AI API Router Directory

TheB.AI is a versatile AI model aggregator and chatbot platform providing access to multiple frontier models (GPT-4, Claude 3, Gemini) via a unified API. It features a pay-as-you-go model and an OpenAI-compatible gateway.

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

TokenReply is a high-volume AI model aggregator offering access to advanced models (GPT-6 Astra, Claude 4.6, DeepSeek-V4 Pro) via an OpenAI-compatible gateway. It features pay-as-you-go billing with various tier-based model rates.

Free-tagged models have model- and campaign-specific daily limits; no fixed global free quota is published.

TokenRouter (tokenrouter.com) is an AI model API aggregator providing a unified gateway to multiple frontier LLMs. It exposes an OpenAI-compatible endpoint for integration with standard SDKs and tools.

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

UncloseAI (uncloseai.com) is a free, public-domain, open-source AI service offering OpenAI-compatible, drop-in endpoints with no cost: hermes.ai.unturf.com/v1 (general chat), qwen.ai.unturf.com/v1 (coding), and speech.ai.unturf.com/v1 (TTS). It currently serves Lorbus/Qwen3.6-27B-int4-AutoRound.

Completely free; no credit system.

UnoRouter is a unified AI API platform providing access to hundreds of models through a single intelligent endpoint. It is fully OpenAI-compatible and supports various clients including coding agents, character chat, and CLI tools. Features both pay-as-you-go and subscription plans with credit bonuses.

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

Void AI is an AI API aggregator compatible with the OpenAI SDK. It uses a credit-based billing system where model costs are calculated using multipliers (e.g., GPT-5.1 is 0.75, GPT-4o is 1.25). Offers both flat-rate plans and usage-based top-ups.

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

Volcengine is ByteDance's enterprise cloud platform. Its Ark (Huoshan Fangzhou) platform provides access to the Doubao (Doubao) model family and other high-performance LLMs. Supports OpenAI-compatible API calls and various billing plans including token-based monthly packages.

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

Weights & Biases Serverless Inference gives API and playground access to open-source LLMs hosted on CoreWeave, using an existing W&B account and no separate provider keys, with support for bringing your own LoRA weights for fine-tuned models. Token rates are listed per 1M tokens on the W&B pricing page: Meta Llama 3.1 8B at $0.22 input / $0.22 output, Meta Llama 3.3 70B at $0.71 / $0.71, OpenAI GPT OSS 120B at $0.03 / $0.17, NVIDIA Nemotron 3.5 Lightning at $0.07 / $0.20 with a $0.04 cache-hit rate, and DeepSeek V4-Pro at $1.15 / $2.55 with a $0.20 cache-hit rate. Inference spend is separate from platform subscriptions and can be capped with a monthly W&B Inference budget.

Weights & Biases states only that Inference includes 'Free credits for a limited time' on the Free plan and a $5/mo credit on Pro, with no dollar amount or expiry published for the free grant (checked 2026-09-16).

Writer is an enterprise generative AI platform featuring its own family of Palmyra models. It provides a consumption-based API for Palmyra X6, X5, and X4 models, optimized for business writing, data security, and precision. It does not natively use OpenAI-compatible request shapes.

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

X5Lab provides an OpenAI-compatible API for accessing various large models. It allows users to authenticate using an API key (format: x5-...) via standard OpenAI clients. Access is based on a pay-as-you-go model with a documented dashboard for key management.

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

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).

Yi is the model family by 01.AI, offering high-performance LLMs including Yi-Lightning and Yi-Large. The developer platform provides OpenAI-compatible API access with usage-based billing. It is optimized for both Chinese and English language tasks.

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

Yolo-Auto offers flat-rate LLM API pricing specifically designed for coding agents and high-context developer workflows. It provides an OpenAI-compatible endpoint with no per-token billing on paid plans, emphasizing predictable costs and private inference (no routine prompt logging).

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

ZeroLimitAI is an AI API aggregator offering free AI chat and a developer API with automatic model routing. It advertises a lifetime access plan for a one-time fee and a free tier for testing. The API is OpenAI-compatible.

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.

b.ai is an OpenAI-compatible LLM gateway (distinct from TheB.AI) focusing on unified multi-model access and privacy. It supports native crypto payments and anonymous access via the https://api.b.ai/v1 base URL.

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

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.