AIREITER
GPT-5.6 Integration GuideYou don't need to understand every API. Pick Responses, Messages, or Chat — the protocols AIReiter currently supports — then copy a config verified against official docs or this project's code.
All prices are per 1M tokens. AIReiter is currently set to half of the official GPT-5.6 rate, including normal input, output, cached input, and cache writes.
| Model | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| GPT-6 Astra | Official $10AIReiter $3 | Official $50AIReiter $15 | Official $1AIReiter $0.3 | Official $12.5AIReiter $3.75 |
| GPT-5.6 Sol | Official $5AIReiter $2.5 | Official $30AIReiter $15 | Official $0.5AIReiter $0.25 | Official $6.25AIReiter $3.125 |
| GPT-6.1 Sol | Official $2AIReiter $0.6 | Official $10AIReiter $3 | Official $0.1AIReiter $0.03 | Official $2.5AIReiter $0.75 |
| GPT-5.6 Terra | Official $2.5AIReiter $1 | Official $15AIReiter $6 | Official $0.25AIReiter $0.1 | Official $3.125AIReiter $1.25 |
| GPT-5.6 Luna | Official $1AIReiter $0.1 | Official $6AIReiter $0.6 | Official $0.1AIReiter $0.01 | Official $1.26AIReiter $0.125 |
| GPT-5.5 | Official $5AIReiter $0.8 | Official $30AIReiter $4.8 | - | - |
| GPT-5.4 | Official $2.5AIReiter $0.5 | Official $15AIReiter $3 | - | - |
OpenAI SDK and OpenAI-compatible clients should use this first. baseURL stops at /api/v1.
The OpenAI SDK baseURL + chat.completions shape follows the official SDK/API conventions; AIReiter's /api/v1/chat/completions comes from this project's route.
Client Base URL
https://aireiter.com/api/v1
Client-appended path
/chat/completions
Final request URL
https://aireiter.com/api/v1/chat/completions
Example model
gpt-5.6-luna
The key point: baseURL stops at /api/v1.
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.AIREITER_API_KEY,
baseURL: "https://aireiter.com/api/v1",
});
const response = await client.chat.completions.create({
model: "gpt-5.6-luna",
messages: [
{ role: "user", content: "Explain the directory structure of this project" }
],
});
console.log(response.choices[0]?.message?.content);If the SDK reports model not found, first confirm the model id exists in /models.
curl -sS "https://aireiter.com/api/v1/models" \
-H "Authorization: Bearer $AIREITER_API_KEY"They are clients that carry a protocol, not protocols themselves: give Claude Code-style tools the Anthropic-style address, and OpenAI-compatible tools /api/v1. Full step-by-step guides live under the matching protocol above.
In the Claude Code tab set the provider base URL to https://aireiter.com/api — guide under "Messages protocol → CC Switch (GUI)". In the Codex tab use https://aireiter.com/api/v1 — guide under "Responses protocol → CC Switch (GUI)".
With api: "openai-completions" set baseUrl to https://aireiter.com/api/v1; with api: "anthropic-messages" use https://aireiter.com/api. Step-by-step guide under "Chat protocol → OpenClaw".
Text-model gateways like OpenRouter, Groq, and Together all have the SDK baseURL/base_url stop at /v1, with the SDK method appending /chat/completions. This page splits them the same way: client base URL, client-appended path, and final request URL are shown separately.
Yes, at /api/v1/messages/count_tokens. It only does Anthropic token counting — it is not a generation endpoint.
Copy-ready configs only include what official docs, the OpenAI/Anthropic protocols, or this project's code can verify; third-party clients get compatibility notes only.
Codex → Responses; Claude Code → Messages; OpenAI SDK and generic OpenAI-compatible clients → Chat; if you'd rather not edit config files, use the CC Switch GUI.