AI API Router Directory

OnAllways (llm.onallways.top) is a 'subscription-to-API' relay that pools various AI subscription accounts (Claude, GPT) and redistributes them as API keys. It is anonymously run and targets users looking for low-cost access to restricted models.

Unknown: the site's subtitle is 'Subscription to API Conversion Platform', with payment/affiliate/risk-control enabled and traffic funneled to third-party card shop catfk.com; no clear public persistent free quota is visible.

OrcaRouter is an LLM gateway offering zero token markup and adaptive routing across 200+ models. It is OpenAI-compatible and supports both pay-as-you-go and subscription plans with a handful of free-tier models.

Free-forever 'Hacker' plan: only $0-priced -free models and orcarouter/free endpoint are genuinely free, limited by request rate; probe showed $0 auto-grant. '1B free tokens'/voucher promos lack verifiable terms.

Perplexity's API blends request and token pricing: Search API at $5 per 1,000 requests; Sonar at $1/$1 tokens plus a $5–$12 per-1K request fee that scales with search depth; and the new Agent API serving OpenAI, Anthropic, Google and xAI models at direct provider rates with no markup, plus per-invocation tool pricing (web_search $0.0025). Sonar is sunset after September 27, 2026 — the Agent API is the successor.

No free tier on the API (checked 2026-09-16). Consumer Pro/Max plan credits (35K bonus + 10K monthly) apply to the app, not the API.

Playhop is a web-based gaming platform offering a variety of casual games. It does not appear to provide a public AI model API or LLM routing service for developers. Details were checked against the provider's own page at playhop.com.

Not an AI API - Playhop is a free online browser-games portal (20,000+ browser games, no login). Mis-listed in this directory; no AI API or free credits apply.

Poe is Quora's multi-model chat product that aggregates GPT, Claude, Gemini, Grok, Kimi and image/video/audio bots behind one subscription and one points balance rather than separate provider plans. Official subscription plans are annual: $49.99/year ($4.17/month) for 10 thousand points per day, $199.99/year for 660 thousand points per month, $499.99/year for 1.65 million, $999.99/year for 3.3 million and $2,499.99/year for 8.25 million points per month, with an add-on rate of $30 per 1M points that subscribers can buy for API or one-off use. Non-paying users receive points daily that reset every 24 hours and never roll over; Poe's help centre states subscriptions start at $4.99/month.

Poe gives non-paying users daily compute points that reset every 24 hours, but no official page fetched states the daily quantity, and poe.com/pricing returns 404, so no dollar value is claimed (checked 2026-09-16).

RRRapi is a third-party AI API relay built on the New API (One API) framework. It provides an OpenAI-compatible endpoint that aggregates multiple upstream models, featuring a balance-based top-up model with Stripe integration for credits.

Operator's own routerpark listing title: '注册总共送110, 0.5倍率' — signup bonus totalling 110 in site credit, currency unspecified (~$15 if CNY). Claim unverified by users; otherwise a Stripe pay-as-you-go relay.

RenAI (renai.uno) is an OpenAI-compatible AI API gateway that aggregates multiple global and Chinese models, including OpenAI, Anthropic, Google, and DeepSeek. It operates on a balance top-up model and is designed for users needing high-compatibility access to a broad range of upstreams.

freeairouter: bonus/invite-code features disabled, no free quota seen — effectively a paid top-up relay (Claude/OpenAI compatible; veridrop median 96/100 quality).

StepFun's open platform exposes Step 3.7 Flash and Step 3.5 Flash reasoning models, a vision model and a full speech stack, priced per 1M tokens, per hour of audio or per 10,000 characters. Step 3.7 Flash is 1.35 CNY per 1M input tokens on a cache miss, 0.27 CNY cached input and 8.1 CNY output; Step 3.5 Flash is 0.7 / 0.14 / 2.1 CNY, and four audio preview models are marked limited-time free in the price table. Rate limits are tiered by cumulative top-up, from V0 with 5 concurrent requests, 10 RPM and 5,000,000 TPM at zero spend to V5 with 200,000 RPM at 10,000 CNY.

No numeric free grant is published on official pages (checked 2026-09-16); the billing doc confirms a gift-balance account is drawn down before paid balance but states no amount, while stepaudio-3-realtime-preview, stepaudio-3-chat-preview, stepaudio-3-gen-preview and stepaudio-3-music-preview are listed as limited-time free in the price table.

SupXH (api.supxh.xin) is a generic AI API relay service providing a direct connection endpoint for various LLMs. It functions as a third-party aggregator with a minimal web presence, primarily serving as a host for OpenAI-compatible client configurations.

Live new-api relay behind free.supxh.xin free (gongyi) station; community posts report signup bonus ~7,000-8,000 quota units (unit unclear, not USD) + ~2,000/day check-in credit. Not verifiable in USD.

