat-completion.md)
- API Reference > Gateway > Passthrough [Evaluate state with TypeSafe Jev](https://respan.ai/docs/apis/gateway/evaluate-state-with-typesafe-jev.md)
- API Reference > Gateway > Batches & files [Create a batch](https://respan.ai/docs/apis/gateway/create-batch.md)
- API Reference > Gateway > Batches & files [List batches](https://respan.ai/docs/apis/gateway/list-batches.md)
- API Reference > Gateway > Batches & files [Get a batch](https://respan.ai/docs/apis/gateway/get-batch.md)
- API Reference > Gateway > Batches & files [Cancel a batch](https://respan.ai/docs/apis/gateway/cancel-batch.md)
- API Reference > Gateway > Batches & files [Upload a file](https://respan.ai/docs/apis/gateway/upload-file.md)
- API Reference > Gateway > Batches & files [List files](https://respan.ai/docs/apis/gateway/list-files.md)
- API Reference > Gateway > Batches & files [Get a file](https://respan.ai/docs/apis/gateway/get-file.md)
- API Reference > Gateway > Batches & files [Download file content](https://respan.ai/docs/apis/gateway/download-file-content.md)
- API Reference > Gateway > Batches & files [Delete a file](https://respan.ai/docs/apis/gateway/delete-file.md)
- API Reference > Gateway > Caches [List cached responses](https://respan.ai/docs/apis/caches/list-cached-responses.md)
- API Reference > Gateway > Caches [Get cache summary](https://respan.ai/docs/apis/caches/get-cache-summary.md)
- API Reference > Gateway > Caches [Get a cached response](https://respan.ai/docs/apis/caches/get-cached-response.md)
- API Reference > Gateway > Caches [Update a cached response](https://respan.ai/docs/apis/caches/update-cached-response.md)
- API Reference > Gateway > Caches [Delete a cached response](https://respan.ai/docs/apis/caches/delete-cached-response.md)
- API Reference > Gateway > Caches [Delete cached responses in bulk](https://respan.ai/docs/apis/caches/delete-cached-responses-in-bulk.md)
- API Reference > Models > Models [List models](https://respan.ai/docs/apis/models/list-models.md)
- API Reference > Models > Models [List public models](https://respan.ai/docs/apis/models/list-public-models.md)
- API Reference > Models > Models [Get model summary](https://respan.ai/docs/apis/models/get-model-summary.md)
- API Reference > Models > Models [Get model status](https://respan.ai/docs/apis/models/get-model-status.md)
- API Reference > Models > Models [Get model status with filters](https://respan.ai/docs/apis/models/get-model-status-with-filters.md)
- API Reference > Models > Custom models [Create or update a custom model](https://respan.ai/docs/apis/models/create-or-update-custom-model.md)
- API Reference > Models > Custom models [Get a model](https://respan.ai/docs/apis/models/get-model.md)
- API Reference > Models > Custom models [Update a custom model](https://respan.ai/docs/apis/models/update-custom-model.md)
- API Reference > Models > Custom models [Replace a custom model](https://respan.ai/docs/apis/models/replace-custom-model.md)
- API Reference > Models > Custom models [Delete a custom model](https://respan.ai/docs/apis/models/delete-custom-model.md)
- API Reference > Models > Custom providers [List custom providers](https://respan.ai/docs/apis/models/list-custom-providers.md)
- API Reference > Models > Custom providers [Create a custom provider](https://respan.ai/docs/apis/models/create-custom-provider.md)
- API Reference > Models > Custom providers [Get a custom provider](https://respan.ai/docs/apis/models/get-custom-provider.md)
- API Reference > Models > Custom providers [Update a custom provider](https://respan.ai/docs/apis/models/update-custom-provider.md)
- API Reference > Models > Custom providers [Replace a custom provider](https://respan.ai/docs/apis/models/replace-custom-provider.md)
- API Reference > Models > Custom providers [Delete a custom provider](https://respan.ai/docs/apis/models/delete-custom-provider.md)
- API Reference > Observability > Spans [Create a span](https://respan.ai/docs/apis/spans/create-span.md)
- API Reference > Observability > Spans [Create spans in bulk](https://respan.ai/docs/apis/spans/create-spans-in-bulk.md)
- API Reference > Observability > Spans [List spans](https://respan.ai/docs/apis/spans/list-spans.md)
- API Reference > Observability > Spans [Get a span](https://respan.ai/docs/apis/spans/get-span.md)
- API Reference > Observability > Spans [Get span summary](https://respan.ai/docs/apis/spans/get-span-summary.md)
- API Reference > Observability > Spans [List span groups](https://respan.ai/docs/apis/spans/list-span-groups.md)
- API Reference > Observability > Spans [List span groups with filters](https://respan.ai/docs/apis/spans/list-span-groups-with-filters.md)
- API Reference > Observability > Traces [Ingest traces (OTLP)](https://respan.ai/docs/apis/traces/ingest-traces-otlp.md)
