Galadriel was a decentralized AI inference platform. As of 2026, the service appears to be discontinued, with the primary API endpoint (api.galadriel.ai) no longer resolving. Details were checked against the provider's own page at galadriel.com.

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

Gemini Business / Enterprise (business.gemini.google) — Google's business edition of Gemini with agents, Workspace/Microsoft 365 connectors and no-code agent builder. Unofficial browser/cookie integration of a licensed business service.

Per-user subscription on top of a qualifying Workspace license; no per-token pricing published for the business edition.

Gemini (gemini.google.com) free web chat — Google AI plans. Unofficial browser/cookie integration forwarding to Google's hosted Gemini models.

A free tier is available; the exact credit value is not quantified.

GigaChat is an AI model series developed by Sberbank, optimized for the Russian language and multimodal tasks. It provides a robust API for developers featuring both chat and reasoning capabilities, primarily targeting the Russian AI ecosystem.

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

OAuth access — sign-in with your existing account. GitLab Duo OAuth is not configured. Register an OAuth application at https://gitlab.com/-/profile/applications with redirect URI http://localhost:20128/callback and scopes "ai_features read_user", the This entry is an access surface/agent — it routes to third-party models rather than hosting its own.

A free tier is available; the exact credit value is not quantified.

GitLab Duo (Duo Agent Platform) - code suggestions, Duo Chat and code review across GitLab Free/Premium/Ultimate tiers; Duo Agent Platform features are usage-based on GitLab Credits (free-tier Duo with Credits since 18.10, Duo Core in 18.0); selectable models include Claude Sonnet 4.5 / Haiku 4.5 (Anthropic via Vertex), Gemini 2.5 Flash (Vertex) and Codestral 25.01/25.08 (Fireworks); default codegen Claude Sonnet 4.6 (Vertex), default completion Codestral 25.08 (Fireworks).

GitLab Credits power Duo Agent Platform usage; USD value per credit not published in fetched sources.

Opengateway (by Gitlawb) is a pay-as-you-go inference gateway providing unified OpenAI- and Anthropic-compatible access to models from Xiaomi MiMo, Google, MiniMax, and Qwen. It features smart routing via 'model: auto' and a permanent free tier for Nemotron 3 Ultra.

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

GetGoAPI is an AI API aggregator that provides unified access to over 500 models, including GPT-6 and Claude 4.5. It offers a flat 20% discount compared to official provider pricing with no platform fees or monthly minimums.

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

Google Jules: asynchronous cloud coding agent (Gemini-powered, AIDA team) that clones your repo into a Cloud VM, plans and implements changes, runs tests, and opens PRs; integrations for GitHub issues/PRs, CLI, and a public API (developers.google.com/jules/api). Plans: free 'Jules' (15 tasks/day, 3 concurrent, Gemini 2.5 Pro), 'Jules in Pro' and 'Jules in Ultra' (100/300 tasks/day, 15/60 concurrent, Gemini 3 Pro access) delivered as benefits of Google AI Pro / Google AI Ultra subscriptions.

Free plan = 15 tasks/day (rolling 24h), 3 concurrent, Gemini 2.5 Pro per jules.google/docs/usage-limits; Google does not publish a per-task dollar value, so monthly value is left unquantified.

Google Programmable Search Engine (Custom Search JSON API): programmatic web/image search results from a configured Programmable Search Engine. 100 free queries/day, $5 per 1,000 additional queries up to 10k/day. IMPORTANT: service discontinues January 1, 2027 and is not available to new customers — legacy pricing applies only to existing customers.

Free tier is 100 queries/day ≈ 3,000/mo × $5/1k ≈ ~$15/mo equivalent if fully used, but the free allotment resets daily and is capped at 100/day; not a purchased credit grant, so left null.

Grok (grok.com) web app — free tier plus SuperGrok. Unofficial browser/cookie integration forwarding to xAI's hosted Grok models.

A free tier is available; the exact credit value is not quantified.

web-cookie access — wraps the provider web app (unofficial). Paste the full grok.com cookie line from DevTools → Application → Cookies. Include both `sso` and `sso-rw` (e.g. `sso=...; sso-rw=...`) — Grok's anti-bot rejects `sso` on its own. 7 models tracked (via OpenRouter catalog).

A free tier is available; the exact credit value is not quantified.

Hailuo / MiniMax (chat.minimax.io) — MiniMax's consumer chat product. Unofficial browser/cookie integration serving MiniMax models (M2/M3/H3).

A free tier is available; the exact credit value is not quantified.

Haiper AI is an advanced generative video platform offering text-to-video, image-to-video, and video-to-video capabilities. Its API provides programmatic access to Haiper Video 2.x and 1.5 models with support for multiple resolutions, billed per second of generated video.

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

HelixMind is an AI API router designed to manage and optimize costs across hundreds of LLMs through a single endpoint. It native speaks the OpenAI API format and features automatic model selection by price and task requirement, ensuring enterprise-grade reliability.

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

Helyx AI is a multi-model gateway providing access to 50+ frontier models like Claude 5 and GPT-4o. It features a unique 'three-stage waterfall' quota system including a large daily free claim, a permanent pool earned via referrals/reviews, and a paid credit balance.

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

Heroku AI is a suite of managed AI services on the Salesforce Heroku platform. It enables developers to integrate and scale AI features using vector databases and third-party AI add-ons. It focuses on simplifying the transition from prototype to production for AI applications.

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

Huancheng Public API is a high-concurrency AI model router based on the New-API framework. It aggregates multiple upstream providers including OpenAI, Anthropic, and Google, offering a stable and low-latency endpoint for Chinese and global developers with real-time usage monitoring.

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

web-cookie access — wraps the provider web app (unofficial). Paste the full Cookie header from huggingface.co/chat (DevTools → Network → /chat/conversation → Request Headers → Cookie). It should include hf-chat and may also include token / aws-waf-token. This entry is an access surface/agent — it routes to third-party models rather than hosting its own.

A free tier is available; the exact credit value is not quantified.

HvoyAI.com (formerly Hvoy.ai) is the primary domain for the Hvoy AI diagnostics platform. It provides API key testing tools, gateway rankings, and comparative performance data for AI relay providers across the global ecosystem.

No free LLM API of its own: /free-tokens page distributes third-party relay redemption codes/temp keys via points & daily lottery (~20 pts signup, ~10/redemption); quota, models, expiry set by third-party gateways.

IBM watsonx.ai Gateway provides managed access to foundation models from IBM and third parties. It offers an OpenAI-compatible endpoint and enterprise-grade tools for model governance and scaling. Access is available via pay-as-you-go billing per million tokens.

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

Ideogram is a specialized AI image generation platform offering a production-grade API. It supports text-to-image, remixing, and advanced editing features like layer separation (Layerize). The API uses a token-based system for both text and image modalities, compatible with standard integration patterns.

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

Inworld AI is a voice AI platform for interactive agents, combining TTS, STT, and LLM into a unified credit system for games and real-time voice agents. Monthly plans allocate credits usable across all products; higher tiers add volume discounts and higher limits. Detailed plan pricing is rendered dynamically on the pricing page (not captured).

Plan credit amounts and USD values are rendered by JavaScript on the pricing page and were not captured; no reliable USD quantification.

Jina AI (Foundation API) provides specialized AI models for search and RAG, including high-quality embeddings, reranking, and a Reader API that converts web content to LLM-friendly markdown. The Reader API is currently free for developers, while other APIs follow token-based usage billing.

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