Conol (conol.ai) — knowledge-base product with background research/notes agents. Web app forwards to OpenAI models via its model picker (e.g. GPT-6 Astra). Unofficial/experimental.

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

OAuth access — sign-in with your existing account. Cursor 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.

DeepAI bundles its image APIs into the DeepAI Pro subscription instead of publishing per-call API pricing. Free access is $0 with no account balance needed and only 'Limited' allowances across HD images, chat, music and video. Pro costs $7.49/month billed annually at $89.99 (or $9.99 monthly with the renewal rate fixed) and includes 500 HD images, 60 Genius images, 10 Super Genius 2K images, 1,750 chat messages, 25 seconds of HD video, 8 seconds of 2K Hollywood Mode, 100 songs and 12 Concierge tasks per month. Overages draw on a prepaid wallet at 1 cent per HD image, 8 cents per Genius image, 25 cents per Super Genius 2K image, 20 cents per second of HD video and 10 cents per song.

The Free plan is $0 with no account balance needed and only 'Limited' allowances (HD images, chat, music, video); no credit quantity or USD value is stated, and API access is bundled with DeepAI Pro (checked 2026-09-16).

DeepInfra is an OpenAI-compatible inference cloud for open-weight models, with per-token rates published on a single pricing page. Examples from that page: DeepSeek-V4-Flash-0731 at $0.06 per 1M input tokens ($0.015 cached) and $0.18 per 1M output; Qwen3.5-9B at $0.10/$0.15; DeepSeek-V3.2 at $0.26/$0.38; Kimi-K3 at $2.85 per 1M input and $14.25 per 1M output; embeddings from $0.005 per 1M input tokens. Models without fixed token rates are billed on execution time, and custom LLM deployments are billed per minute of GPU uptime across A100 ($0.89/GPU-hour) through B300 ($4.89/GPU-hour). There is no free credit: the pricing page states you must add a card or pre-pay before you can use the service.

No free tier stated on official pages (checked 2026-09-16): deepinfra.com/pricing states that you must add a card or pre-pay before using the service, with no starter credit offered.

OAuth access — sign-in with your existing account. Requires the Devin CLI binary. Run `devin auth login` to authenticate, or provide your WINDSURF_API_KEY. Install: https://cli.devin.ai 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.

no-auth access — no key or sign-in required. Authentication is owned by the official Devin CLI in its isolated bridge volume. 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.

Dola (dola.com) — ByteDance's international AI chat assistant (international Doubao) serving the Doubao Seed model family. Unofficial browser/cookie integration.

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

Duck.ai is DuckDuckGo's free, private AI chat (also surfaced at duckduckgo.com/duckchat). It requires no account and offers chat, voice, image, and search across models including OpenAI GPT (e.g., '5.6 Luna') and Claude.

Free anonymous chat; an 'Upgrade'/Pro option exists but pricing not quantified on fetched pages.

fal.ai runs a generative-media model API: 1,000+ endpoints across image, video, audio and 3D behind one queue-based HTTP interface, called with the same request/response shape from Python, JavaScript or raw HTTP. Pricing is per output rather than per token, as published on its pricing page: $0.03 per Seedream V4 image, $0.04 per Flux Kontext Pro image, $0.02 per megapixel for Qwen image, $0.05 per second of Wan 2.5 video, $0.07 per second of Kling 2.5 Turbo Pro and $0.40 per second of Veo 3 video. Dedicated GPU capacity is listed at $4.50/hr for H100 (as low as $1.89/hr), $4.50/hr for H200, $6.25/hr for B200 and $8.50/hr for B300. There is no free token allowance: fal runs on a prepaid credit balance that funds both model usage and the account's concurrency limit.

No free tier stated on official pages (checked 2026-09-16): fal.ai/pricing and the Model APIs pricing docs describe only prepaid credits, with no starter credit or free allowance.

Featherless AI provides serverless access to LLMs and agent runtimes. It offers subscription-based 'Chat' plans with unlimited tokens and credit-based 'Developer' plans for API usage. Details were checked against the provider's own page at featherless.ai.

Free tier available — no credit card required

Felo (felo.ai) is a free, no-signup multilingual AI search and creation platform for chat, web search, and content generation. It exposes frontier models (e.g., GPT-6 Astra) and offers a paid Pro tier for heavier usage.

Free no-signup tier; Pro subscription pricing not quantified on fetched pages.

Free.ai is an AI tool aggregator offering 477+ tools across chat, image, and video. It provides 30,000 free tokens daily for registered users and supports premium models like GPT-6 and Claude via paid plans. The platform features an in-browser IDE for deploying AI applications.

