AI API Router Directory

Play.ht is an AI text-to-speech platform with 900+ ultra-realistic voices, 32+ languages, voice cloning, and a real-time voice generation API. Plans: Free (1,000 chars/mo, no API), Creator ($31.20/mo billed annually, ~3M chars/yr), Unlimited ($99/mo regular; API add-on billed separately), Enterprise custom. Note: the official pricing page is JS-rendered and could not be fully captured; details sourced from third-party pricing guides.

Free tier = 1,000 chars/month (third-party guide; official page not captured); too small to value reliably against current API rates, and sources conflict on exact current pricing — set to null rather than guess.

Playhop is a web-based gaming platform offering a variety of casual games. It does not appear to provide a public AI model API or LLM routing service for developers. Details were checked against the provider's own page at playhop.com.

Not an AI API - Playhop is a free online browser-games portal (20,000+ browser games, no login). Mis-listed in this directory; no AI API or free credits apply.

Poe is Quora's multi-model chat product that aggregates GPT, Claude, Gemini, Grok, Kimi and image/video/audio bots behind one subscription and one points balance rather than separate provider plans. Official subscription plans are annual: $49.99/year ($4.17/month) for 10 thousand points per day, $199.99/year for 660 thousand points per month, $499.99/year for 1.65 million, $999.99/year for 3.3 million and $2,499.99/year for 8.25 million points per month, with an add-on rate of $30 per 1M points that subscribers can buy for API or one-off use. Non-paying users receive points daily that reset every 24 hours and never roll over; Poe's help centre states subscriptions start at $4.99/month.

Poe gives non-paying users daily compute points that reset every 24 hours, but no official page fetched states the daily quantity, and poe.com/pricing returns 404, so no dollar value is claimed (checked 2026-09-16).

Poixe AI is a commercial AI API router and aggregator that provides a unified interface for multiple LLM upstreams. It features model-group specific rate limits and a dashboard for API key management, targeting developers seeking simplified access to global and Chinese models.

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

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.

Prox (Aiproxy) is a closed AI API relay based on New-API, restricted to users with OAuth access from the external forum dc.hhhl.cc. It offers Stripe integration for paid top-ups and primarily serves a private community with aggregated access to frontier models.

Unknown/almost none — password signup disabled (password_register_enabled=false), check-in disabled (checkin_enabled=false), admission only via dc.hhhl.cc OAuth with Stripe (unit_price=8); no evidence of public free quota.

Proxy-GLS Public (api-public.proxy-gls.de5.net) appears to be an internal or developer-facing API relay for the GLS Group (logistics). While primarily handling logistics data, research indicates the domain has been used as a proxy for internal AI tools and agentic workflows, though it is not a general-purpose public

No public free-tier information found (researched 2026-08-28).

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.

Qwen Cloud / Alibaba Cloud Model Studio is the API and model-marketplace side of Qwen, reachable internationally at qwencloud.com and in mainland China through Bailian at bailian.console.aliyun.com. The international marketplace page states that new users get 70M+ free tokens and advertises full-modality access from $6/month. Chinese-language Model Studio documentation states that activating Bailian for the first time automatically issues a newcomer free quota per model, usually 1,000,000 tokens, valid for 90 days and available only in the Beijing (cn-beijing) region.

Free grants are token allowances, not currency: 70M+ tokens for new users on the international Qwen Cloud marketplace, and typically 1,000,000 tokens per model (90 days, cn-beijing only) on Chinese Model Studio.

RRRapi is a third-party AI API relay built on the New API (One API) framework. It provides an OpenAI-compatible endpoint that aggregates multiple upstream models, featuring a balance-based top-up model with Stripe integration for credits.

Operator's own routerpark listing title: '注册总共送110, 0.5倍率' — signup bonus totalling 110 in site credit, currency unspecified (~$15 if CNY). Claim unverified by users; otherwise a Stripe pay-as-you-go relay.

Recraft bills its image and vector API in prepaid API Units sold at USD $1.00 per 1,000 units, making one unit equal $0.001. Recraft V4.1 raster generation costs $0.035 per image, V3 $0.04, V4 $0.04, V4 Pro $0.25 and V2 $0.022, while vector output costs more (V4.1 Vector $0.08, V3 Vector $0.08, V4.1 Pro Vector $0.30). Utility calls are metered per request - background removal and vectorization $0.01, erase region $0.002, crisp upscale $0.004, creative upscale $0.25. API Units are prepaid, non-cancellable, non-refundable and never expire.

A Free plan is documented on recraft.ai/pricing (images owned by Recraft, publicly visible, non-commercial) but no credit quantity or USD value is published, so none is set (checked 2026-09-16).

Regolo AI provides scalable serverless AI infrastructure with a focus on privacy and zero data retention. It serves popular open-source models (Llama, Mistral, Qwen) via an OpenAI-compatible API, offering monthly token capacity plans and a flexible free trial.

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

Reka AI develops natively multimodal foundation models (Spark, Edge, Flash, Core) capable of processing text, image, audio, and video. Their API offers high-performance inference with competitive usage-based pricing for both compact on-device models and large flagship models.

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

RenAI (renai.uno) is an OpenAI-compatible AI API gateway that aggregates multiple global and Chinese models, including OpenAI, Anthropic, Google, and DeepSeek. It operates on a balance top-up model and is designed for users needing high-compatibility access to a broad range of upstreams.

freeairouter: bonus/invite-code features disabled, no free quota seen — effectively a paid top-up relay (Claude/OpenAI compatible; veridrop median 96/100 quality).