Shawn AI (肖恩AI) is a community-driven API relay station aimed at roleplay and tavern users. It aggregates hundreds of models including Claude 4.7 and GPT-5.5, offering free daily points and signing bonuses. It features a transparent point-deduction system and recovery for failed generations.

Uses a 'points' system (5000 on signup, 1000-3000 daily check-in) which does not have a fixed USD conversion rate.

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.

Wuqiongyun is an anonymous Chinese AI API relay aggregating GPT, Claude, and Gemini models using the New-API panel. It specializes in reselling access with model-specific multipliers, often including 'anti-reverse' and 'kiro channel' model variants.

Directory listings (routerpark 2026-03, routerhub): invite registration quota + daily check-in credit, 600+ models; amount unpublished. Prior probe showed checkin_enabled=false — config may change.

Xiaolangwangyue (integrated with GetToken.dev) is an AI API aggregator platform offering highly discounted balance top-up plans and subscriptions for ChatGPT (GPT-6/5.6/5.4) and other models. It follows a 1:1 official rate deduction from a prepaid USD balance bought with CNY at significant discounts.

GetToken is a paid Codex API reseller (ChatGPT Pro 20x resources; balance plans from ¥0.15 per $1). 'First recharge offer' is a paid promo; dashboard has a 'Free trial quota' field but no public free-credit offer.

mimo.xiaomi.com is Xiaomi's MiMo model site, listing MiMo-V2.5-Pro, MiMo-V2.5, MiMo-V2.5-TTS and MiMo-V2.5-ASR alongside a web demo, API access, papers and blog posts. Paid access runs through the MiMo Platform Token Plan, priced in USD per month: Lite $5.28 (list $6), Standard $14.08 ($16), Pro $44 ($50) and Max $88 ($100), covering 49.2B to 984B credits with full V2.5 text, multimodal and speech model access and free TTS models as a limited-time offer. MiMo Code, Xiaomi's coding agent, is documented as startable with no login ('无需登录，开箱即用') and its provider doc points to an OpenAI-compatible endpoint at api.xiaomimimo.com/v1 with an Anthropic-compatible option at /anthropic.

No free credit grant stated: MiMo Code is documented as usable free without login and Token Plans include 'Free TTS Models - Limited time offer', but no USD credit amount is published (mimo.xiaomi.com/mimocode and platform.xiaomimimo.com/token-plan, checked 2026-09-16).

ZenMux is a commercial unified API gateway providing access to 100+ mainstream AI models. It features a unique 'LLM insurance' mechanism that compensates users for slow or failed requests. The platform aggregates models from official providers and authorized cloud partners.

Free tier: basic monitoring plus some free models; once ran limited-time free trials of Claude Opus 4.6 and similar; core is pay-as-you-go with Pro/Max/Ultra paid subscriptions. No quantifiable standing credit.

iFlyTek's Spark (星火) open platform sells its models through xinghuo.xfyun.cn in CNY per million tokens: the flagship Spark-X2.5 is listed at a limited-time 50% discount of 1.60 CNY per million input tokens, 6.00 CNY per million output tokens and 0.24 CNY per million cache-hit tokens. Spark X2 is quoted at 2–3 CNY per million tokens and Spark-X2-Flash at 1–2 CNY, while the small dense models Spark-X2.5-4B (limited-time free) and Spark-X2.5-1.7B (free) are offered at no cost. The same catalogue resells third-party open models such as GLM-5.2 (8 CNY in / 28 CNY out per million) and DeepSeek-V4-Flash (1 CNY in / 2 CNY out), alongside fine-tuning rates from 6 CNY per million tokens.

No cash credit: the platform states new users get 10,000 free voice interactions and 200,000 free tokens per Spark model ('每个模型20万tokens免费额度') on xinghuo.xfyun.cn/sparkapi; no CNY or USD credit figure is published (checked 2026-09-16).

spark-api-open.xf-yun.com is the OpenAI-compatible HTTP endpoint for iFlyTek's Spark (讯飞星火) LLM. It provides access to multimodal models via the iFlyTek Open Platform. A permanently free 'Lite' version is available for developers.

Spark Lite (model=lite) permanently free since May 2024: unlimited tokens, QPS caps only - unquantifiable; one-off token packs for other tiers (~2M tokens ~ $2, promo-dependent); real-name registration required.

xAI's API serves the Grok family — flagship grok-4.6 with 500K context at $2.00/$6.00 per 1M and configurable reasoning — plus Voice (agent/TTS/STT) and Imagine image/video generation, all in an OpenAI-compatible shape. X Search and Web Search are first-party server-side tools; free credits are promotional, not a published standing program.

No standing free-credit program published in xAI's docs (checked 2026-09-16). Promotional credits vary by account/region/campaign — confirm in the console at sign-up.