Other OpenAI-compatible clients

Anything that speaks OpenAI Chat Completions works with Hyphen. The recipe is always the same three values:

Code
Base URL   https://api.hyphen-solution.com/v1
API key    sk-hy-...
Model      m2.5 · m2.7 · m3 · text

Get a key at app.hyphen-solution.com (Dashboard → API Keys → Create), set those three, and you're done.

Cursor

Settings → Models → enable Custom OpenAI base URL:

• Base URL: https://api.hyphen-solution.com/v1
• API key: sk-hy-...
• Add a model named m3 (or another Hyphen model) and select it.

Cline

In Cline's provider settings choose OpenAI Compatible:

• Base URL: https://api.hyphen-solution.com/v1
• API key: sk-hy-...
• Model ID: m3

Aider

Pass the base URL and key as flags (or the matching env vars):

Code
aider \
  --openai-api-base https://api.hyphen-solution.com/v1 \
  --openai-api-key sk-hy-... \
  --model m3

Equivalent environment variables:

Code
export OPENAI_API_BASE="https://api.hyphen-solution.com/v1"
export OPENAI_API_KEY="sk-hy-..."
aider --model m3

Continue

In ~/.continue/config.json (or the YAML config), add an OpenAI-compatible model:

Code
{
  "models": [
    {
      "title": "Hyphen m3",
      "provider": "openai",
      "model": "m3",
      "apiBase": "https://api.hyphen-solution.com/v1",
      "apiKey": "sk-hy-..."
    }
  ]
}

OpenAI SDK (raw)

Code
from openai import OpenAI

client = OpenAI(
    base_url="https://api.hyphen-solution.com/v1",
    api_key="sk-hy-...",
)
resp = client.chat.completions.create(
    model="m3",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Code
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.hyphen-solution.com/v1",
  apiKey: "sk-hy-...",
});
const resp = await client.chat.completions.create({
  model: "m3",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Hitting the cap

Every client sees the same HTTP 429 with the reset date when the monthly budget is spent. No overage.