CONNECT YOUR TOOLS
Your tools. One API key.
Find your tool, follow its setup guide, and verify your first model call. Router One handles the model request; your application stays in charge of its agents and workflows.
Find your integration
Choose what you use, then check its provider settings and model requirements.
59 of 59 integration guides
Coding & agent tools
26- Claude CodeTerminal coding agent · Anthropic Messages setupRead setup guide
- Codex CLITerminal coding agent · Responses and config.tomlRead setup guide
- ClineVS Code, JetBrains and CLI agent · OpenAI Compatible providerRead setup guide
- AiderTerminal pair programmer · openai/ model strings and .aider settings filesRead setup guide
- Roo CodeShut down 2026-05-15 · migrate to Cline, Zoo Code or Kilo CodeRead migration guide
- OpenCodeTerminal agent · opencode.json provider blockRead setup guide
- Kilo CodeVS Code and CLI agent · custom provider and kilo.jsonc limitsRead setup guide
- CursorBring your own key · chat and feature boundariesRead setup guide
- OpenClawSelf-hosted AI assistant · custom provider and spend limitsRead setup guide
- ZedZed Agent · openai_compatible provider in settings.jsonRead setup guide
- ContinueNo longer maintained (final 2.x, 2026-06-19) · config.yaml and alternativesRead setup guide
- GitHub CopilotVS Code Chat · custom endpoint and BYOK scopeRead setup guide
- OpenHandsCoding agent · provider and protocol selectionRead setup guide
- XcodeXcode 26 and 27 chat provider · host-root URL and model listRead setup guide
- Qwen CodeTerminal coding agent · OPENAI_* env and modelProvidersRead setup guide
- GooseDesktop and CLI agent · OPENAI_HOST or custom providerRead setup guide
- Pi AgentTerminal coding agent · models.json and explicit provider selectionRead setup guide
- CrushTerminal coding agent · crushrc openai-compat providerRead setup guide
- JetBrains AI AssistantIDE AI plugin · OpenAI-compatible BYOK provider in Providers & API keysRead setup guide
- TRAEAI IDE · custom model in OpenAI or Anthropic formatRead setup guide
- QoderDesktop app · BYOK custom Base URL, Chat Completions or ResponsesRead setup guide
- CodeBuddyCLI and IDE · models.json custom modelsRead setup guide
- Hermes AgentTerminal agent · custom endpoint or named provider in config.yamlRead setup guide
- GitHub Copilot CLITerminal agent · BYOK through COPILOT_PROVIDER_* environment variablesRead setup guide
- DeepSeek HarnessAgent harness Web UI · Custom model API provider per protocolRead setup guide
- WorkBuddyOffice AI agent · custom model with the full /chat/completions URLRead setup guide
SDKs & frameworks
17- LangChainChatOpenAI or ChatAnthropic · Python and JSRead setup guide
- LlamaIndexOpenAILike · chat model and context settingsRead setup guide
- Vercel AI SDKTypeScript · .chat(), OpenAI-compatible or Anthropic providerRead setup guide
- OpenAI SDKPython, Node, Go and Java · Chat Completions for every chat modelRead setup guide
- Pydantic AIPython agents · OpenAIChatModel and provider setupRead setup guide
- CrewAIPython agents · custom OpenAI-compatible LLMRead setup guide
- Spring AIJava · version-specific base URL configurationRead setup guide
- OpenAI Agents SDKPython agents · explicit Chat Completions modelRead setup guide
- Claude Agent SDKClaude Code runtime · environment and model setupRead setup guide
- HaystackPython pipelines · chat generator and RAG boundariesRead setup guide
- Google ADKPython agents · LiteLlm model with api_baseRead setup guide
- smolagentsHugging Face agents · OpenAIModel with api_baseRead setup guide
- MastraTypeScript agents · model object with url and apiKeyRead setup guide
- DSPyPython LM programs · dspy.LM with openai/ prefix and api_baseRead setup guide
- Microsoft Agent FrameworkPython and .NET agents · OpenAIChatCompletionClient with base_urlRead setup guide
- AgnoPython agent framework · OpenAILike and an explicit model IDRead setup guide
- AutoGenPython multi-agent framework · OpenAIChatCompletionClient with base_url and model_infoRead setup guide
Chat, RAG & translation
08- Cherry StudioDesktop chat · custom provider with OpenAI, Anthropic and Responses endpointsRead setup guide
- ChatboxDesktop and mobile chat · API mode and API hostRead setup guide
- Open WebUISelf-hosted chat · OpenAI API connection and model allowlistRead setup guide
- LibreChatSelf-hosted chat · librechat.yaml custom endpointRead setup guide
- Immersive TranslateBrowser translation · custom API endpoint and model IDsRead setup guide
- NextChatChat client · host-root BASE_URL configurationRead setup guide
