AI API Router Directory

BluesMinds is a primarily-paid AI relay reselling access to Claude and GPT at significant discounts. It offers a large free credit bonus ($500) for accounts linked to aged GitHub profiles, and provides free daily calls for specialized models like GPT-4.1.

Up to ~$500 in credits for aged GitHub accounts per community reports.

Agent Router is an open-source, public-welfare AI API aggregation platform designed to unify access to agents and MCP tools. It is 'forever free' for both users and developers, providing a discovery registry for skills (ClawHub) and a live A2A directory.

Offers $100-$200 free credit bonus for new accounts to bootstrap agent usage.

Amazon Bedrock is AWS's model-API layer: 18 provider brands (Anthropic, OpenAI, Meta, Mistral, DeepSeek, Google, NVIDIA, xAI, Qwen, Amazon Nova and more) behind one AWS account, priced per 1M tokens with a 50% batch discount, tiered cross-region pricing and reserved/provisioned capacity. Bedrock itself has no standing free tier — new AWS accounts get $100 in credits at sign-up plus up to $100 more over a 6-month free plan.

New AWS accounts: $100 credits at sign-up + up to $100 earned over the 6-month free plan (aws.amazon.com/free, verified 2026-09-16). Bedrock itself has no standing free tier.

token.sensenova.cn is the official Token Plan for SenseTime's SenseNova multimodal AI platform. During its public beta, it offers generous free quotas for models like SenseNova 6.8 Flash Lite and U1 Fast, suitable for complex office workflows.

Free public beta (extended to end of July): 1,500 calls/5h per model (verified: 60k points/5h on token-plan page); ~7,200 calls/day ~ $200/mo equivalent at ~1K tokens/call. Phone signup, up to 20 API keys.

LongCat is Meituan's large model API platform (longcat.chat/platform), offering OpenAI/Anthropic-compatible endpoints. During its public beta phase in 2026, it provides generous daily free token allowances for models including LongCat-Flash and LongCat-2.0, with a context window of 131K tokens.

Free during public beta: initial ~5M tokens/day (per API changelog), activity can raise it up to ~120M/day; ~$150/mo equivalent at blended $1/1M tokens. Phone signup, key in ~3 min; paid top-ups not yet supported.

Hajimi API (api.gemai.cc) is a Chinese third-party relay aggregation platform. It specializes in routing requests to Claude, Gemini, and GPT models through a unified OpenAI-compatible endpoint, primarily catering to users requiring simplified access to international models.

New users get 100 units of balance by default (community figure ~¥500 (≈$74.39)), QQ-email signup only; there is a daily check-in farming crowd; 'limited perk' zero-priced models can be delisted anytime.

AnyRouter is a third-party relay that forwards Claude Code and OpenAI Codex traffic through an Anthropic- and OpenAI-compatible endpoint at https://anyrouter.top. Registration is via GitHub or LinuxDO, and the official docs advertise a $50 free credit on signup with no credit card required, plus $50 for each side on a successful referral. Rates are expressed as billing multipliers rather than an open price list - the docs recommend Claude 4 Sonnet for routine work because it bills at one fifth of Claude 4 Opus. Dated notices track model availability (GPT 6 on 2026-09-05, GPT 5.5 on 2026-05-26) alongside a documented record of attacks, abuse-driven registration freezes and a one-day outage.

docs.anyrouter.top states the signup grant as $50 free credit with no credit card required, plus $50 for each party on a successful referral (registration notice on anyrouter.top, fetched 2026-09-16).

Groq runs LPU inference hardware tuned for raw tokens-per-second. The API offers a documented free developer tier — per-model rate limits such as 30 RPM / 1,000 RPD / 8K TPM on gpt-oss-120b — with full x-ratelimit-* header observability, and paid Developer plans that add Batch and Flex processing plus higher ceilings.

Community reported approximate monthly value of free tier rate limits for individual developers.

AeroLink (aerolink.lat) is a commercial AI API gateway and relay service that routes multiple coding assistants and automation tools through a single key. It offers tiered subscription plans with rolling usage windows and claims access to high-end models like Claude Opus 4.8.

Starter plan offers a 1-week free trial included in the promo.

Cerebras Inference offers ultra-fast AI inference powered by its Wafer-Scale Engine (WSE-3) technology, achieving record-breaking speeds up to 3000 tokens/s. The official API is OpenAI-compatible and features a generous free tier alongside professional pay-as-you-go access.

Free tier ≈1M tokens/day (resets UTC 00:00, no card, no waitlist) → ≈$30/mo blended at $1/1M; 8K context cap; RPM reported 5–30 by different sources. Paid dev tier from $10.

Modal is serverless compute for AI workloads rather than a token-billed model API: you pay per second for CPU, memory and GPU time (H100 SXM5 $0.001097/sec, B200 $0.001736/sec, CPU $0.0000131 per core per second) and never for idle resources. The Starter plan is $0 plus compute and includes $30 per month of free compute with 3 seats, 100 containers and 10 GPU concurrency; Team is $250 per month with $100 per month of free compute. Volumes include 1 TiB per month free, then $0.09/GiB per month.

Starter plan includes $30 per month of free compute, stated on the Modal pricing page (Team includes $100 per month on the $250 plan); academics can apply separately for up to $10,000 in credits.

Z.ai is Zhipu AI's international developer platform, offering access to the GLM (General Language Model) family. It provides a high-performance alternative to Western models, with the GLM-Flash series offered permanently for free to developers to encourage global adoption of its flagship reasoning models.

