Skip to content

Tested Provider List

This page lists AI services and developer tools that Patronus can identify or observe when their traffic passes through an active Patronus protection path.

StatusMeaning
SupportedPatronus can identify the surface and show AI activity for supported request and response flows.
DetectedPatronus can identify the surface as AI-related. The amount of visible detail may depend on the app, transport, or account setup.
Compatible APIPatronus can observe the traffic when the tool uses a supported OpenAI-compatible, Anthropic-compatible, Gemini-compatible, or local model API shape.
Protocol or encodingStatusWhat customers can expect to see
HTTP/1.0 and HTTP/1.1SupportedJSON requests and responses, including content-length and chunked response flows.
HTTP/2SupportedJSON, concurrent HTTP/2 requests, large payloads, streaming JSONL responses, and compressed request or response bodies.
HTTPS through Patronus protectionSupportedProvider traffic is visible when the app or runtime trusts the Patronus CA and does not bypass the active protection path.
Server-Sent EventsSupportedStreaming AI responses from providers such as OpenAI-compatible APIs, Anthropic, Gemini, Mistral, Perplexity, Bedrock, Copilot, and similar event streams.
WebSocketSupportedText frames, UTF-8 JSON binary frames, SignalR-style frames, MessagePack frames, and selected real-time provider streams.
gRPCSupportedUnary and server-streaming protobuf payloads where Patronus can decode the message shape.
JSONSupportedStandard request and response bodies used by most provider APIs.
JSONL / NDJSON / JSON sequenceSupportedToken-style streamed responses and line-delimited generated output.
URL-encoded form bodiesSupportedPrompt fields and single embedded JSON fields used by some browser and provider flows.
Multipart form dataSupportedJSON fields inside multipart requests. Binary file content is not treated as prompt text by default.
ProtobufSupportedStructured protobuf bodies and common AI-specific protobuf-like message shapes.
MessagePackSupportedBinary MessagePack frames used by selected web app and real-time agent surfaces.
AWS EventStreamSupportedBedrock streaming responses, including common Converse and model stream formats.
gzipSupportedCompressed request and response bodies.
BrotliSupportedCompressed request and response bodies.
ZstandardSupportedCompressed request and response bodies.
ProviderStatusWhat customers can expect to see
OpenAI APISupportedChat Completions, Responses API, streaming responses, tool calls, and tool results.
ChatGPTSupportedChatGPT web and Codex-related AI activity when routed through Patronus.
Anthropic / Claude APISupportedMessages API traffic, streaming responses, tool use, and tool results.
Claude WebSupportedClaude-related AI traffic when the app traffic is visible to Patronus.
Google Gemini APISupportedGenerate Content and streaming Gemini API traffic.
Gemini WebSupportedGemini web activity, including streamed response content where available.
Google Vertex AISupportedVertex AI model requests when they use supported Gemini-style request and response shapes.
NotebookLMSupportedNotebookLM generated answer streams when routed through Patronus.
Microsoft CopilotSupportedCopilot web and Microsoft 365 Copilot chat activity where traffic is visible to Patronus.
GitHub CopilotSupportedCopilot API and CLI-style activity, including tool-oriented events where available.
Azure OpenAI / Azure AI FoundrySupportedAzure-hosted OpenAI and Azure AI endpoints.
Amazon BedrockSupportedConverse, streaming Converse, and common Bedrock model response shapes.
MistralSupportedMistral API and Mistral web chat streams.
PerplexitySupportedPerplexity API, web app streams, Sonar search activity, and agent-style search activity.
GroqSupportedGroq OpenAI-compatible chat and Responses traffic, plus Groq web activity where visible.
xAI / GrokSupportedxAI API chat and Responses traffic, plus Grok web activity where visible.
DeepSeekSupportedDeepSeek API and web chat activity.
CohereSupportedCohere chat API traffic for v1 and v2 chat shapes.
OpenRouterDetectedOpenRouter AI API traffic. Visible detail depends on the routed model and API shape.
Hugging Face RouterDetectedOpenAI-compatible chat traffic through the Hugging Face router.
Together AIDetectedOpenAI-compatible chat traffic through Together endpoints.
Fireworks AIDetectedOpenAI-compatible chat and inference endpoints.