- AnythingLLMKnowledge-base chat · Generic OpenAI configurationRead setup guide
- Copilot for ObsidianObsidian note assistant · BYOK custom providerRead setup guide
Workflows & API tools
08- DifyApps and workflows · OpenAI-API-compatible pluginRead setup guide
- n8nWorkflow nodes · OpenAI credentials and API checksRead setup guide
- FastGPTAI Proxy channel · model IDs and workflow callsRead setup guide
- FlowiseLow-code LLM flows · OpenAI Custom Model node and Base PathRead setup guide
- LangflowVisual flow and agent builder · OpenAI Compatible model providerRead setup guide
- RAGFlowSelf-hosted RAG engine · OpenAI-API-Compatible provider instanceRead setup guide
- MaxKBKnowledge-base applications · OpenAI provider and custom base modelRead setup guide
- one-api / new-apiAPI relay stations · OpenAI upstream channel setupRead setup guide
Before your first request
Match the URL to your client
A base URL and a full request endpoint are different. Check the client's field and selected protocol before copying an address.
Check connection settingsUse an exact model ID
Copy an ID from the model catalog. Match its supported endpoints and capabilities to the features your client needs.
Browse models and capabilitiesVerify the finished request
Start with plain text. Check the result, request ID, and settlement in Logs before enabling streaming or tools.
Read the request log guide
Which URL should I enter?
OpenAI-compatible SDKs and Codex use the /v1 base URL; Claude Code uses the host root; for Immersive Translate, enter the full /v1/chat/completions URL, which works in every version. Check the configured protocol and model support.
Compare client URL settings
| Client / setting | Value to enter | API used |
|---|---|---|
SDK Chat Completions setupbase_url / baseURL / apiBase | https://api.router.one/ | Chat CompletionsPOST /v1/ |
Codex CLIbase_url; wire_api = "responses" | https://api.router.one/ | ResponsesPOST /v1/ |
Claude CodeANTHROPIC_BASE_URL | https://api.router.one | Anthropic MessagesPOST /v1/ |
Immersive TranslateCustom API endpoint (the full URL works in every version; 1.30.2 and later also accept /v1) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
GitHub Copilot (VS Code)chatLanguageModels.json → models[].url; apiType: "chat-completions" | https://api.router.one/ | Chat CompletionsPOST /v1/ |
OpenHandsBase URL (Advanced) / LLM_BASE_URL (GPT-5-family IDs use /v1/responses; see the guide) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
NextChatBASE_URL / OpenAI Endpoint | https://api.router.one | Chat CompletionsPOST /v1/ |
CrewAIbase_url; custom_openai=True (or OPENAI_API_BASE) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
Spring AIspring.ai.openai.base-url (2.0.x; 1.x uses the host root) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
OpenAI Agents SDKAsyncOpenAI(base_url=…) + OpenAIChatCompletionsModel (string model names default to /v1/responses) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
Claude Agent SDKClaudeAgentOptions(env={ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN}) | https://api.router.one | Anthropic MessagesPOST /v1/ |
HaystackOpenAIChatGenerator(api_base_url=…) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
AnythingLLMSettings → AI Providers → LLM → Base URL / GENERIC_OPEN_AI_BASE_PATH | https://api.router.one/ | Chat CompletionsPOST /v1/ |
FastGPTAI Proxy channel → Base url (Protocol Type: OpenAI) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
XcodeSettings → Intelligence → Add a Chat Provider → Internet Hosted → URL (Xcode appends /v1/models and /v1/chat/completions) | https://api.router.one | Chat CompletionsPOST /v1/ |
Qwen CodeOPENAI_BASE_URL (.qwen/.env) / modelProviders.openai[].baseUrl | https://api.router.one/ | Chat CompletionsPOST /v1/ |
Google ADKLiteLlm(model="openai/<id>", api_base=…, api_key=…) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
smolagentsOpenAIModel(model_id=…, api_base=…, api_key=…) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
GooseOPENAI_HOST (OPENAI_BASE_PATH keeps its default v1/chat/completions; gpt-5, gpt-6 and o-series names go to /v1/responses, see the guide) | https://api.router.one | Chat CompletionsPOST /v1/ |
MastraAgent model: { id: "custom/<model-id>", url: …, apiKey: … } | https://api.router.one/ | Chat CompletionsPOST /v1/ |
DSPydspy.LM("openai/<model-id>", api_base=…, api_key=…) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
Microsoft Agent FrameworkOpenAIChatCompletionClient(model=…, api_key=…, base_url=…) / .NET OpenAIClientOptions.Endpoint | https://api.router.one/ | Chat CompletionsPOST /v1/ |