Routeway is an AI model router and gateway that provides a unified Bearer-auth interface for multiple global and domestic models. It simplifies integration for developers by handling model-specific protocols and providing a consistent management dashboard for keys and usage.

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

Runway bills generative video, image and audio in credits, with consumption rates published per model. Free includes 125 one-time credits that do not expire plus 5GB storage; Standard is $12/month billed annually for 625 credits/month, Pro $28/month for 2,250 and Max $76/month for 9,500 with up to one month of rollover. Gen-4.5 costs 60 credits per 5-second clip, Gen-4 Image 8 credits per 1080p image and Gen-4 Image Turbo 2 credits. The developer API uses usage tiers 1-5 with monthly spend caps from $100 to $100,000, where tier 2 unlocks immediately after $50 purchased.

The Free plan is documented as 125 one-time credits that do not expire plus 5GB storage (runwayml.com/pricing); credits have no published USD conversion, so no dollar value is set (checked 2026-09-16).

SAP generative AI hub is model management and orchestration for enterprise AI inside SAP AI Core, giving developers one API across hosted SAP models and partner models such as Anthropic Claude Sonnet 4, Google Gemini 2.5 Pro and OpenAI GPT-5, with prompt lifecycle management, an experimentation playground, automated prompt optimisation and inference observability. SAP does not publish list prices for it: the official trial page states the 30-day basic trial, after which the service is bought through Pay-As-You-Go for SAP BTP or an Enterprise Agreement, with pricing details routed to the SAP Discovery Center service catalogue. A page footnote states that token and after-promotion optimisation costs apply.

SAP offers a 30-day basic trial of generative AI hub with no dollar credit value stated on the official trial or product pages; it is a time-boxed licence grant, not a cash allowance (checked 2026-09-16).

SEA-LION (Southeast Asian Languages In One Network) is a suite of LLMs specifically optimized for Southeast Asian languages and cultural contexts. The API platform allows developers to integrate these regional models into localized applications with easy Google-auth signup.

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

Segmind is a serverless AI platform providing access to a wide range of models via API, including image generation (Stable Diffusion, Flux), LLMs, and more. It offers a pay-as-you-go model with monthly credits included in paid plans. Access is configured via an API key created in the dashboard.

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

Snowflake Cortex AI runs LLMs, agents and search inside the Snowflake governance perimeter, exposed through SQL AI functions, Cortex Agents, Cortex Analyst and Cortex Search. It bills on a second credit type: AI Credits, priced at $2.00 per credit on demand globally and $2.20 regionally (Snowflake Service Consumption Table, effective 2026-09-09), on top of Platform Credits for warehouses. Published AI Credit rates per 1M tokens include llama3.1-8b at 0.11 in / 0.11 out, llama3.3-70b at 0.36 / 0.36, mistral-large2 at 1.00 / 3.00, and claude-sonnet-5 at 1.30 / 6.50 when invoked via Snowflake CoWork or Cortex Agents; Cortex Search is 6.3 AI Credits per GB per month of indexed data and Cortex Analyst is 67 Platform Credits per 1,000 messages.

Snowflake markets a free 'start for free' signup but no dollar credit amount or free Cortex allowance is stated on the official pricing page or consumption table (checked 2026-09-16).

Soniox (soniox.com) sells speech-to-text, text-to-speech and speech translation through REST and WebSocket APIs, billed by tokens rather than per minute. Official pricing works out to about $0.10 per hour for async file transcription and $0.12 per hour for real-time streaming, expressed as $1.50 per 1M input audio tokens (async) or $2.00 per 1M (real-time), with input and output text at $3.50–$4.00 per 1M tokens; TTS is $4.00 per 1M input text tokens and $21.50 per 1M output audio tokens, about $0.70 per hour of generated speech. Translation across 60+ languages, speaker diarization, language identification and smart formatting are bundled in the same call at no extra cost.

No free tier or credit grant stated on official pages (checked 2026-09-16; reviewed soniox.com/pricing, soniox.com/docs and the soniox.com home page).

Speka is a unified AI API gateway providing access to frontier models (DeepSeek, Nemotron, Llama) via a single API key. It uses a subscription model with monthly usage allowances and standard per-token overage rates.

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

StepFun's open platform exposes Step 3.7 Flash and Step 3.5 Flash reasoning models, a vision model and a full speech stack, priced per 1M tokens, per hour of audio or per 10,000 characters. Step 3.7 Flash is 1.35 CNY per 1M input tokens on a cache miss, 0.27 CNY cached input and 8.1 CNY output; Step 3.5 Flash is 0.7 / 0.14 / 2.1 CNY, and four audio preview models are marked limited-time free in the price table. Rate limits are tiered by cumulative top-up, from V0 with 5 concurrent requests, 10 RPM and 5,000,000 TPM at zero spend to V5 with 200,000 RPM at 10,000 CNY.

No numeric free grant is published on official pages (checked 2026-09-16); the billing doc confirms a gift-balance account is drawn down before paid balance but states no amount, while stepaudio-3-realtime-preview, stepaudio-3-chat-preview, stepaudio-3-gen-preview and stepaudio-3-music-preview are listed as limited-time free in the price table.