- API Reference > Observability > Traces [Ingest spans (legacy)](https://respan.ai/docs/apis/traces/ingest-spans-legacy.md)
- API Reference > Observability > Traces [List traces](https://respan.ai/docs/apis/traces/list-traces.md)
- API Reference > Observability > Traces [Get a trace](https://respan.ai/docs/apis/traces/get-trace.md)
- API Reference > Observability > Traces [Get a public trace](https://respan.ai/docs/apis/traces/get-public-trace.md)
- API Reference > Observability > Traces [Update trace sharing](https://respan.ai/docs/apis/traces/update-trace-sharing.md)
- API Reference > Observability > Traces [Delete a trace](https://respan.ai/docs/apis/traces/delete-trace.md)
- API Reference > Observability > Traces [Delete traces in bulk](https://respan.ai/docs/apis/traces/delete-traces-in-bulk.md)
- API Reference > Observability > Errors [List error groups](https://respan.ai/docs/apis/errors/list-error-groups.md)
- API Reference > Observability > Errors [Get an error group](https://respan.ai/docs/apis/errors/get-error-group.md)
- API Reference > Observability > Errors [Resolve or ignore an error group](https://respan.ai/docs/apis/errors/resolve-or-ignore-error-group.md)
- API Reference > Observability > Errors [Get error signals over time](https://respan.ai/docs/apis/errors/get-error-signals-over-time.md)
- API Reference > Observability > Errors [Get errors by dimension](https://respan.ai/docs/apis/errors/get-errors-by-dimension.md)
- API Reference > Observability > Errors [List incidents](https://respan.ai/docs/apis/errors/list-incidents.md)
- API Reference > Observability > Errors [Get an incident](https://respan.ai/docs/apis/errors/get-incident.md)
- API Reference > Observability > Errors [Acknowledge an incident](https://respan.ai/docs/apis/errors/acknowledge-incident.md)
- API Reference > Observability > Behaviors [List behaviors](https://respan.ai/docs/apis/behaviors/list-behaviors.md)
- API Reference > Observability > Behaviors [Get behavior summary](https://respan.ai/docs/apis/behaviors/get-behavior-summary.md)
- API Reference > Observability > Behaviors [Get behavior signals over time](https://respan.ai/docs/apis/behaviors/get-behavior-signals-over-time.md)
- API Reference > Observability > Behaviors [Get behavior counts by dimension](https://respan.ai/docs/apis/behaviors/get-behavior-counts-by-dimension.md)
- API Reference > Observability > Behaviors [List spans where a behavior fired](https://respan.ai/docs/apis/behaviors/list-spans-where-behavior-fired.md)
- API Reference > Observability > Behaviors [Override a behavior verdict](https://respan.ai/docs/apis/behaviors/override-behavior-verdict.md)
- API Reference > Observability > Custom behaviors [List custom behaviors](https://respan.ai/docs/apis/behaviors/list-custom-behaviors.md)
- API Reference > Observability > Custom behaviors [Create a custom behavior](https://respan.ai/docs/apis/behaviors/create-custom-behavior.md)
- API Reference > Observability > Custom behaviors [Get a custom behavior](https://respan.ai/docs/apis/behaviors/get-custom-behavior.md)
- API Reference > Observability > Custom behaviors [Update a custom behavior](https://respan.ai/docs/apis/behaviors/update-custom-behavior.md)
- API Reference > Observability > Custom behaviors [Delete a custom behavior](https://respan.ai/docs/apis/behaviors/delete-custom-behavior.md)
- API Reference > Observability > Users [List users](https://respan.ai/docs/apis/users/list-users.md)
- API Reference > Observability > Users [Get a user](https://respan.ai/docs/apis/users/get-user.md)
- API Reference > Observability > Users [Update a user](https://respan.ai/docs/apis/users/update-user.md)
- API Reference > Observability > Users [Delete a user](https://respan.ai/docs/apis/users/delete-user.md)
- API Reference > Observability > Metrics [Get LLM metrics over time](https://respan.ai/docs/apis/metrics/get-llm-metrics-over-time.md)
- API Reference > Observability > Metrics [Get LLM metric summary](https://respan.ai/docs/apis/metrics/get-llm-metric-summary.md)
- API Reference > Observability > Metrics [Get performance quantiles over time](https://respan.ai/docs/apis/metrics/get-performance-quantiles-over-time.md)
- API Reference > Observability > Metrics [Get performance quantile summary](https://respan.ai/docs/apis/metrics/get-performance-quantile-summary.md)
- API Reference > Observability > Metrics [Get metrics by dimension](https://respan.ai/docs/apis/metrics/get-metrics-by-dimension.md)
- API Reference > Observability > Metrics [Get active users over time](https://respan.ai/docs/apis/metrics/get-active-users-over-time.md)
- API Reference > Observability > Metrics [Get total users over time](https://respan.ai/docs/apis/metrics/get-total-users-over-time.md)
- API Reference > Observability > Metrics [Get cache hits over time](https://respan.ai/docs/apis/metrics/get-cache-hits-over-time.md)
