AI API Router Directory

LLM.Kiwi is an AI model router offering access to various LLMs via an OpenAI-compatible endpoint. It provides a free tier with a rate limit of 40 requests per hour for specific high-resource models and higher limits for pro subscribers.

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

LLM7.io is an open-source AI API gateway providing unified access to leading models like GPT and DeepSeek. It stands out for its unique anonymous access tier, allowing developers to test models without registration, and a registration-based free tier with higher limits.

Free relay: ~30 RPM anonymous, rising to ~120 RPM with free token from token.llm7.io (20/min, 100/h sub-caps); base URL api.llm7.io/v1 with api_key 'unused'. No token quota published → no USD estimate.

LZJAPI is an obscure AI API provider (lzjapi.cloud) that was unreachable during research in September 2026. No official documentation, pricing, or model lists could be verified from the domain, which appears to be offline.

Domain does not resolve (DNS 'Name or service not known'); no active service. No free-tier information found and no useful search results.

Lambda sells NVIDIA GPU cloud rather than a token-metered API. Self-serve instance pricing is per GPU-hour: NVIDIA B200 SXM6 at $6.69, H100 SXM at $3.99, A100 SXM 80GB at $2.79, A100 SXM 40GB at $1.99, GH200 96GB at $2.29, A10 at $1.29, A6000 at $1.09 and Tesla V100 at $0.79, all plus applicable sales tax/VAT/GST. 1-Click Clusters scale from 16 to 2,000+ GPUs on 2-week-to-1-year terms at $8.87-$9.86 per GPU-hour for HGX B200 and $5.54-$6.16 for H100. Lambda's own Inference API is being retired: the official page states that "as the Inference API winds down" customers should continue by deploying and scaling models on NVIDIA GPU instances.

No free tier stated on official pages (checked 2026-09-16): lambda.ai/pricing lists only per-GPU-hour instance and cluster rates plus tax, with no trial credit or free allowance.

LaoZhang AI is an enterprise-grade AI API integration platform reselling over 200 models from OpenAI, Anthropic, and Google. It provides an OpenAI-compatible interface, invoice support for businesses, and a small signup credit ($0.05) for testing.

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

Leonardo AI offers a high-performance image generation API for creative workflows. It supports advanced features like text-to-image, image-to-image, upscaling, and motion generation, all accessible via a unified production-ready API.

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

Linkup: production web search API for AI — Search (sub-200ms to ~30s ranked results/answers), Fetch (clean markdown), Research (async deep reports), Tasks, Extract. 4,000 free queries; per-request pricing $0.001-$0.006 for search, $0.25-$2.50 for research; SOC 2 Type II on all tiers, ZDR on Enterprise; $5,000 startup credit program.

4,000 free queries; at $0.005-0.006/query that is ~$20-24 of value, but the free grant is a fixed query count (not credits) so left null for honesty.

Liquid AI develops Liquid Foundation Models (LFMs), a new class of efficient, hybrid AI models. The platform offers serverless inference for models like LFM-2.5-2.6B, which are free for use by companies with annual revenue under $10 million.

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

LiteRouter is an AI API aggregator that provides access to hundreds of models from various providers via a single OpenAI-compatible interface. It supports free models with specific daily limits and pay-as-you-go billing for premium variants.

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

LlamaGate could not be verified on any official domain as of 2026-09-16. The domain in this listing, llamagate.ai, does not resolve at all, and the alternative domain found in a third-party integration library, llamagate.dev, returns only a LiteSpeed web-server 404 on its root, /pricing, /docs and on api.llamagate.dev/v1/models - the host answers, but no product page, pricing page or API response is served. Because no vendor-owned page could be retrieved, this entry deliberately makes no pricing, model or free-tier claims; third-party descriptions of the product were not used as a source.

No free tier stated on official pages (checked 2026-09-16): llamagate.ai does not resolve and llamagate.dev returns 404 on root, /pricing, /docs and api.llamagate.dev/v1/models, so no free allowance or price could be verified.

Logfare is an AI API router providing serverless inference for a wide range of open-source models. It includes access to many free-to-use models from providers like Liquid, Cohere, and NVIDIA, managed through a unified API dashboard.

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

MNN AI (mnnai.ru) is a Russian AI API aggregator offering access to models like GPT-5.6 and Claude 5. It features a free entry tier with $1 monthly credits and strict rate limits (10 RPM), designed for low-volume testing and regional access.

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

Magnific (formerly Freepik) is a professional AI creative platform offering image, video, and audio generation and upscaling. Its API provides credit-based access to proprietary models like Nano Banana 2 and Seedream 5.0, with subscription tiers ranging from a limited free plan to professional unlimited tiers.

