AI API Router Directory

ChatAnywhere is a widely used free LLM relay. Users bind a GitHub account to get a free API key and access GPT-4o, Claude, and Gemini models through an OpenAI-compatible interface, optimized for access from mainland China.

GitHub-bound free key: 10,000 points/day with per-model caps (GPT-5/4o/4.1 5/day, DeepSeek 30/day, mini models 100/day, ~200 req/day total) ≈ $2/mo; personal non-commercial use only.

ChatAnywhere (GPT_API_free) is a widely used AI API relay providing unified access to global models including OpenAI, Claude, Gemini, and DeepSeek. It offers a GitHub-authorized free tier and low-cost paid access with endpoints optimized for users in mainland China and overseas.

Free keys, personal non-commercial only: ~200 req/day per IP&key (GPT-5/4o/4.1 5/day, DeepSeek 30/day, small models 200/day) ≈ $2/mo equivalent at typical token volumes.

Cohere's API splits keys into a free Trial tier (auto-created at sign-up: 1,000 API calls/month, 20 RPM on chat models, no commercial use) and an application-gated Production tier (500 RPM chat, pay-as-you-go, invoiced monthly or at $250 outstanding). Legacy Command models price from $0.30–$2.50 per 1M in; dedicated Model Vault instances run $4–$10/hr.

Trial key (auto-created at sign-up): 1,000 calls/month + 20 RPM chat (docs.cohere.com rate-limits, verified 2026-09-16); no production/commercial use. Dollar value is an estimate.

DuiAPI is a Chinese commercial-aggregator relay emphasizing compliant, ICP-registered access to official AI platforms. It supports Qwen, DeepSeek, and Kimi models through OpenAI and Anthropic compatible endpoints.

$2 signup trial credit reported.

ElevenLabs is a voice AI platform whose API covers text to speech, speech to text, sound effects, voice design, music and dubbing from one shared monthly credit pool. The Free plan costs $0 and includes 10,000 credits per month; paid plans start at Starter ($6/month, 30,000 credits) and rise to Creator ($22/month, 121,000 credits), Pro ($99/month, 600,000 credits), Scale ($299/month, 1,800,000 credits with 3 seats) and Business ($990/month, 6,000,000 credits with 10 seats). For V2 Multilingual models 1 text character equals 1 credit, while V2 Flash/Turbo English and V2.5 Flash/Turbo Multilingual cost 0.5 to 1 credit per character on API usage; speech to text is metered at 330 credits per minute.

Free plan is published as 10,000 credits per month at $0; valued at the Starter plan rate ($6 per 30,000 credits) this is about $2.00 per month, an estimate because ElevenLabs does not price the free allowance in USD (elevenlabs.io/pricing, checked 2026-09-16).

RouterPark is a directory and monitoring site for unofficial and free AI model relays. It catalogues third-party Claude and GPT proxies, providing a dashboard for status and latency while offering its own unified entry point for multiple 'free' upstreams.

Directory is free/login-free; any.routerpark.com proxy (ANTHROPIC_BASE_URL) signup credit: site advertises $20 but probes report ~$2 (+~$10 for posting). Conservative: $2; quota depends on third-party relays.

Super NB (api.super-nb.me) is a Chinese AI API gateway providing OpenAI-compatible access to global LLM providers. It aggregates GPT and Claude models, offering a simplified top-up and usage experience for developers in the region through a New-API based interface.

Nodeloc partner post (2026-08-19): Nodeloc users get $2 signup credit plus weekly lottery and first-top-up promos; e7ai post mentions a claimable $50 subscription voucher. Core remains a paid top-up relay.

Unity2.Ai is a commercial AI infrastructure provider offering seamless access to top Chinese and global AI models (Claude, GPT, Gemini, DeepSeek) via a single OpenAI-compatible API. Features self-developed cluster architecture for high concurrency and smart upstream scheduling. Supports Alipay and WeChat via Stripe.

$2 sign-up credit; Linux.do/V2EX campaign activity (replies, votes, per-100-floors) can add $10-$100 (promotional, unverified terms). Core is pay-as-you-go; no long-term free flagship quota.

OpenRouter is a unified, OpenAI-compatible API aggregating hundreds of model providers behind one key. Free model variants (:free IDs) are genuinely free with documented platform caps — 20 requests/min and 50/day for accounts that have purchased under 10 credits, 1,000/day once you've purchased 10+ — while paid variants have no platform request cap. Fallback routing, per-key credit caps, and BYOK are built in.

:free models cost $0, no card; 20 req/min; 50 :free req/day with <10 credits, 1000/day after buying $10+ credits (verified FAQ; failed reqs count). ~$1.5/mo equivalent at 50 req/day, ~1K tokens/call.

Hvoy AI is a specialized diagnostic and directory site for third-party AI API gateways. It performs continuous latency, uptime, and model-adulteration testing to help developers benchmark and select relay providers. Mirrored at hvoyai.com.

The site is primarily a checker/comparison tool; minor perks: ~20 points on signup, ~10 points to claim one free token, ~20 points for sharing, plus an occasional ~5 CNY (≈$0.74) redeem code; it claims a small daily 'freebie' of reverse-proxied sonnet-4.6/gpt5.3 (e.g. ~50 sonnet4.6 calls/day), with no guaranteed quota or stability.

mx.236600.xyz is an anonymous commercial relay service on the New API framework. As of September 2026, the site is unreachable and appears to have ceased operations after advertising aggressive top-up multipliers and lottery schemes.