- API Reference > Observability > Metrics [Get cache hit summary](https://respan.ai/docs/apis/metrics/get-cache-hit-summary.md)
- API Reference > Observability > Metrics [Get lifetime cache hit totals](https://respan.ai/docs/apis/metrics/get-lifetime-cache-hit-totals.md)
- API Reference > Observability > Metrics [Get storage volume over time](https://respan.ai/docs/apis/metrics/get-storage-volume-over-time.md)
- API Reference > Observability > Metrics [Get storage volume summary](https://respan.ai/docs/apis/metrics/get-storage-volume-summary.md)
- API Reference > Admin > Temporary API keys [Create a temporary API key](https://respan.ai/docs/apis/api-keys/create-temporary-api-key.md)
- API Reference > Admin > Temporary API keys [List temporary API keys](https://respan.ai/docs/apis/api-keys/list-temporary-api-keys.md)
- API Reference > Admin > Temporary API keys [Get a temporary API key](https://respan.ai/docs/apis/api-keys/get-temporary-api-key.md)
- API Reference > Admin > Temporary API keys [Update a temporary API key](https://respan.ai/docs/apis/api-keys/update-temporary-api-key.md)
- API Reference > Admin > Temporary API keys [Revoke a temporary API key](https://respan.ai/docs/apis/api-keys/revoke-temporary-api-key.md)
- API Reference > Admin > Limit policies [Create a limit policy](https://respan.ai/docs/apis/limit-policies/create-limit-policy.md)
- API Reference > Admin > Limit policies [List limit policies](https://respan.ai/docs/apis/limit-policies/list-limit-policies.md)
- API Reference > Admin > Limit policies [Get a limit policy](https://respan.ai/docs/apis/limit-policies/get-limit-policy.md)
- API Reference > Admin > Limit policies [Update a limit policy](https://respan.ai/docs/apis/limit-policies/update-limit-policy.md)
- API Reference > Admin > Limit policies [Delete a limit policy](https://respan.ai/docs/apis/limit-policies/delete-limit-policy.md)
- API Reference > Admin > Credit transactions [List credit transactions](https://respan.ai/docs/apis/credit-transactions/list-credit-transactions.md)
- API Reference > Admin > Credit transactions [Get a credit transaction](https://respan.ai/docs/apis/credit-transactions/get-credit-transaction.md)
- API Reference > Prompts > Prompts [List prompts](https://respan.ai/docs/apis/prompts/list-prompts.md)
- API Reference > Prompts > Prompts [Create a prompt](https://respan.ai/docs/apis/prompts/create-prompt.md)
- API Reference > Prompts > Prompts [Get a prompt](https://respan.ai/docs/apis/prompts/get-prompt.md)
- API Reference > Prompts > Prompts [Update a prompt](https://respan.ai/docs/apis/prompts/update-prompt.md)
- API Reference > Prompts > Prompts [Delete a prompt](https://respan.ai/docs/apis/prompts/delete-prompt.md)
- API Reference > Prompts > Prompts [Update, commit, or deploy prompts in bulk](https://respan.ai/docs/apis/prompts/update-commit-or-deploy-prompts-in-bulk.md)
- API Reference > Prompts > Prompts [Get prompt summary](https://respan.ai/docs/apis/prompts/get-prompt-summary.md)
- API Reference > Prompts > Versions [List prompt versions](https://respan.ai/docs/apis/prompts/list-prompt-versions.md)
- API Reference > Prompts > Versions [Create a prompt version](https://respan.ai/docs/apis/prompts/create-prompt-version.md)
- API Reference > Prompts > Versions [Get a prompt version](https://respan.ai/docs/apis/prompts/get-prompt-version.md)
- API Reference > Prompts > Versions [Update a prompt version](https://respan.ai/docs/apis/prompts/update-prompt-version.md)
- API Reference > Prompts > Versions [Delete a prompt version](https://respan.ai/docs/apis/prompts/delete-prompt-version.md)
- API Reference > Prompts > Versions [Commit a prompt version](https://respan.ai/docs/apis/prompts/commit-prompt-version.md)
- API Reference > Prompts > Versions [Deploy a prompt version](https://respan.ai/docs/apis/prompts/deploy-prompt-version.md)
- API Reference > Prompts > Response format presets [List response format presets](https://respan.ai/docs/apis/prompts/list-response-format-presets.md)
- API Reference > Prompts > Response format presets [Create a response format preset](https://respan.ai/docs/apis/prompts/create-response-format-preset.md)
- API Reference > Prompts > Response format presets [Get a response format preset](https://respan.ai/docs/apis/prompts/get-response-format-preset.md)
- API Reference > Prompts > Response format presets [Update a response format preset](https://respan.ai/docs/apis/prompts/update-response-format-preset.md)
- API Reference > Prompts > Response format presets [Delete a response format preset](https://respan.ai/docs/apis/prompts/delete-response-format-preset.md)

## OpenAPI Specification

The raw OpenAPI 3.1 specification for this API is available at:
- [OpenAPI JSON](https://respan.ai/docs/openapi.json)
- [OpenAPI YAML](https://respan.ai/docs/openapi.yaml)