Quick Start

One API key. All models. OpenAI & Anthropic compatible.

Base URL

Try it now

curl https://api.luno.codes/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 1024
  }'

Get API Key

Dashboard → API Keys → Create

Set Base URL

https://api.luno.codes/v1

Use any model

claude-sonnet-4-6, gpt-4o, gemini-3.1-pro...

Authentication

Pass your API key via the Authorization header or x-api-key.

Header format

Authorization: Bearer YOUR_API_KEY

# or

x-api-key: YOUR_API_KEY

Create API keys in Dashboard → API Keys. Each key inherits your plan's limits.

Integrations

Drop-in replacement for any tool that supports OpenAI or Anthropic API.

Claude Code

Copy-paste ready. Replace your settings file and you're live.

~/.claude/settings.json

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.luno.codes",
    "ANTHROPIC_AUTH_TOKEN": "YOUR_API_KEY",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "claude-opus-4-8",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "claude-sonnet-4-6",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "claude-haiku-4-5"
  }
}

ANTHROPIC_BASE_URL — без /v1 (Claude Code добавляет сам)

Задай все 3 DEFAULT_*_MODEL — иначе фоновые задачи упадут с "model may not exist"

Codex CLI

export OPENAI_BASE_URL=https://api.luno.codes/v1
export OPENAI_API_KEY=YOUR_API_KEY
codex

OpenCode

~/.config/opencode/config.json

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "luno": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Luno",
      "options": {
        "baseURL": "https://api.luno.codes/v1",
        "apiKey": "YOUR_API_KEY"
      },
      "models": {
        "claude-opus-4-8": { "name": "Claude Opus 4.8" },
        "claude-sonnet-4-6": { "name": "Claude Sonnet 4.6" },
        "gpt-4o": { "name": "GPT-4o" }
      }
    }
  }
}

Cursor

Settings → Models → OpenAI API Key:

Base URL: https://api.luno.codes/v1
API Key:  YOUR_API_KEY

OpenAI Python SDK

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.luno.codes/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Anthropic Python SDK

Python

import anthropic

client = anthropic.Anthropic(
    base_url="https://api.luno.codes/v1",
    api_key="YOUR_API_KEY"
)

message = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}]
)
print(message.content[0].text)

Any tool that takes a Base URL + API Key works. Just point it at https://api.luno.codes/v1

Models

All models available through a single endpoint. Click any model ID to copy.

List models

curl https://api.luno.codes/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Claude

claude-opus-4-8

Most capable, complex tasks

claude-opus-4-7

Previous flagship

claude-opus-4-6

Strong reasoning

claude-opus-4-5

Balanced Opus

claude-sonnet-4-6

Best speed/quality balance

claude-sonnet-4-5

Fast generation

claude-sonnet-4

Lightweight Sonnet

claude-haiku-4-5

Ultra-fast

Claude Fable

claude-fable-5

Latest Fable series, creative & fast

GPT

gpt-5.5

Latest flagship

gpt-5.4

Previous flagship

gpt-5.3-codex

Agentic coding

gpt-5.2-codex

Long-horizon coding

gpt-5.1

Adaptive reasoning

gpt-4o

Multimodal

gpt-4o-mini

Fast & cheap

Gemini

gemini-3.5-flash

Fastest, best value

gemini-3.1-pro

Most capable Gemini

gemini-3.1-flash

Lightweight & fast

Endpoints

POST/v1/chat/completions

OpenAI format — works with all models

POST/v1/messages

Anthropic format — Claude models (Claude Code, SDK)

Streaming

Add "stream": true for real-time Server-Sent Events output.

cURL (SSE)

curl https://api.luno.codes/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "stream": true,
    "messages": [{"role": "user", "content": "Explain SSE briefly"}]
  }'

Node.js

const res = await fetch("https://api.luno.codes/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "claude-sonnet-4-6",
    stream: true,
    messages: [{ role: "user", content: "Hello" }]
  })
});

const reader = res.body.getReader();
const decoder = new TextDecoder();
while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  process.stdout.write(decoder.decode(value));
}

Errors

Standard HTTP status codes with JSON error bodies.

401

auth_error

Invalid or missing API key

402

insufficient_funds

Token budget exhausted for this period

429

rate_limit_exceeded

Too many requests — slow down

502

upstream_error

Model provider temporarily unavailable

Error response format

{
  "error": {
    "message": "Invalid API key provided.",
    "type": "auth_error",
    "code": 401
  }
}