AI API Router Directory

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.

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.

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.

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).

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.

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.

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.

Muse Code is Meta's specialized AI coding environment and agent service, built on the Meta Model API. It provides a terminal-based interface for code generation and transformation, featuring both a monthly subscription plan for high usage and credit-based PAYG options via Muse Spark.

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

Naver CLOVA Studio is a hyperscale AI service platform using the HyperCLOVA X model. It provides APIs for text generation, chat, and specialized tuning, primarily serving the Korean language market via Naver Cloud Platform.

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

Nous Research is an AI research lab offering the Hermes family of models via the Nous Portal. It provides an OpenAI-compatible endpoint for pay-as-you-go inference with no complex configuration required.

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

Nube Cloud is a specialized inference provider focused on cutting costs for open-source models like GLM, DeepSeek, and Qwen. It offers a zero-data-retention policy and deeply optimized routing for lightning-fast latency.

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

OpenAI's API is per-token with no free tier: GPT-6 Astra $10/$50, GPT-5.6 Sol $4/$20 (promo through Nov 21, 2026), Terra $2/$12 and Luna $0.20/$1.20 per 1M in/out for standard context (<272K), with Batch at 50% off, cached-input pricing, and a +10% data-residency toggle. Images (GPT-Image-2.5) and voice (GPT-Live-1) carry separate token rates.

No free tier on the API (checked 2026-09-16). The consumer ChatGPT free plan is a separate product, not API access.

OpenAdapter is an AI model API providing access to models like DeepSeek, Qwen, and GLM through an OpenAI-compatible endpoint. It focuses on easy integration by allowing standard clients to switch base URLs.

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

PLaMo is a Japanese LLM platform developing the PLaMo 3.0 Prime flagship model. It offers an OpenAI-compatible API optimized for high-performance Japanese language processing at a very low cost. Details were checked against the provider's own page at plamo.preferredai.jp.

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

Poolside develops foundation models optimized for software engineering. Their API provides access to the Laguna series models (Laguna S, Laguna XS) with an emphasis on code generation and technical reasoning.

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

Predibase is an enterprise-grade low-code platform for fine-tuning and serving small language models. As of mid-2026, evidence suggests their managed public serving API has been discontinued or moved behind a private VPC-only model.

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

PublicAI is a decentralized AI data network and API gateway. It facilitates access to LLMs by leveraging a community-governed data infrastructure, offering an API platform for developers to integrate models with a focus on data transparency.

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