mj_custom_zoom — price, context and performance

Q: What is the context window of mj_custom_zoom?

mj_custom_zoom has a - context window: the combined token limit for input and output in a single request.

Overview

API formats	openai, openai-response, openai-response-compact, anthropic, gemini, openai-alpha-search

Pricing

Per request	-

Performance

API endpoint	https://api.airai.cc/v1
OpenAI-compatible	OpenAI-compatible

FAQ

How much does mj_custom_zoom cost?

mj_custom_zoom is billed per request at - each.

What is the context window of mj_custom_zoom?

mj_custom_zoom has a not specified context window: the combined token limit for input and output in a single request.

How do I call mj_custom_zoom from code?

Point base_url to https://api.airai.cc/v1 and set model to mj_custom_zoom. The API is fully OpenAI compatible.

Why does mj_custom_zoom return error 429?

429 is a rate limit response. Lower your concurrency, retry with backoff, or switch to a plan with a larger quota.

Troubleshooting

429 is a rate limit response. Lower your concurrency, retry with backoff, or switch to a plan with a larger quota.

Common causes

Too many concurrent requests
Quota of the current plan exhausted
Retrying immediately without backoff

How to fix

Limit concurrency and retry with exponential backoff
Switch to a plan with a larger quota
Cache repeated requests

How to connect

cURLPythonTypeScriptJavaScript

curl https://api.airai.cc/v1/chat/completions \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mj_custom_zoom",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="<YOUR_API_KEY>",
    base_url="https://api.airai.cc/v1"
)

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

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "<YOUR_API_KEY>",
  baseURL: "https://api.airai.cc/v1"
});

const response = await client.chat.completions.create({
  model: "mj_custom_zoom",
  messages: [{ role: "user", content: "Hello" }]
});
console.log(response.choices[0].message.content);

const OpenAI = require("openai");

const client = new OpenAI({
  apiKey: "<YOUR_API_KEY>",
  baseURL: "https://api.airai.cc/v1"
});

client.chat.completions.create({
  model: "mj_custom_zoom",
  messages: [{ role: "user", content: "Hello" }]
}).then((r) => console.log(r.choices[0].message.content));

Replace <YOUR_API_KEY> with the API Key from your token settings.

Compatible endpoints

openaiopenai-responseopenai-response-compactanthropicgeminiopenai-alpha-search

Gemini SDK · TypeScript

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI("<YOUR_API_KEY>");
const model = genAI.getGenerativeModel({ model: "mj_custom_zoom" });

const result = await model.generateContent(
  "Explain quantum entanglement in one paragraph."
);
console.log(result.response.text());

Authentication

All requests must include the Authorization: Bearer <TOKEN> header. Anthropic-format endpoints also accept the x-api-key header. Generate your API Key on the Tokens page, where you can scope access by model, group, IP, and rate limits.

Supported parameters

Parameter	Type	Default	Range	Description
`temperature`	float	1	0–2	Sampling temperature; lower is more stable
`top_p`	float	1	0–1	Nucleus sampling cumulative probability
`max_tokens`	integer	—	—	Maximum tokens in the response
`frequency_penalty`	float	0	−2–2	Penalizes repeated high-frequency tokens
`presence_penalty`	float	0	−2–2	Encourages introducing new topics
`stop`	string[]	null	≤ 4	Up to 4 strings that stop generation
`seed`	integer	null	—	Seed for more reproducible sampling
`n`	integer	1	—	Number of candidate completions
`stream`	boolean	false	—	Stream tokens via SSE
`response_format`	object	—	—	Force JSON output or schema-conformant results
`tools`	array	—	—	Function/tool declarations the model can call
`tool_choice`	string \| object	auto	—	Tool selection strategy or specific tool name
`logprobs`	boolean	false	—	Return log probabilities for each token
`top_logprobs`	integer	null	0–20	Number of top probabilities returned per token
`logit_bias`	map	—	—	Logit bias mapping per token
`user`	string	—	—	End-user identifier for risk auditing

Rate limits

Tier	RPM	TPM	RPD
Eco	990	398K	20K
Test	980	393K	20K

Data updated: 2026-10-10 08:15