One OpenAI-Compatible API for Claude, GPT, Gemini, and DeepSeek

Integrating large language models usually means a different SDK, a different auth scheme, and a different billing dashboard for every provider. RouteAll removes that friction: it exposes Claude, Gemini, DeepSeek, Qwen, MiniMax and other models behind one OpenAI-compatible API — so the OpenAI client you already use just works.

One key, one base URL

You get a single sk-ra-... key and point your client at one base URL:

curl https://api.routeall.ai/v1/chat/completions \
  -H "Authorization: Bearer $ROUTEALL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-haiku-4-5",
    "messages": [{"role": "user", "content": "Say hello in one sentence."}]
  }'

Switch models by changing the model field — deepseek-v4-flash, gemini-2.5-flash, a Claude or Qwen model, and so on. Browse the live catalog and your tier's price on the model marketplace.

Use it from any SDK

Because the API is OpenAI-compatible, the official OpenAI SDKs work unchanged:

from openai import OpenAI
client = OpenAI(api_key="sk-ra-...", base_url="https://api.routeall.ai/v1")

resp = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Explain RAG in two sentences."}],
)
print(resp.choices[0].message.content)

Streaming, tool calls, vision inputs and the /v1/models listing all behave the way you expect from the OpenAI API.

What you get beyond a passthrough

• Smart routing & failover — requests go to a healthy channel by priority/weight; if an upstream errors, RouteAll fails over automatically and you are never double-billed.
• Transparent, metered billing — pay per token or per call, see your charge per request, top up in USD / CNY / USDT. Prompt-cache hits are discounted.
• More than chat — the same key also does embeddings, image/video/audio generation, web search and speech-to-text.

Start in three steps

1. Create a free account and generate an API key.
2. Point your OpenAI client's base_url at https://api.routeall.ai/v1.
3. Call chat/completions with any model name from the marketplace.

Full reference is in the API docs. One key, every model — that's the whole idea.