Almost no free tier — /api/pricing only lists GPT-5.4/5.5, codex-Pro and image models; core is pay-as-you-go via 'top up 1 RMB (≈$0.15) = $1 quota'. No public, sustained free quota.

APIPlus is a third-party AI API relay built on the New-API framework, reselling access to Claude, GPT, and Gemini. It offers a small registration credit and an intermittently available 'free channel' with deep discounts, primarily targeting the low-cost reseller market.

Grants ~$1 registration credit for new users.

Agnes AI, developed by Singapore-based Sapiens AI, is an omni-modal AI platform offering indefinitely free access to core text, image, and video models. It supports OpenAI-compatible API keys and tiered 'Token Plans' for production-level throughput.

Advertised as indefinitely free core-model API with rate/volume caps; signup probe hints ~$1 starter credit (counted). Free tier reportedly sufficient for individual developers and demos.

Bytez is an AI model hosting platform that offers an OpenAI-compatible API for a wide range of models. It provides $1 in free credits that refresh every 4 weeks and uses a low-cost pay-as-you-go pricing model.

$1 free credits, refreshes every 4 weeks

Electron Hub provides a unified API to 600+ models, including premium frontier models (GPT, Claude, Gemini). It offers weekly credit refills on both free and paid subscription plans, plus permanent top-ups.

$0.25 weekly credits on the Free plan.

FastRouter is a high-performance gateway for AI model routing, comparison, and operations. It supports 200+ models via an OpenAI-compatible API with intelligent cost optimization and failover. Details were checked against the provider's own page at fastrouter.ai.

Free credits included to build, test and explore.

Fireworks AI is a self-serve inference platform: per-token serverless (Standard/Priority/Fast tiers) with $1 in free credits and postpaid billing, fine-tuning (LoRA and full-param, priced per 1M training tokens), a shared-pool Serverless Training API, and on-demand GPUs from $8/hr (H100, from Sep 1 2026) to $20/hr (GB300).

Official pricing page: 'Get started with $1 in free credits' (confirmed 2026-09-16).

HyperAgent (hyperagent.com) — fleet-of-AI-agents platform (research, docs, sites, decks, video). Plans convert monthly price 1:1 into spendable credits (up to 45% bonus); agents draw on hosted LLMs (Claude, ChatGPT, Kimi, etc.). Unofficial browser/cookie integration.

Every dollar of plan price returns as credit (1 credit = $1 of model spend); higher tiers add 10-45% bonus. Pay-as-you-go discontinued Aug 2026; top-ups via credit blocks.

Hyperbolic (hyperbolic.xyz) is the API-specific endpoint for Hyperbolic's AI cloud. It provides serverless inference for over 25 open-source models through an OpenAI-compatible /v1 endpoint. The platform supports text, image, and audio generation with pay-as-you-go pricing.

~$1 trial credit for new users (DeepSeek V3, Llama 3.1 405B, Qwen); pay-as-you-go after it is used (Llama 405B ~$4/M, DeepSeek R1 ~$3/M tokens).

Nebius AI Studio is a European-based GPU cloud platform providing managed inference for top open-source LLMs like Llama 3.1 and DeepSeek R1. It leverages its own EU data centers to offer high-performance, privacy-compliant inference with transparent pay-as-you-go pricing tailored for both developers and enterprises.

AI Studio grants new accounts ~$1 one-time trial credit (startup/promo programs can grant far more); Nebius AI Cloud free-trial program suspended as of 2026-07-13; studio models otherwise pay-as-you-go.

Rev AI (rev.com API) offers machine transcription (Reverb/Reverb Turbo), translation, summarization and voice agents, plus human transcription. Pay-as-you-go API with free signup credits equivalent to 5 hours of Reverb ASR (usable on all products); volume-based pricing; enterprise options with dedicated account management.

Free credits equivalent to 5 hours of Reverb ASR (official pricing page). At Reverb's published rate of $0.20/hour (via pricing-page search snippet), 5h ≈ $1.00.

Venice (venice.ai) — privacy-focused web app (anonymous or zero-retention) for chat, image, video and audio, known for self-hosted open-weight models plus TEE-hosted closed models. Unofficial browser/cookie integration (merged into existing 'venice' row).

Credits are USD-denominated; Pro $18/mo → $1 credit, Pro+ $68/mo → $75 credit (10% bonus), Max $200/mo → $225 credit (12.5% bonus).

JuCodex is a Chinese-market AI relay specializing in coding models, reselling access to OpenAI's Codex and GPT-4 variants. It features a custom ratio system for billing and provides a small initial credit for new accounts to test compatibility with IDE extensions.

One-off new-user credit: 6 RMB (≈$0.89) on signup (QQ-email only), ratios as low as 0.15; only 1 free entry in /api/pricing, no sustained free quota, essentially pay-as-you-go.

DeepSeek's official API serves the current V4.1-Flash and V4-Pro models with 1M-token context and 384K max output, from $0.15/$0.60 per 1M in/out off-peak (Flash) — peak hours bill at 2x, cached input drops to $0.003/M. One key exposes both an OpenAI-compatible and an Anthropic-compatible endpoint, and sign-up grants a free token balance that is deducted before any top-up.

Free 'granted balance' of ~5M tokens at sign-up (deducted before top-ups per official billing rules); $0.70 is an estimate at V4-Flash off-peak rates.