OpenAI-compatible. Eleven frontier models. List price halved.

From "never heard of it" to first call. Three steps.

Every step below is the actual flow — no marketing detour, no SSO mandate, no calendar invite. If you already have an OpenAI client somewhere in your stack, you're 90 % of the way there.

1. 01

   Generate an sl- key

   Email-only sign-up at dashboard.slashed.pro. No card, no SSO mandate. You receive a key prefixed sl- plus a 1 M-token migration credit on first issue. The key is scoped per-seat — you can mint sub-keys with their own per-month cost ceilings before you write a single line.

   Generate a key → Key management docs
2. 02

   Point OPENAI_BASE_URL at SLASHED

   Three OpenAI-compatible clients, three near-identical patches. The only thing that changes is the base URL and the key prefix; the model name, message shape, and response shape stay where they were.

   OpenAI Python LangChain Vercel AI SDK

   from openai import OpenAI
   
   client = OpenAI(
     base_url="https://api.slashed.pro/v1",
     api_key="sl-...",
   )
   resp = client.chat.completions.create(
     model="gpt-5.4",
     messages=[{"role": "user", "content": "ping"}],
   )
   print(resp.choices[0].message.content)

   from langchain_openai import ChatOpenAI
   
   llm = ChatOpenAI(
     base_url="https://api.slashed.pro/v1",
     api_key="sl-...",
     model="claude-opus-4-7",
   )
   print(llm.invoke("ping").content)

   // app/ai.ts
   import { createOpenAI } from "@ai-sdk/openai";
   import { generateText } from "ai";
   
   const slashed = createOpenAI({
     baseURL: "https://api.slashed.pro/v1",
     apiKey:  process.env.SLASHED_API_KEY,  // sl-...
   });
   
   const { text } = await generateText({
     model: slashed("gemini-3.5-flash"),
     prompt: "ping",
   });

3. 03

   Make your first call — and read the response

   Copy-paste this. If it returns a non-null content string, you are integrated. The response shape is the OpenAI chat.completions object verbatim — every existing parser keeps working.

   — Request

   curl $OPENAI_BASE_URL/chat/completions \
     -H "Authorization: Bearer $OPENAI_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
       "model": "claude-opus-4-7",
       "messages": [{"role":"user","content":"In one word: ping."}]
     }'

   — Response (shape, abbreviated)

   {
     "id": "chatcmpl-...",
     "object": "chat.completion",
     "model": "claude-opus-4-7",
     "choices": [{
       "index": 0,
       "message": { "role": "assistant", "content": "pong" },
       "finish_reason": "stop"
     }],
     "usage": { "prompt_tokens": 8, "completion_tokens": 1, "total_tokens": 9 }
   }