CodeI Lab gateway details

A third-party paid GPT API relay aimed at coding agents; the website states it is not affiliated with OpenAI. One key works over two protocols: the OpenAI-compatible endpoint https://www.codeilab.com/api/codex (Responses and Chat Completions) and the Anthropic Messages-compatible endpoint https://www.codeilab.com/api/anthropic. Over the Claude protocol, requests for claude-sonnet / opus / haiku are mapped to GPT models of the matching tier; no Claude models are offered. The pricing page lists six models: GPT-6 Astra, GPT-6 Sol, GPT-6.1 Sol, GPT-6.1 Terra, GPT-5.6 Sol, and GPT-5.6 Terra. The docs include setup guides for Claude Code, Codex CLI, Cursor, and OpenCode, plus a one-line install script.

Small amounts
Trial first

Overview

A third-party paid GPT API relay aimed at coding agents; the website states it is not affiliated with OpenAI. One key works over two protocols: the OpenAI-compatible endpoint https://www.codeilab.com/api/codex (Responses and Chat Completions) and the Anthropic Messages-compatible endpoint https://www.codeilab.com/api/anthropic. Over the Claude protocol, requests for claude-sonnet / opus / haiku are mapped to GPT models of the matching tier; no Claude models are offered. The pricing page lists six models: GPT-6 Astra, GPT-6 Sol, GPT-6.1 Sol, GPT-6.1 Terra, GPT-5.6 Sol, and GPT-5.6 Terra. The docs include setup guides for Claude Code, Codex CLI, Cursor, and OpenCode, plus a one-line install script.

Best for: For developers who run GPT models in Claude Code, Codex CLI, Cursor, or OpenCode with fairly steady monthly usage; buy the $3 trial first to check models and speed before choosing a monthly plan.

Availability and latency

Current status
Test yourself
Latency reference
Not tested
/models check
The pricing table lists 6 models; /api/codex/models has no public model list
Last verified
2026-11-06
Status notes
The website, docs, pricing page, terms of service, and privacy policy were accessible; keyless requests to /api/codex/responses and /api/anthropic/v1/messages both returned 401 authentication errors. AI Beyond has not signed up, made paid requests, or tested latency, and has not verified the upstream source or an independent public status page.

Supported models

OpenAI

Pricing and multipliers

Pricing mode
Priced in USD. Plans include a USD quota deducted at official pay-as-you-go rates: Trial $3.00 for 7 days with $30, Plus $9.90/month with $100, Pro $39.90/month with $500, and Ultra $99.90/month with $1,500, plus a custom plan with a chosen monthly quota and a 1–6 month term; quarterly and yearly billing are listed at 15% and 30% off. Every plan includes all six models and differs in quota and API key limit (3 / 10 / 50 / 100 keys). The pricing page also mentions pay-as-you-go top-ups that do not expire with a billing cycle. Per-1M-token rates include GPT-6.1 Terra at $1 input / $5 output and GPT-6 Astra at $10 input / $50 output; for GPT-6 Astra, GPT-6 Sol, and both GPT-6.1 models, a request with more than 272K input tokens is billed at 2x input and cache rates and 1.5x output for the whole request. The website's "up to 93% below official pay-as-you-go cost" figure is Ultra's $99.90 divided by its $1,500 quota, which holds only if the quota is fully used. The terms of service say payments go through Stripe. On 2026-11-06 the discount note labeled Ultra as "Ultra (Monthly) (One-time)" while the bottom of the pricing page said plans renew automatically and can be cancelled any time; check the checkout page for the renewal terms.
Price tags
Plan-based, Pay-as-you-go
Free quota
No free quota; the cheapest option is the $3 seven-day trial

Payment methods

Stripe

How to call the API

Usually you create an API key in the platform console, then replace the SDK's baseURL, model name, and auth details per the docs. Test streaming, function calling, error codes, and rate limits before launch.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AI_GATEWAY_API_KEY,
  baseURL: "https://www.codeilab.com/api/codex"
});

const response = await client.chat.completions.create({
  model: "gpt-6.1-terra",
  messages: [{ role: "user", content: "Test one call through an AI gateway." }]
});

Pros

  • Supported models: OpenAI.
  • Capabilities: OpenAI-compatible.
  • Documentation completeness: High; stability not tested.