GLM Flash models (4.7/4.5 text, 4.6V vision) listed $0 on official pricing — ongoing free models, not trial credits; ~1 QPS and ~1K calls/day (third-party, unofficial) → ≈$30/mo blended. Flagship GLM-5.x paid.

Tokeness (tokeness.io) is an AI model aggregator providing access to 50+ frontier models via a standard, unified API protocol. It focuses on stability and security, relaying requests without retaining conversation data. It includes a referral program and free routing options.

New users get only ~¥0.5 (≈$0.07) trial credit at signup, after which calls require prepayment (deducted from balance); there is no public, sustained free allowance, so it is a paid aggregator.

xAI (founded by Elon Musk) offers the official API for the Grok series of LLMs. Known for leading benchmarks in coding and reasoning, the Grok-4.6 flagship model is available via an OpenAI-compatible API, featuring low-latency inference and high agentic tool-calling capabilities.

No permanent free tier; ~$25 promo credit on signup (30-day expiry, varies by region/promotion). $150/mo data-sharing credits still listed by 2026 guides despite mid-2025 end reports — rely on what the console shows.

Feifeimiao (api.feifeimiao.top) is a Chinese third-party relay service offering an OpenAI-compatible API gateway. Built on the New-API framework, it aggregates various models and focuses on providing access to tools like Codex and Claude Code for developers in the region.

$10 trial credit on signup; promotional $20 weekly-limited cards for new and existing users (weekly expiry). The core is paid subscriptions (Small ¥60 (≈$8.93)/30d ≈ $20/day, Medium ¥150 (≈$22.32)/30d ≈ $60/day).

Cun.ai is a commercial AI relay aggregator based on the New-API framework, providing access to GPT, Claude, and DeepSeek. It targets Chinese developers with localized payment methods and a substantial signup credit promotion.

Signup credit up to approx. $20.83 (RMB 140) with redemption codes.

Camel-Hub (api.camel-hub.com) is a commercial AI API relay aggregating 330+ models. It emphasizes prompt caching to reduce user costs and requires real-name verification (KYC) for full access. Free access is limited to tool-class models like Suno and Midjourney.

$20 credit granted after real-name verification.

Google AI Studio gives free API access to Gemini models — free input and output tokens under per-model rate limits, not a depleting credit. Current-generation Flash models (including Gemini 3.8 Flash) are free-tier eligible. Paid tiers unlock higher limits, context caching, the 50%-off Batch API, and the most advanced models on the same API; free-tier data is used by Google to improve its products, paid-tier data is not.

Estimated based on high free-tier rate limits (RPD) vs paid input/output rates for equivalent usage.

Lightning AI (LitAI) provides a unified gateway to frontier models through an OpenAI-compatible API. New users receive 40 million free tokens (approx. $15 in credits) to test models like Claude, GPT, and Gemini. Usage beyond the initial credit is billed as pay-as-you-go.

~30M free tokens per user per month (~15 credits = $15 value), no card required; credits refresh monthly and expire if unused; plus 1 free 4-CPU Studio and 10GB Drive.

NLP Cloud is an API platform offering pre-trained and custom models for summarization, classification, embeddings, ASR, speech synthesis and large language models such as GPT-OSS 120B, LLaMA 3.1 405B and ChatDolphin. Its pay-as-you-go plan has no fixed monthly cost and automatically grants a $15 free credit, then bills per request at $0.003 on CPU or $0.005 on GPU with token surcharges for the largest models. Published prepaid plans run from Starter at $29 per month (10 parallel requests) to the Large Language Models plan at $2,499 per month (50 parallel requests), with dedicated fine-tuning plans from $399 per month.

Official pricing page states that the pay-as-you-go plan automatically gives a $15 FREE credit with no fixed monthly cost (nlpcloud.com/pricing.html, checked 2026-09-16).

MonkeyAPI (monkeyapi.apimonkey.online) is an anonymous individual relay service built on the New API framework. In late 2026, the service operator reported penalties for violations and announced plans to migrate, significantly reducing quotas and referral benefits.

Previously offered registration credit and check-in/referral bonuses, but notices state it is 'cutting referral and registration quotas for cost control' and will adjust after migrating; no stable public free flagship quota.

AI21 Labs sells API access to its Jamba foundation models through AI21 Studio on usage-based pricing, with a self-serve free trial and a custom plan for volume. The free trial is published as $10 in credits for 7 days with no credit card required. Published pay-as-you-go rates are Jamba Mini at $0.2 per 1M input tokens and $0.4 per 1M output tokens, and Jamba Large at $2 per 1M input tokens and $8 per 1M output tokens. AI21 states that on Studio models an average token equals about 1 word or 6 characters of English text.

Official pricing page states a Free Trial of $10 credits for 7 days, no credit card needed (ai21.com/pricing, checked 2026-09-16).

Eden AI is a commercial AI aggregation gateway providing a single API to 500+ models. It features cost tracking, automatic fallback, and a unified format for LLMs, vision, and translation. Details were checked against the provider's own page at www.edenai.co.

$10 starter credit reported for new users.

FreeModel is a multi-model gateway that intelligently routes requests to the best-performing open models. It supports both OpenAI and Anthropic API formats and provides automatic model fallback and smart provider selection to optimize for quality.

Signup credits land instantly, no card. Community reports conflict: $10 signup credit (phone/Telegram verify) up to claims of ~$66/week (~$300 cumulative) - authenticity unconfirmed. Conservative: $10.