One OpenAI-compatible API for every model and provider.
Route chat, images, embeddings, audio, and video through app.nz. Point any OpenAI or Anthropic SDK at the base URL below, keep your code, and switch models with one field. Smart auto routing, automatic failover, usage metering, and one API key.
https://app.nz/v1from openai import OpenAI
client = OpenAI(base_url="https://app.nz/v1", api_key="pk_live_...")
resp = client.chat.completions.create(
model="auto", # smart routing, or pin a model like "gpt-latest"
messages=[{"role": "user", "content": "Write a tiny SSE server in Go."}],
reasoning_effort="auto", # none | low | medium | high | auto
)
print(resp.choices[0].message.content)Authentication
Send your key as Authorization: Bearer pk_live_.... Create one on the account page. Signed in here? Same-origin calls use your session automatically.
Smart auto routing
Send "model": "auto" and the gateway classifies the prompt and routes to the right tier — or pin an explicit model id.
autoDefault chat. Classifies the prompt and routes to the best tier.openpaths/auto-codeAgents, refactors, and bug fixes.openpaths/auto-reasoningPlanning, math, and hard reasoning (auto thinking depth).openpaths/auto-cheapTrivial / classification prompts on the cheapest capable model.openpaths/auto-visionPrompts that include images.openpaths/auto-imageImage generation with a hosted fallback.Endpoints
/v1/chat/completionsOpenAI-compatible chat completions (streaming + tools).
/v1/messagesAnthropic-compatible Messages API for Claude + agent SDKs.
/v1/images/generationsGenerate images (GPT Image, Flux, and more).
/v1/embeddingsVector embeddings for search and RAG.
/v1/audio/speechText-to-speech (also /v1/tts).
/v1/audio/transcriptionsSpeech-to-text transcription.
/v1/videos/generationsGenerate video clips (job-based).
/v1/music/generationsGenerate music (job-based).
/v1/3d/generationsGenerate textured 3D models (job-based).
/api/gateway/modelsList every routable model + provider metadata.
/api/gateway/resolve?model=Preview how a model name routes (provider, fallbacks).
/api/gateway/routePreview which model a bare "auto" request resolves to.
Playground
Run real requests against any model right here — chat, image, embeddings, video, music, speech, transcription, and image→3D, each with a live preview and the raw JSON response. Signed in, it uses your session; otherwise paste an API key.