Cons

  • Not an official OpenAI service; the website describes itself as an independent third-party gateway. It sells quota at a fraction of official pay-as-you-go prices but does not disclose its upstream source, and AI Beyond has not verified its authorization or the identity of the models served. Over the Claude protocol the models actually called are GPT models; tool calling depends on the model, and the website says GPT-6 Astra and GPT-6.1 models need the Responses API for tools. The terms of service grant the platform a limited license to use your code and feedback to improve the service, and the privacy policy says it collects API requests and interaction data; avoid sending sensitive code or data. The terms offer a 14-day money-back guarantee for new subscriptions, with later refunds at the platform's discretion. Unused plan quota does not carry over. The privacy policy lists the contact email cfjwlchangji@gmail.com, and the submitter also provided links@codeilab.com; the footer names the company Fomalhaut Labs, which the submitter says is based in Singapore; AI Beyond has not verified the operating entity. No independent public status page has been verified.
  • Third-party relay pricing, models, and availability can change, so re-check them periodically.

Alternatives

AggregatorPrepaid

A third-party multi-model API relay built on New API. One key works with the OpenAI-compatible endpoint https://www.aifast.link/v1 (Chat Completions and Responses) and the Anthropic Messages endpoint https://www.aifast.link/v1/messages, and Gemini models also support the native Gemini API; the site configuration lists https://api.aifast.link as a backup address. On 2026-11-06 the public model catalog listed GPT (gpt-6-astra, gpt-6.1-sol, gpt-6.1-terra, gpt-5.6-sol, and others), Claude (claude-opus-5-5, claude-sonnet-5-5, claude-haiku-5-5, claude-fable-5-1, and others), and Gemini models (gemini-4-argon, gemini-3.8-flash, and others), plus the gpt-image-2 image model, with available models determined by the key's group. The developer docs include setup guides for Codex, Claude Code, Cursor, Dify, Cherry Studio, OpenWebUI, and other clients.

Models
OpenAI, Claude, Gemini
Payment
Alipay, WeChat
Price
Charged per token from an in-site USD credit balance, with the actual cost equal to the model's official USD price times the key group's multiplier; the dollar sign in the dashboard is an in-site usage unit, not cash. On 2026-11-06 the public pricing API showed Codex discount / dedicated / stable group multipliers of 0.7 / 1 / 1.1, Claude discount / stable groups at 0.9 / 1.5, Claude Code discount / stable / dedicated groups at 1.6 / 3.35 / 4.5, and the Gemini group at 1.8; group multipliers are the site's own billing coefficients, not official discounts. Pay-as-you-go: a 2026-10-08 check of the wallet page recorded in the docs shows CNY 7.50 paid for USD 10 of credit, and the docs give gpt-6.1-sol in the Codex discount group as an example, at a top-up-adjusted price of CNY 1.05 input and CNY 5.25 output per 1M tokens. There are also 30-day monthly plans with a daily quota that resets each day and covers only specified groups: in the docs' 2026-11-04 snapshot, GPT plans cost CNY 199 / 349 / 639 / 1199 for USD 20 / 40 / 80 / 160 of daily credit, and Claude plans cost CNY 258 / 449 / 889 / 1599 for the same four tiers; monthly plans do not include the Gemini group. The docs say the wallet page offers WeChat Pay and the monthly plan page offers Alipay and WeChat Pay, while credit cards and USDT are unconfirmed; check the dashboard and checkout page for current prices.
AggregatorPrepaid

A third-party multi-model API relay built on New API, aimed mainly at Chinese-speaking developers. Codex and OpenAI-compatible clients use https://api.linktoagi.com/v1 (Codex uses the Responses protocol), while Claude Code and Gemini CLI use https://api.linktoagi.com without /v1. The public model catalog lists GPT / Codex, Claude, Gemini, Grok, DeepSeek, and GLM models plus gpt-image image models, with available models determined by the key's group. The docs include setup guides for Codex, Claude Code, Gemini CLI, CC Switch, and Cherry Studio.

