Free AI Router · free LLM API radar | risk review of free AI API sites

// STATIONS 143 sites · page 2/6

Official (free tier)Up

platform.moonshot.cn

Source · 12britz/awesome-free-models

Overviewplatform.moonshot.cn is Moonshot AI's official Kimi open platform, providing an OpenAI-compatible HTTP API for the Kimi family of large models. New users can claim a RMB 15 trial voucher; the core business is pay-as-you-go.

Free quotaAfter phone-number verification, new users automatically receive a RMB 15 trial voucher credited to their balance, usable directly to offset API call costs; the voucher typically has a 30-day validity and cannot be used for the latest models such as K3. Once used up or expired, it converts to pay-as-you-go.

Free modelsmoonshot-v1-8k moonshot-v1-32k moonshot-v1-128k kimi-k2

See platform.moonshot.cn's free quota / risk review →platform.moonshot.cn

Official (free tier)Up

ovhcloud.com

Source · 12britz/awesome-free-models

OverviewOVHcloud (a long-established European cloud provider) offers AI Endpoints — an OpenAI-compatible inference API for open-weight models with anonymous and registered free rate-limited tiers.

Free quotaHas a free tier: call for free (rate-limited) with no API key (or an empty key); registered users get higher rate limits. Totals subject to change by policy.

Free modelsQwen Mistral Llama DeepSeek

See ovhcloud.com's free quota / risk review →ovhcloud.com

Free productUp

pollinations.ai

Source · 12britz/awesome-free-models

OverviewPollinations.AI is a Berlin-based open-source generative-AI platform offering a signup-free, OpenAI-compatible free API for text/image/audio, covering GPT-5 Mini/Nano, Gemini, DeepSeek, Qwen, Mistral, Grok, and more.

Free quotaBasic use needs no signup and no API key; a Pollen credit system was introduced (free tier ~1.5 Pollen/week), with some models/higher limits requiring an account or higher tier

Free modelsOpenAI GPT-5 (Mini/Nano/5.2)Google Gemini 3 Flash / 2.5 Flash Lite DeepSeek V3.2 Mistral Small 3.2 Qwen3 Coder xAI Grok（含 grok-reasoning）

See pollinations.ai's free quota / risk review →pollinations.ai

Commercial aggregatorUp

ai-gateway.vercel.sh

Source · for-the-zero/Free-LLM-Collection

OverviewVercel AI Gateway is Vercel's official AI model gateway, offering hundreds of text/image/video/speech models through an OpenAI-compatible API (ai-gateway.vercel.sh/v1). It bills at provider list prices with zero markup and includes $5 of free credit per team each month.

Free quota$5 of free credit per Vercel team per month (starts at the first request, refreshes every 30 days, no credit card), usable only on a subset of free-tier models with per-model rate limits (429 on overflow). Buying any credits moves you to the paid tier and permanently ends the monthly $5.

Free modelsnvidia/nemotron-3.5-lightning-free convaiinnovations/laya-free poolside/laguna-s-2.1-free reflection/beam openai/gpt-oss-120b google/gemini-2.5-flash+1

See ai-gateway.vercel.sh's free quota / risk review →ai-gateway.vercel.sh

Official (free tier)Up

chat.intern-ai.org.cn

Source · for-the-zero/Free-LLM-Collection

OverviewInternLM (Shanghai AI Laboratory) official open platform provides an OpenAI-compatible API with a monthly free token allowance for programmatic access to its in-house intern/InternVL model family.

Free quotaNew community users get roughly 1M input / 3M output tokens free per month; endpoint https://chat.intern-ai.org.cn/api/v1, rate limit ~10 RPM, keys valid for 6 months; monthly usage visible under API Usage in the console.

Free modelsintern-latest intern-s1 intern-s1-mini intern-s1-pro internvl3.5-latest

See chat.intern-ai.org.cn's free quota / risk review →chat.intern-ai.org.cn

Official (free tier)Up

inference.api.nscale.com

Source · mnfst/awesome-free-llm-apis

OverviewNscale is a British AI 'hyperscaler' (raised €936M Series B in 2025); its Serverless Inference offers an OpenAI-compatible API with a one-time $5 signup credit for new users.

Free quotaNew users get a one-time $5 free credit to explore the models; after that you add a card to buy more. The core is pay-as-you-go (e.g. GPT-OSS 120B ~$0.1 in / $0.4 out per 1M tokens), with no rate limits and no cold starts.

Free modelsgpt-oss-120b Llama 系列 DeepSeek 系列 Qwen 系列（按官方 Serverless 目录）

See inference.api.nscale.com's free quota / risk review →inference.api.nscale.com

Official (free tier)Up