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

MakeLove NewAPI (Nianhua API) is an anonymously operated Chinese API relay on the New-API panel that aggregates various models with paid top-up packages as the primary business model. Details were checked against the provider's own page at newapi.makelove.cloud.

Free model entries remain (~13 per /api/pricing); affiliate posts advertise '$10 signup + daily check-in' but site announced removing new-user free credit; free models are the reliable free tier.

Maritalk (by Maritaca AI) is a Brazilian AI provider specializing in Portuguese language models (Sabiá family). It offers an OpenAI-compatible API with inference hosted in Brazil for data sovereignty, featuring a daily free tier for chat and competitive PAYG token rates for the Sabiá-4 flagship model.

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

MegaNova AI is a comprehensive AI API aggregator and infrastructure provider, offering access to 200+ models including GPT-5.6, Claude 4, and proprietary Manta models. It features a tiered free quota system based on account status and spend, plus OpenAI-compatible serverless and dedicated GPU endpoints.

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

Meta's developer site now fronts a single Meta Model API (documented at dev.meta.ai) covering Muse and Llama models: Muse Spark 1.3 for agentic and coding work, Muse Glimmer as an open-weight model for local agents, Muse Image, Muse Voice Transcribe, and the Llama 4 and Llama 3 families. The only unit prices published on the official pages that returned content are Muse Voice Transcribe at $0.18/hour for streaming transcription and Muse Image at $0.01/image; no per-million-token Llama pricing and no free-credit figure appeared there, and the llama.developer.meta.com documentation domain returned no fetchable content on 2026-09-16.

No free tier or credit is stated on the official Meta pages that returned content (checked 2026-09-16); the llama.developer.meta.com documentation domain returned no fetchable content, so no allowance is claimed.

Microsand AI is an AI infrastructure provider that appears to be transitioning or offline as of September 2026. Official domains return errors or lack public-facing documentation, with no verifiable pricing or model availability found.

Site unreachable at research time: TLS handshake via Cloudflare completes but no HTTP response on ports 80/443; searches found nothing on microsand.ai as an API provider.

MiniMax China (minimaxi.com) is the domestic-facing platform for MiniMax's foundation models. It mirrors the global platform's model offering and OpenAI-compatible API but optimizes for mainland China compliance and billing workflows.

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

MiniMax's open platform prices large language models per token with a published input-length threshold: MiniMax-M3 is $0.30 per 1M input tokens and $1.20 per 1M output tokens for prompts up to 512K input tokens, described as a permanent 50% discount off $0.60 / $2.40, and doubles to $0.60 / $2.40 above 512K. M2.7 is $0.30 / $1.20 with prompt-cache reads at $0.06 and writes at $0.375 per 1M tokens; a Priority service tier costs 1.5x standard. The same account also bills video, speech and image work separately, for example H3 video at $0.08 per second in 768P, speech-2.8-hd TTS at $100 per 1M characters and image-01 at $0.0035 per image.

No free tier or free credit stated on official pages (checked 2026-09-16); the documented entry points are prepaid Credits (1,000 credits = $1, packages from $5) and Token Plans from $22 per month.

Mixedbread AI is a specialized provider of knowledge-retrieval models and agents. Its platform offers an OpenAI-compatible API for its 'Toast' agent models, alongside managed search and indexing services billed by content tokens. It features a $5 one-time free credit for new users.

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

Mixlayer is an AI API router and aggregator (mixlayer.com) offering transparent pay-as-you-go pricing for frontier models like GLM-5.3 and Qwen 3.5. It provides a free tier for small models like Qwen 3.5 4B and dedicated GPU hosting (H100/H200) billed by the hour.

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

ModelScope (魔搭, modelscope.cn) is an open-source model and dataset community founded in June 2022 by the Institute for Intelligent Computing together with the CCF Open Source Development Committee, organised around 'Model-as-a-Service'. The platform publishes models, datasets, Studios (application display space), MCP and Skills listings, and maintains the ModelScope, Swift, EvalScope and ModelScope-Agent frameworks. Its stated free offering is platform credits: 'Sign up / Log in to get 200 Magicubes' plus 'Link Alibaba Cloud account, get 50 more daily', with Studios described as 'a free and flexible AI application display space'.

No cash value stated: the official home page says 'Sign up / Log in to get 200 Magicubes' and 'Link Alibaba Cloud account, get 50 more daily' (modelscope.cn, checked 2026-09-16); Magicubes have no published CNY or USD rate.

MonsterAPI (monsterapi.ai) was an AI compute and model deployment platform. The service permanently shuttered operations on June 30, 2026, and its domains are no longer active. Details were checked against the provider's own page at www.crunchbase.com.

No free tier — the source marks this service as deprecated/discontinued.