AI API Router Directory

GitLab Duo is GitLab's set of AI features across the software lifecycle, including AI chat and code suggestions in the IDE, agentic chat, foundational agents and flows, a custom agent catalog, model selection and MCP integrations. GitLab's pricing page lists GitLab.com Free at $0/user/month with up to 5 users in a private top-level group, 400 compute minutes per month, 10 GiB storage and static application security testing, but states plainly that on Free "AI features can be accessed via the purchase of GitLab Credits add-on". Included AI credits appear only on paid tiers, shown as a limited-time promotional offer: $12 GitLab Credits per user/month on Premium ($29/user/month billed annually) and $24 per user/month on Ultimate, with GitLab Credits priced at $1 per credit.

GitLab.com Free is $0/user/month but includes no AI credits: the pricing page states AI features on Free are accessed only by purchasing the GitLab Credits add-on at $1 per credit, so the free AI grant is zero (checked 2026-09-16).

Adapta One (adapta.org / agent.adapta.one) — Brazilian multi-model AI subscription ('maior ecossistema de IA generativa do Brasil') bundling 15+ chat and image models (GPT, Claude, Gemini, DeepSeek, Qwen, Llama, Grok, Kimi, Flux, Nano Banana, etc.) in one chat with documents/spreadsheet analysis. Unofficial browser/cookie integration.

Flat R$99/user/month (≈US$18) with unlimited access to the bundled models; annual option R$1,428/year (12× R$119 with 2+ seats).

Antigravity CLI (agy) — the terminal TUI for Google Antigravity 2.0, replacing Gemini CLI. Shares the same agent backend as the Antigravity IDE (incl. Claude models). Authenticates via Google OAuth. Free 'Individual' tier with weekly rate limits; higher limits via Google AI Pro/Ultra plans. No bring-your-own-key support.

Overage billed via purchased Google AI credits at Gemini Enterprise Agent Platform consumption pricing (not per-token fixed).

Arena.ai (formerly LMArena / Chatbot Arena, lmarena.ai) is a free, anonymous multi-model chat + blind A/B voting service that powers the public LLM/image/code leaderboards. It rotates a large lineup of frontier and open models. This route is an unofficial web-cookie integration (arena-auth cookie, optional Cloudflare clearance/reCAPTCHA tokens); the site also supports anonymous sessions but automated access is rate-limited and subject to bot checks.

A free tier is available; the exact credit value is not quantified.

Gemini for business is delivered through Google Workspace rather than as a standalone AI SKU: Gemini is included in every Workspace plan, from Starter at $7.00 per user per month (with a $5.60 introductory rate) through Business Standard at $14 per user per month on annual terms ($16.80 billed monthly) and Business Plus at $17.60 annual ($22.00 monthly), with 14-day free trials and no-commitment monthly billing. The Enterprise tier is quote-based ('Let's talk', contact sales) and adds agent management via Gemini Enterprise, agent governance, AI-powered DLP, digital sovereignty controls, eDiscovery and no minimum or maximum user limits. Standard seats include 2 TB pooled storage per user, AI in Gmail/Drive/Sheets/Meet/Vids, Gemini Notebook and Studio workflow automation.

Google offers a 14-day Google Workspace trial at no cost ('No cost for 14 days') with promotional discounts, but no dollar credit or Gemini allowance is stated on the official pricing or AI pages (checked 2026-09-16).

The Gemini app is free with a personal Google Account at 'standard limits'; Google's help centre states Gemini Apps use compute-based usage limits that refresh every 5 hours until a weekly limit is reached. Free accounts get a 32k-token context window and access to Gemini Flash-Lite, Flash and Pro models, while paid tiers raise limits (Google AI Plus 2x at $4.99/mo, AI Pro 4x at $19.99/mo, AI Ultra 5x or 20x at $99.99 and $199.99/mo) and lift the context window to 1M tokens on Pro and Ultra.

No monetary credit accompanies the free Gemini tier; Google states free access has 'standard limits' with a 32k-token context window, while paid Google AI plans are $4.99/mo (Plus), $19.99/mo (Pro) and from $99.99/mo (Ultra, 5x and 20x variants).

Google Jules is an asynchronous coding agent that clones a connected GitHub repository into a Google Cloud VM, presents a plan for approval, then returns a diff and pull request. The no-cost tier is stated as 15 tasks per day and 3 concurrent tasks, while Jules in Google AI Pro provides 100 tasks per day and 15 concurrent tasks and Jules in Google AI Ultra provides 300 tasks per day and 60 concurrent tasks. Jules is described as language agnostic but works best with JavaScript/TypeScript, Python, Go, Java and Rust projects.