Models
OpenAI, Claude, Gemini, Grok, DeepSeek, GLM
Payment
Alipay, WeChat
Price
Charged per token from a CNY balance, with the actual cost equal to the model's base billing times the key group's multiplier; image models are billed per request. On 2026-11-05 the public pricing API showed Codex Sale / Plus / Pro group multipliers of 0.10 / 0.15 / 0.25, Grok 0.2, DeepSeek 0.3, GLM 0.4, Gemini 0.6, and Claude groups ranging from 0.4 to 2. When rechecked on 2026-11-10, the API showed 0.08 for the Codex Sale group, while the operator's promotion post and message still state 0.10; check the model hub before paying. Group multipliers are the site's own billing coefficients, not USD-per-million-token prices or official discounts; check the model hub for unit prices. The docs list Alipay and WeChat Pay; the submitter says the wallet accepts custom top-ups from CNY 1.
Aggregator

A third-party multi-model API relay where one key works across three protocols: OpenAI-compatible endpoints (Chat Completions and Responses at https://tokenbuddy.cc/v1), Anthropic Messages, and the native Gemini API (at https://tokenbuddy.cc). Its public model marketplace lists chat models including GPT, Claude, Gemini, Grok, DeepSeek, GLM, and Kimi, plus gpt-image image generation and Seedance video models; the docs cover setup for clients such as Codex, Claude Code, Gemini CLI, OpenCode, and WorkBuddy. Group names and model attributions are platform-reported and do not establish official authorization.

Models
OpenAI, Claude, Gemini, Grok, DeepSeek, GLM and more
Payment
Price
Billed per token; the model marketplace lists prices in CNY per 1M tokens, and video models are billed per request. GPT and Claude models come in an economy group and a -full stable / full-strength group at different prices. For example, on 2026-10-28 the page showed gpt-5.6-sol (economy) at CNY 0.693 input / CNY 4.158 output, claude-sonnet-5 (economy) at CNY 1 / CNY 5, and claude-sonnet-5-full (full-strength group) at CNY 4 / CNY 20. Prices change; check the marketplace. Top-up codes are redeemed for credit on the website's Redeem page. When the service was listed on 2026-10-28, a separate public top-up code shop at shop.tokenbuddy.cc offered only "Epay - Alipay" as a payment method and sold a $100 code for CNY 100; on the 2026-11-04 recheck that shop redirected to a sign-in-gated purchase page on the main site, so the current payment methods and prices could not be rechecked.
Aggregator

A third-party paid API relay built on the open-source New API project, with an OpenAI-compatible endpoint at https://catcatcode.com/v1; Claude models are also listed with an Anthropic endpoint type. Its public model catalog lists GPT and Claude models plus DeepSeek, GLM, Kimi, Doubao, MiniMax, and others, and its docs include setup guides for Codex, Claude Code, OpenCode, and WorkBuddy. Model names and group descriptions are platform-reported and do not establish official authorization.

Models
OpenAI, Claude, DeepSeek, Moonshot, Doubao, GLM and more
Payment
Price
Subscription plans are bought one month at a time and do not auto-renew: Light CNY 99, Standard CNY 199, and Pro CNY 299, with daily allowances of $10 / $25 / $40 and monthly allowances of $300 / $700 / $1,100 in "official list-price quota", deducted at each model's official list price; the daily allowance resets and unused amounts do not carry over. Wallet top-ups are charged under the site's own billing rules; public group multipliers include gpt-plus 0.5, gpt-pro 0.8, workbuddy 0.6, claude max 2, and the domestic-model group 1, and actual charges also depend on model, input/output, and caching. The submitter says Alipay, WeChat, and credit card (Stripe) are supported; top-up and checkout pages require sign-in, so AI Beyond has not verified payment methods.

FAQ

Is CodeI Lab compatible with the OpenAI API?
This entry is marked as supporting the OpenAI-compatible format, but the exact base_url, model names, and parameters still follow the official docs.
Is CodeI Lab ready for production?
Run a small-traffic load test, rate-limit test, and error-code test first, and confirm the billing rules; keep a backup provider for important workloads.

Risk

Risk notice

This site only organizes information about AI API relay services; it makes no guarantee about third-party platforms' stability, price, data security, or availability. Judge the risk yourself before use, and avoid uploading sensitive data, personal privacy, trade secrets, or core API keys to unknown platforms.