FlowiseOpenAI Custom Model node → Additional Parameters → Base Path | https://api.router.one/ | Chat CompletionsPOST /v1/ |
LangflowSettings → Model Providers → OpenAI Compatible → Base URL (OPENAI_COMPATIBLE_BASE_URL) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
RAGFlowModel providers → OpenAI-API-Compatible → Base URL | https://api.router.one/ | Chat CompletionsPOST /v1/ |
AgnoOpenAILike(id=…, base_url=…, api_key=…) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
MaxKBOpenAI provider → API URL | https://api.router.one/ | Chat CompletionsPOST /v1/ |
Pi Agentmodels.json → providers.router-one.baseUrl (api: openai-completions) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
AutoGenOpenAIChatCompletionClient(model=…, base_url=…, api_key=…, model_info={…}) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
Crushcrushrc → provider add router-one --type openai-compat --base-url (legacy crush.json: base_url) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
JetBrains AI AssistantProviders & API keys → Third-party AI providers → OpenAI-compatible → URL | https://api.router.one/ | Chat CompletionsPOST /v1/ |
Copilot for ObsidianSettings → Copilot → BYOK → Add a custom provider → Base URL | https://api.router.one/ | Chat CompletionsPOST /v1/ |
AiderOPENAI_API_BASE (or --openai-api-base); --model openai/<exact catalog ID> | https://api.router.one/ | Chat CompletionsPOST /v1/ |
ClineAPI Provider: OpenAI Compatible → Base URL (CLI: cline auth --baseurl) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
Zedlanguage_models.openai_compatible.<id>.api_url | https://api.router.one/ | Chat CompletionsPOST /v1/ |
Zed (anthropic_compatible, optional)language_models.anthropic_compatible.<id>.api_url | https://api.router.one | Anthropic MessagesPOST /v1/ |
DifyOpenAI-API-compatible plugin → API Base URL (API endpoint URL in plugin 0.0.53 and earlier) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
Open WebUIAdmin Panel → Settings → Connections → URL (or OPENAI_API_BASE_URL on the first launch) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
OpenClawopenclaw onboard --custom-base-url (--custom-compatibility openai or openai-responses; anthropic takes the host root) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
TRAE (TraeCode)Settings > Models > Add Model > Custom Model → Custom Request URL (OpenAI Chat Completions, Full URL off; Claude and DeepSeek V4 IDs can also use Anthropic Messages with the host root, see the guide) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
QoderSettings → Models → + Add → Provider → Custom → OpenAI Compatible → Base URL (Chat Completions API; Responses API for GPT, DeepSeek V4 and Grok chat IDs) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
CodeBuddymodels.json → models[].url (full request path; OpenAI format only) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
Hermes Agenthermes model → Custom endpoint → API base URL (or providers.<name>.api in config.yaml; transport chat_completions) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
GitHub Copilot CLICOPILOT_PROVIDER_BASE_URL (COPILOT_PROVIDER_TYPE=openai, COPILOT_PROVIDER_WIRE_API=completions) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
Cherry StudioSettings → Model Provider → Add Provider → Endpoint settings → OpenAI (Cherry appends /v1/chat/completions; Anthropic and OpenAI Responses take the same host root) | https://api.router.one | Chat CompletionsPOST /v1/ |
ChatboxSettings → Model Provider → Add → Add Custom Provider → OpenAI API Compatible → API Host (Claude API Compatible mode also needs /v1) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
DeepSeek HarnessSettings → Models → Add model provider → Custom model API → Base URL (API protocol OpenAI Chat Completions; OpenAI Responses also takes /v1, Anthropic Messages the host root) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
WorkBuddySettings → Model → add a model → Provider: Custom → URL (the full /chat/completions path, Custom Protocol off; OpenAI-compatible APIs only) | https://api.router.one/ | Chat CompletionsPOST /v1/ |
- SDK Chat Completions setup
base_url / baseURL / apiBase- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Codex CLI
base_url; wire_api = "responses"- Value to enter
https://api.router.one/v1 - API used
- Responses
POST /v1/responses
- Claude Code
ANTHROPIC_BASE_URL- Value to enter
https://api.router.one- API used
- Anthropic Messages
POST /v1/messages
- Immersive Translate