CerebrasDetectedOpenAI-compatible chat endpoints.
Cloudflare AI GatewayDetectedAI gateway traffic when routed through Cloudflare’s AI endpoints.
Vercel AI GatewayDetectedOpenAI-compatible traffic through Vercel AI Gateway.
MiniMaxSupportedMiniMax and Anthropic-compatible MiniMax message traffic.
Moonshot / KimiDetectedKimi and Moonshot API traffic, including coding and chat endpoints.
Qwen / DashScopeDetectedQwen and DashScope chat activity.
Zhipu / BigModel / GLMSupportedGLM and BigModel chat activity, including streamed output where available.
DeepLDetectedDeepL AI translation endpoints.
Many moreDetectedPatronus also detects additional AI providers and compatible provider gateways when their traffic uses recognizable AI request, response, or streaming patterns.
SurfaceStatusWhat customers can expect to see
CursorSupportedCursor agent and chat activity, including streamed assistant output where visible.
Windsurf / CodeiumSupportedLocal language-server chat and Windsurf cloud chat activity.
JetBrains AI / JunieSupportedJetBrains AI chat and response streams.
Claude CodeSupportedClaude Code CLI activity when routed through Patronus.
OpenAI Codex CLISupportedCodex CLI activity when routed through Patronus.
Gemini CLISupportedGemini CLI requests, responses, and tool-related activity.
GitHub Copilot CLISupportedCopilot CLI prompts, responses, and tool-oriented events.
ClineCompatible APIActivity is visible when Cline uses a supported provider or compatible API path.
AmpCompatible APIActivity is visible when Amp uses a supported provider or compatible API path.
GooseCompatible APIActivity is visible when Goose uses a supported provider or local model endpoint.
AntigravitySupportedGemini-compatible Antigravity traffic when routed through Patronus.
Qoder / iFlow / OpenCodeCompatible APIOpenAI-compatible or provider-compatible traffic from these tools.
Sentry AI surfacesDetectedAI assistant traffic in supported Sentry chat-style flows.
Notion AISupportedNotion AI request and streamed response activity where traffic is visible.
Microsoft 365 Copilot in Office appsSupportedCopilot chat and AugLoop-style AI activity where traffic is visible to Patronus.
Many moreDetectedPatronus also detects additional AI apps, IDE extensions, and agent tools when their traffic uses recognizable AI request, response, or streaming patterns.
SurfaceStatusWhat customers can expect to see
OpenAI SDKsSupportedChat, Responses, streaming, tool calls, and tool results.
Anthropic SDKsSupportedMessages, streaming, tool use, and tool results.
Google Gen AI SDKsSupportedGemini request and response activity.
LangChainCompatible APIActivity is visible when LangChain uses a supported provider integration.
AutoGenCompatible APIMulti-agent activity is visible when provider calls use supported API shapes.
CrewAICompatible APIAgent activity is visible when provider calls use supported API shapes.
OpenAI Agents SDKSupportedAgent requests, responses, tool calls, and policy-visible activity.
Google ADKSupportedAgent requests, responses, and tool-related activity through supported Gemini paths.
LiteLLMCompatible APITraffic is visible when LiteLLM uses supported provider-compatible request and response shapes.
Vercel AI SDKCompatible APIStreamed responses using Vercel AI SDK formats.
MCP over HTTP or streamable HTTPSupportedMCP messages, tool lists, and tool calls when routed through Patronus.
Many moreCompatible APIPatronus can observe additional SDKs and frameworks when they call supported providers or use compatible API shapes.
SurfaceStatusWhat customers can expect to see
OllamaSupportedLocal chat, generate, streaming responses, and tool calls.
LM StudioSupportedLocal OpenAI-compatible chat and model traffic when routed through Patronus.
OpenAI-compatible local serversCompatible APIRequests and responses that use OpenAI-compatible chat or Responses formats.
Many moreCompatible APIPatronus can observe additional local model runtimes when they expose compatible chat, generate, or Responses-style endpoints.
  • Patronus can only observe traffic that passes through an active Patronus protection path.
  • Some apps encrypt, tunnel, batch, or proxy their own traffic. In those cases Patronus may show the provider or app but less message detail.
  • Local CLIs and containers may require certificate trust configuration before HTTPS traffic is visible.
  • Provider support can vary by app version, account configuration, transport, and model feature.