Provider guides

Every provider, one OpenAI-compatible API

Routeplane fronts 14 model providers behind a single OpenAI-compatible endpoint. Pick a provider to see the drop-in code, fallback example, and the gateway’s provider-specific behaviour — all verified against the adapter source.

provider · openai OpenAI Keep your OpenAI SDK. Point its base URL at Routeplane and get automatic fallback to a second provider, PII redaction on the hot path, residency-aware routing, and cost attribution — without changing a line of application code. Integration guide → provider · anthropic Anthropic Use Claude with the OpenAI SDK you already have. Routeplane translates your OpenAI-shaped request to Anthropic’s Messages API and back, so you never touch the native format — and get fallback, guardrails, and residency on top. Integration guide → provider · gemini Google Gemini Call Gemini with your OpenAI SDK. Routeplane translates your request into Google’s native generateContent shape and maps the response back — you keep one client, and add fallback, guardrails, and residency. Integration guide → provider · azure_openai Azure OpenAI Front your Azure OpenAI deployments with the same OpenAI-compatible endpoint as every other provider — and add fallback, in-data-plane guardrails, and region-locked routing on top. Integration guide → provider · bedrock AWS Bedrock Put Bedrock behind the same OpenAI-compatible endpoint as every other provider, with fallback, guardrails, and region-locked routing — and keep the AWS region as a first-class residency signal. Integration guide → provider · mistral Mistral Call Mistral models with your OpenAI SDK through Routeplane — with fallback, in-data-plane guardrails, and residency routing that fits Mistral’s EU footprint. Integration guide → provider · cohere Cohere Use Cohere’s chat, embeddings, and rerank through the OpenAI-compatible endpoint. Routeplane translates to and from Cohere’s native v2 API, so you keep one client — and add fallback, guardrails, and residency. Integration guide → provider · groq Groq Route Groq’s fast inference through the same OpenAI-compatible endpoint as everything else — with fallback, guardrails, and residency, plus Whisper transcription on the same surface. Integration guide → provider · deepseek DeepSeek Call DeepSeek’s low-cost models with your OpenAI SDK through Routeplane — with fallback, in-data-plane guardrails, residency routing, and cost attribution. Integration guide → provider · together Together AI Call Together’s catalog of open models with your OpenAI SDK through Routeplane — with fallback, in-data-plane guardrails, residency routing, and cost attribution. Integration guide → provider · fireworks Fireworks AI Call Fireworks’ fast open-model inference with your OpenAI SDK through Routeplane — with fallback, in-data-plane guardrails, residency routing, and cost attribution. Integration guide → provider · xai xAI Grok Call xAI’s Grok models with your OpenAI SDK through Routeplane — with fallback, in-data-plane guardrails, residency routing, and cost attribution. Integration guide → provider · openrouter OpenRouter Put OpenRouter’s aggregated model catalog behind Routeplane’s governance — fallback, in-data-plane guardrails, residency, and cost attribution — while keeping OpenRouter’s breadth. Integration guide → provider · self_hosted Self-hosted (Ollama / vLLM / LocalAI) Front your own Ollama, vLLM, or LocalAI server with Routeplane and get the same fallback, guardrails, residency, and cost attribution as the hosted providers — while your model stays on your infrastructure. Integration guide →

Provider-specific behaviour on each page is verified against the Routeplane adapter source. Model availability and pricing are the provider’s own; re-verify before procurement.