Copy page

Get Started

Quickstart

Three steps: get a key, point at the base URL, send a request.

1. Get a key

Keys come from the Hyphen console, and a key needs an active plan behind it: create an account, subscribe (from $3/mo) or grab a credit pack, and your key appears in the console.

1. Go to app.hyphen-solution.com and sign in.
2. Pick a plan or credit pack on the Billing page (skip if you already have one).
3. Open Dashboard → API Keys and copy the key — it looks like sk-....

One key authenticates every endpoint. Keep it secret — treat it like a password. Export it into your shell so the samples below pick it up:

Code
export HYPHEN_API_KEY="sk-..."

2. Set the base URL

The gateway root is:

Code
https://api.hyphen-solution.com

OpenAI-style clients want the /v1 root:

Code
https://api.hyphen-solution.com/v1

3. Make your first request

A minimal Chat Completions call with curl — this returns a completion from the flagship model, minimax-m3:

Code
curl https://api.hyphen-solution.com/v1/chat/completions \
  -H "Authorization: Bearer $HYPHEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m3",
    "messages": [
      { "role": "user", "content": "Say hello in one sentence." }
    ]
  }'

You'll get back an OpenAI-shaped response:

Code
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "minimax-m3",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "Hello — great to meet you!" },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 12, "completion_tokens": 8, "total_tokens": 20 }
}

If you see a choices[0].message.content, you're connected.

Same call, OpenAI SDK

Code
from openai import OpenAI

client = OpenAI(
    base_url="https://api.hyphen-solution.com/v1",
    api_key="sk-...",  # your Hyphen key
)

resp = client.chat.completions.create(
    model="minimax-m3",
    messages=[{"role": "user", "content": "Say hello in one sentence."}],
)
print(resp.choices[0].message.content)

Code
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.hyphen-solution.com/v1",
  apiKey: "sk-...", // your Hyphen key
});

const resp = await client.chat.completions.create({
  model: "minimax-m3",
  messages: [{ role: "user", content: "Say hello in one sentence." }],
});
console.log(resp.choices[0].message.content);

Check which models you have

Code
curl https://api.hyphen-solution.com/v1/models \
  -H "Authorization: Bearer $HYPHEN_API_KEY"

Code
{
  "object": "list",
  "data": [
    { "id": "minimax-m2", "object": "model", "owned_by": "minimax" },
    { "id": "minimax-m2-her", "object": "model", "owned_by": "minimax" },
    { "id": "minimax-m2.1", "object": "model", "owned_by": "minimax" },
    { "id": "minimax-m2.1-highspeed", "object": "model", "owned_by": "minimax" },
    { "id": "minimax-m2.5", "object": "model", "owned_by": "minimax" },
    { "id": "minimax-m2.5-highspeed", "object": "model", "owned_by": "minimax" },
    { "id": "minimax-m2.7", "object": "model", "owned_by": "minimax" },
    { "id": "minimax-m2.7-highspeed", "object": "model", "owned_by": "minimax" },
    { "id": "minimax-m3", "object": "model", "owned_by": "minimax" },
    { "id": "minimax-text-01", "object": "model", "owned_by": "minimax" }
  ]
}

All ten are MiniMax models under their real names. Pick by tier — flagship minimax-m3, balanced minimax-m2.7, fast minimax-m2.5 — and see Models for the full catalog, including the -highspeed variants, the older generations, and the specialty models.

What happens at the cap

When your key's monthly budget is spent, requests fail closed with HTTP 429 instead of running over budget:

Code
{
  "error": {
    "message": "Budget has been exceeded! Monthly budget resets on 2026-08-01.",
    "type": "budget_exceeded",
    "code": "429"
  }
}

No overage is ever charged. Full details on Rate limits & caps.

Where to go next

• Connect your coding agent — one page per tool, each a single copy-paste block.
• Choosing a model for which model fits which job. Read the max_tokens section before you build anything.
• Recipes for copy-pasteable code. Streaming, tool calling, structured JSON, a small agent loop, and 429 handling.
• API Reference — try every endpoint interactively.