The no-cost tier is stated on jules.google as 15 tasks per day and 3 concurrent tasks, described in Google's blog as 'Introductory access to Jules'; no USD credit is published and daily task caps do not convert to a dollar amount.

HelixMind is an AI API router designed to manage and optimize costs across hundreds of LLMs through a single endpoint. It native speaks the OpenAI API format and features automatic model selection by price and task requirement, ensuring enterprise-grade reliability.

No public free-tier information found in the source reference; treat free-tier availability as unverified rather than confirmed absent.

Juzi AI (api.juziai.cc) is a Chinese commercial-aggregator relay built on the New-API framework. It aggregates high-end models like GPT-5 and Claude Opus by leveraging various upstream account pools, offering pay-as-you-go access to users in mainland China.

Free quota negligible: daily check-in after 10 calls grants 5–20 quota (quota_per_unit=500000 ≈ $1 per 500K quota) → well under $0.01/day; most model_ratio=0 models are pay-per-call. Not quantifiable.

KIE.AI is an AI model API relay providing access to frontier models like Claude 3.5 Sonnet and GPT-4o. It operates on a pay-as-you-go basis and provides an integrated dashboard for API key management and usage tracking.

No public free-tier information found (researched 2026-08-29).

MNN AI (mnnai.ru) is a Russian AI API aggregator offering access to models like GPT-5.6 and Claude 5. It features a free entry tier with $1 monthly credits and strict rate limits (10 RPM), designed for low-volume testing and regional access.

No public free-tier information found in the source reference; treat free-tier availability as unverified rather than confirmed absent.

NavyAI (api.navy) is a unified AI API gateway providing access to 150+ models through flat-rate subscription plans with daily token quotas. It offers an OpenAI-compatible interface, 'Login with Navy' OAuth for BYOP workflows, and plans ranging from a basic free tier to high-volume 'Apex' tiers.

No public free-tier information found in the source reference; treat free-tier availability as unverified rather than confirmed absent.

OpenVecta provides an AI model API with an OpenAI-compatible endpoint. It focuses on simplicity and ease of use, with reports of a free tier or trial credits available for new users. Details were checked against the provider's own page at openvecta.com.

Free credits on signup for OpenAI-compatible inference across LLMs, embeddings, and reasoning models

TGhan (Xiao Yu Yun API) is a feature-rich AI API relay providing unified access to over 30 LLM providers including OpenAI, Claude, and Grok. It offers professional features like empty-response compensation, transparent usage logs, and multi-protocol support optimized for high stability.

Confirmed paid-only via direct /api/pricing check: 49 models, all paid (fixed-price quota_type=1 or per-token model_ratio>0); zero free-price entries. Top-up is via third-party redemption codes.

TheOldLLM (theoldllm.vercel.app) is a free, browser-based multi-model AI workspace for comparing leading models, chat, file/image analysis, web research, and study tools. Standard models need no account; frontier-tier models require a verified email, and rate limits apply.

Free chat interface; access/rate limits vary by account status, no USD credit.

Token Kiosk (gaib.ai) is an AI model router and aggregator part of the GAIB AI infrastructure capital platform. it provides access to various open and proprietary models, potentially linked to compute-backed financial assets.

No public free-tier information found in the source reference; treat free-tier availability as unverified rather than confirmed absent.

Zylo API provides a unified OpenAI-compatible gateway to models from Anthropic, OpenAI, Google, and more with zero token markup. Billing is based on base per-token rates deducted from a prepaid balance. A flat platform fee applies when adding credits.

No public free-tier information found in the source reference; treat free-tier availability as unverified rather than confirmed absent.

T3 Chat (t3.chat) is a multi-model chat client by T3 Tools, Inc. with model selection, web search, attachments and temporary chats, and its terms state that 'the Services are provided to you without charge up to certain usage limits, and usage in excess of these limits may require purchase of additional resources and the payment of fees'. The FAQ documents the usage meter as two buckets — a Base bucket that refills every 4 hours and an Overage bucket that refills on the monthly renewal date — using an illustrative example of 20 Base points plus 200 Overage points (220 total capacity). Price points themselves are not public: /pricing, /plans and /upgrade all return 404 and the terms direct users to the signed-in settings page for pricing details.

No dollar credit or numeric free allowance is published; the terms state only that the Services are 'provided to you without charge up to certain usage limits', with pricing on the signed-in settings page (t3.chat/terms-of-service, checked 2026-09-16).