Custom API endpoint (the full URL works in every version; 1.30.2 and later also accept /v1)- Value to enter
https://api.router.one/v1/ chat/ completions - API used
- Chat Completions
POST /v1/chat/ completions
- GitHub Copilot (VS Code)
chatLanguageModels.json → models[].url; apiType: "chat-completions"- Value to enter
https://api.router.one/v1/ chat/ completions - API used
- Chat Completions
POST /v1/chat/ completions
- OpenHands
Base URL (Advanced) / LLM_BASE_URL (GPT-5-family IDs use /v1/responses; see the guide)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- NextChat
BASE_URL / OpenAI Endpoint- Value to enter
https://api.router.one- API used
- Chat Completions
POST /v1/chat/ completions
- CrewAI
base_url; custom_openai=True (or OPENAI_API_BASE)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Spring AI
spring.ai.openai.base-url (2.0.x; 1.x uses the host root)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- OpenAI Agents SDK
AsyncOpenAI(base_url=…) + OpenAIChatCompletionsModel (string model names default to /v1/responses)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Claude Agent SDK
ClaudeAgentOptions(env={ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN})- Value to enter
https://api.router.one- API used
- Anthropic Messages
POST /v1/messages
- Haystack
OpenAIChatGenerator(api_base_url=…)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- AnythingLLM
Settings → AI Providers → LLM → Base URL / GENERIC_OPEN_AI_BASE_PATH- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- FastGPT
AI Proxy channel → Base url (Protocol Type: OpenAI)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Xcode
Settings → Intelligence → Add a Chat Provider → Internet Hosted → URL (Xcode appends /v1/models and /v1/chat/completions)- Value to enter
https://api.router.one- API used
- Chat Completions
POST /v1/chat/ completions
- Qwen Code
OPENAI_BASE_URL (.qwen/.env) / modelProviders.openai[].baseUrl- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Google ADK
LiteLlm(model="openai/<id>", api_base=…, api_key=…)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- smolagents
OpenAIModel(model_id=…, api_base=…, api_key=…)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Goose
OPENAI_HOST (OPENAI_BASE_PATH keeps its default v1/chat/completions; gpt-5, gpt-6 and o-series names go to /v1/responses, see the guide)- Value to enter
https://api.router.one- API used
- Chat Completions
POST /v1/chat/ completions
- Mastra
Agent model: { id: "custom/<model-id>", url: …, apiKey: … }- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- DSPy
dspy.LM("openai/<model-id>", api_base=…, api_key=…)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Microsoft Agent Framework
OpenAIChatCompletionClient(model=…, api_key=…, base_url=…) / .NET OpenAIClientOptions.Endpoint- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Flowise
OpenAI Custom Model node → Additional Parameters → Base Path- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Langflow
Settings → Model Providers → OpenAI Compatible → Base URL (OPENAI_COMPATIBLE_BASE_URL)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- RAGFlow
Model providers → OpenAI-API-Compatible → Base URL- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Agno
OpenAILike(id=…, base_url=…, api_key=…)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- MaxKB
OpenAI provider → API URL- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Pi Agent
models.json → providers.router-one.baseUrl (api: openai-completions)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- AutoGen
OpenAIChatCompletionClient(model=…, base_url=…, api_key=…, model_info={…})- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Crush
crushrc → provider add router-one --type openai-compat --base-url (legacy crush.json: base_url)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- JetBrains AI Assistant
Providers & API keys → Third-party AI providers → OpenAI-compatible → URL- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Copilot for Obsidian
Settings → Copilot → BYOK → Add a custom provider → Base URL- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Aider
OPENAI_API_BASE (or --openai-api-base); --model openai/<exact catalog ID>- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Cline
API Provider: OpenAI Compatible → Base URL (CLI: cline auth --baseurl)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Zed
language_models.openai_compatible.<id>.api_url- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Zed (anthropic_compatible, optional)
language_models.anthropic_compatible.<id>.api_url- Value to enter