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

FreeInference (freeinference.org) is an OpenAI- and Anthropic-compatible inference API offering frontier open models free of charge to the research community, with no credit card required at signup. It is presented as built at Harvard SEAS (MadSys Lab) and lists NVIDIA and Harvard SEAS as sponsors. The quota is described only as a "generous quota for research and prototyping"; no numeric limit is published, and the /pricing and /limits paths both return 404. The site carries a banner warning that GLM, Minimax and Kimi will be discontinued on Oct 1, and on Aug 11, 2026 it announced that new account onboarding is paused because the service is at capacity.

No free tier stated on official pages (checked 2026-09-16): freeinference.org offers a free account with a "Generous quota for research and prototyping" but publishes no dollar or token figure, and freeinference.org/pricing returns 404.

Freebuff is a specialized AI API relay often associated with developer automation and coding tools. It provides programmatic access to high-end models for free or via community-shared keys, primarily aimed at script-based integration and tool builders.

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

FriendliAI is a high-performance AI inference platform specializing in serving frontier open-weight models like GLM, DeepSeek, and Llama with industry-leading speed. It offers serverless Model APIs, dedicated GPU endpoints, and on-premise containers.

Free tier for serverless inference — no credit card required

Zhipu AI's GLM platform (bigmodel.cn, also served at open.bigmodel.cn) sells model access per token in CNY and bundles agentic coding into a separate GLM Coding Plan. The official pricing page lists GLM-5.3 at 8 yuan per million input tokens, 2 yuan per million cached tokens and 28 yuan per million output tokens with a 1M-token context, and GLM-5.3-Flash at 0.8 / 0.23 / 2.8 yuan. New accounts receive 20 million free tokens on registration, and the text model GLM-4.7-Flash (200K context) and vision model GLM-4.6V-Flash are listed as free for input, output and cache. The GLM Coding Plan shows 118 yuan/month (Lite), 538 yuan/month (Pro) and 1078 yuan/month (Max), with discounted continuous-subscription prices of 94.4 / 430.4 / 862.4 yuan and quarterly billing at 8-fold and annual at 7-fold discounts.

Free grant is 20,000,000 GLM tokens for new registrations (tokens, not currency), stated on bigmodel.cn/pricing and bigmodel.cn/claude-code; GLM-4.7-Flash and GLM-4.6V-Flash are additionally free per token.

The Gemini app is free with a personal Google Account at 'standard limits'; Google's help centre states Gemini Apps use compute-based usage limits that refresh every 5 hours until a weekly limit is reached. Free accounts get a 32k-token context window and access to Gemini Flash-Lite, Flash and Pro models, while paid tiers raise limits (Google AI Plus 2x at $4.99/mo, AI Pro 4x at $19.99/mo, AI Ultra 5x or 20x at $99.99 and $199.99/mo) and lift the context window to 1M tokens on Pro and Ultra.

No monetary credit accompanies the free Gemini tier; Google states free access has 'standard limits' with a 32k-token context window, while paid Google AI plans are $4.99/mo (Plus), $19.99/mo (Pro) and from $99.99/mo (Ultra, 5x and 20x variants).

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.

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 is an asynchronous coding agent that clones a connected GitHub repository into a Google Cloud VM, presents a plan for approval, then returns a diff and pull request. The no-cost tier is stated as 15 tasks per day and 3 concurrent tasks, while Jules in Google AI Pro provides 100 tasks per day and 15 concurrent tasks and Jules in Google AI Ultra provides 300 tasks per day and 60 concurrent tasks. Jules is described as language agnostic but works best with JavaScript/TypeScript, Python, Go, Java and Rust projects.

The no-cost tier is stated on jules.google as 15 tasks per day and 3 concurrent tasks, described in Google's blog as 'Introductory access to Jules'; no USD credit is published and daily task caps do not convert to a dollar amount.

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 Build is xAI's terminal coding agent, installed from x.ai/cli and documented at docs.x.ai/build, running on grok-4.6. The official CLI page states the tool is available to try for free and the client is open source, while xAI's developer pricing page meters every request at API token rates: grok-4.6 costs $2.00 per million input tokens, $0.50 per million cached input tokens and $6.00 per million output tokens for prompts under 200k tokens, rising to $4.00 / $1.00 / $12.00 once a request reaches the long-context threshold.

No numeric free allowance is stated - x.ai/cli says only that Grok Build is available to try for free (checked 2026-09-16).

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.