https://api.router.one- API used
- Anthropic Messages
POST /v1/messages
- Dify
OpenAI-API-compatible plugin → API Base URL (API endpoint URL in plugin 0.0.53 and earlier)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Open WebUI
Admin Panel → Settings → Connections → URL (or OPENAI_API_BASE_URL on the first launch)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- OpenClaw
openclaw onboard --custom-base-url (--custom-compatibility openai or openai-responses; anthropic takes the host root)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- TRAE (TraeCode)
Settings > Models > Add Model > Custom Model → Custom Request URL (OpenAI Chat Completions, Full URL off; Claude and DeepSeek V4 IDs can also use Anthropic Messages with the host root, see the guide)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Qoder
Settings → Models → + Add → Provider → Custom → OpenAI Compatible → Base URL (Chat Completions API; Responses API for GPT, DeepSeek V4 and Grok chat IDs)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- CodeBuddy
models.json → models[].url (full request path; OpenAI format only)- Value to enter
https://api.router.one/v1/ chat/ completions - API used
- Chat Completions
POST /v1/chat/ completions
- Hermes Agent
hermes model → Custom endpoint → API base URL (or providers.<name>.api in config.yaml; transport chat_completions)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- GitHub Copilot CLI
COPILOT_PROVIDER_BASE_URL (COPILOT_PROVIDER_TYPE=openai, COPILOT_PROVIDER_WIRE_API=completions)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- Cherry Studio
Settings → Model Provider → Add Provider → Endpoint settings → OpenAI (Cherry appends /v1/chat/completions; Anthropic and OpenAI Responses take the same host root)- Value to enter
https://api.router.one- API used
- Chat Completions
POST /v1/chat/ completions
- Chatbox
Settings → Model Provider → Add → Add Custom Provider → OpenAI API Compatible → API Host (Claude API Compatible mode also needs /v1)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- DeepSeek Harness
Settings → Models → Add model provider → Custom model API → Base URL (API protocol OpenAI Chat Completions; OpenAI Responses also takes /v1, Anthropic Messages the host root)- Value to enter
https://api.router.one/v1 - API used
- Chat Completions
POST /v1/chat/ completions
- WorkBuddy
Settings → Model → add a model → Provider: Custom → URL (the full /chat/completions path, Custom Protocol off; OpenAI-compatible APIs only)- Value to enter
https://api.router.one/v1/ chat/ completions - API used
- Chat Completions
POST /v1/chat/ completions
These are the configurations documented in the linked guides. A client can support other providers or APIs; verify the actual request path before changing the URL.
Integration questions, answered
Which Router One base URL should I use?
For the OpenAI-compatible SDK configuration in these guides, use https://api.router.one/v1. Claude Code and Claude Agent SDK use the host root, https://api.router.one. Clients that ask for a full Chat Completions endpoint need https://api.router.one/v1/chat/completions. Some clients append /v1 themselves; follow the guide for the actual field rather than adding it twice.
Does a listed integration support every model and feature?
A guide documents a particular provider configuration. The selected API, model, and client must all support the feature you need. Check the exact model ID, endpoints, context limit, and tool or image support on the model's detail page. A working text request does not verify streaming, tools, or image input.
Can Router One run my agent or index my knowledge base?
Your client or framework runs the agent loop, executes tools, and manages documents. Router One handles each supported model call. Configure embeddings, reranking, and vector storage separately when your knowledge base needs them; the chat connection alone does not provide those services.
How do I check that my integration worked?
Send a simple request and check its final result. In Dashboard → Logs, match the model, time, and request ID, then inspect tokens, latency, status, and settlement. HTTP 200 alone does not prove a stream completed, and pending settlement does not mean a request was free. The customer log view does not display provider attempts or the internal fallback chain.
Your tool isn't listed?
Check whether it accepts a custom provider URL and API key, then match its request protocol to a supported model. The API reference describes the available endpoints.
Read as Markdown