As of 2026-10-09, 50 free LLM API offers we track need no credit card at signup, by their recorded access and signup method. Read each row's caveats: our filter cannot, and a caveat can qualify the answer.
| Offer | Provider | Status | What it offers | Expiry | Verified | Source | Caveats |
|---|---|---|---|---|---|---|---|
| AI Gateway free tier | Vercel | available | A standing monthly free credit on AI Gateway for every Vercel team account, giving access to a subset of the model catalog (browsable at vercel.com/ai-gateway/models?freeTier=true) through one OpenAI… | no stated expiry | 2026-09-08 | source | AMOUNT NOW PUBLISHED FIRST-PARTY: Vercel's pricing page states "Monthly credit $5 /month included" in its free-tier column (checked 2026-10-08); when this row was last verified (2026-09-08) the page stated no figure. On… |
| AI21 Jamba free trial | AI21 | available | $10 in credits for 7 days on the foundation-model API, covering Jamba Mini and Jamba Large. No credit card required to start. | no stated expiry | 2026-09-16 | source | A 7-DAY TRIAL, NOT A STANDING FREE TIER — the clock starts at signup and the credits expire with it, so this is unsuitable for anything durable. Verbatim from the pricing page: "Free Trial — $10 credits for 7 days. No c… |
| Aion Labs free tier | Aion Labs | available | Free tier at $0 with a daily credit allowance covering the API. "No card required." The free tier ("Default on signup") allows 15 requests per minute, 20,000 tokens per minute and a 20,000 daily toke… | no stated expiry | 2026-10-06 | source | The dollar size of the daily credit allowance is not stated publicly. Which models the free tier may call is not stated publicly. The site header shows "Request Access" next to "Sign In", and whether sign-up is open or… |
| Apodex 1.1 Mini (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on apodex/apodex-1.1-mini:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 262,144 tokens; input: text. | no stated expiry | 2026-10-05 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. End rule: when OpenRouter stops listing this slug at $0, the row is retired to a dat… |
| Baseten new-account credits | Baseten | available | "new Baseten accounts come with credits so you can get to know the UI and experiment with deployments for free." The amount is not stated publicly. | no stated expiry | 2026-10-08 | source | The credit amount is not stated on the pricing page. |
| BazaarLink free gateway tier | BazaarLink | available | Free tier on an OpenAI-compatible gateway: 10 requests/minute and 60 weighted units/day per account (longer inputs use more units), shared across the free models, no credit card and no waitlist (“Sig… | no stated expiry | 2026-10-06 | source | SMALL, AND SMALLER THAN AGGREGATORS CLAIM — third-party listings report 130 req/day and imply the whole catalog is free; the provider's own page (read 2026-10-06) lists exactly TWO models with a free allowance (Qwen3.7… |
| Dots3-Note Preview (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on dots-studio/dots-3-note-preview:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 512,000 tokens; input: te… | expires 2026-12-31 | 2026-10-05 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. OpenRouter's model list gives an expiration_date of 2026-12-31; the row is retired t… |
| Fireworks $1 starter credit | Fireworks AI | available | A one-time $1 credit (Fireworks' billing FAQ: “What happens when I finish my $1 credit?”), usable on serverless models while it lasts. The pages read do not state when it is granted. | no stated expiry | 2026-10-06 | source | Account is suspended once the credit is spent unless a payment method is added — that much is first-party. UNSOURCED FIGURE REMOVED 2026-09-08: this row previously stated “600 req/min” at confidence “verified”. That num… |
| Gemini API free tier (AI Studio) | available | Ongoing free tier (not a trial). Free of charge on Gemini 3.8 / 3.7 / 3.6 / 3.5 Flash, 3.5 Flash-Lite, 3.1 Flash-Lite, 3 Flash Preview, 3.1 Flash TTS Preview, the 3.5 audio models (Transcribe, Transc… | no stated expiry | 2026-09-16 | source | free-tier prompts/outputs ARE used to train Google products; Pro models paid-only since Apr 2026; some region restrictions. CORRECTION 2026-09-16, WRONG IN BOTH DIRECTIONS. (1) This row listed Gemini 2.0 Flash as fr… | |
| Gemma 4 26B A4B (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on google/gemma-4-26b-a4b-it:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 262,144 tokens; input: image, t… | no stated expiry | 2026-10-05 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. End rule: when OpenRouter stops listing this slug at $0, the row is retired to a dat… |
| Gemma 4 31B (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on google/gemma-4-31b-it:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 262,144 tokens; input: image, text… | no stated expiry | 2026-10-05 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. End rule: when OpenRouter stops listing this slug at $0, the row is retired to a dat… |
| GLM Flash models ($0) | Z.ai (Zhipu) | available | GLM-4.7-Flash and GLM-4.5-Flash (text) and GLM-4.6V-Flash (vision) priced $0 for input, cached input, and output — ongoing, OpenAI-compatible endpoint | no stated expiry | 2026-10-06 | source | PRC-based provider — assume training use / PRC data rules for sensitive data; ~1 concurrent request reported |
| GroqCloud Free Plan | Groq | available | Persistent free tier, no card. The rate-limits page embeds its figures as two tier-labelled arrays (freeRows / devRows); these are the freeRows values, read 2026-09-27. Free-plan models: openai/gpt-o… | no stated expiry | 2026-09-27 | source | THREE MODELS LEFT THE FREE TIER between 2026-09-08 and 2026-09-27: qwen/qwen3.6-27b (30 RPM / 1K req-day) and groq/compound and compound-mini (30 RPM / 250 req-day / 70K TPM) are absent from freeRows on 2026-09-27; the… |
| Inference Providers monthly credits | Hugging Face | available | $0.10/month included credits on free accounts, $2.00/month on PRO, and $2.00 per seat for Team or Enterprise organizations (pooled across members), usable across 200+ models on eligible integrated pr… | no stated expiry | 2026-10-06 | source | $0.10/month is tiny (~1-2M tokens of cheap models); only applies to HF-routed requests — bringing your own provider key means the credits do not apply and the provider bills you directly. PRO/Team/Enterprise credits are… |
| Inkling (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on thinkingmachines/inkling:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 1,048,576 tokens; input: text, i… | no stated expiry | 2026-10-05 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. End rule: when OpenRouter stops listing this slug at $0, the row is retired to a dat… |
| Inkling Small (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on thinkingmachines/inkling-small:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 1,048,576 tokens; input: t… | no stated expiry | 2026-10-05 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. End rule: when OpenRouter stops listing this slug at $0, the row is retired to a dat… |
| Kilo AI Gateway free models (no key) | Kilo | available | Free models with no key and no account ("The gateway allows unauthenticated access for free models only.") — but "Auto Free may route your requests to providers that log prompts and outputs and use t… | no stated expiry | 2026-10-06 | source | DATA: "Auto Free may route your requests to providers that log prompts and outputs and use them to improve their services", and "Some free models require data collection to be allowed". Don't send anything confidential… |
| La Plateforme Free mode | Mistral | available | Free mode is the default state for new accounts. Mistral's pricing page lists the Free plan with “$10 /mo in API credits”, and its docs say Free mode “lets you create API keys and use included monthl… | no stated expiry | 2026-10-06 | source | PROVENANCE CORRECTION 2026-09-08: this row carried access: "phone-verification" at confidence: verified, and its own source_url does not support it. A full read of that page today returns ZERO occurrences of “phone”; al… |
| Laguna S 2.1 (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on poolside/laguna-s-2.1:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 262,144 tokens; input: text. | expires 2026-10-31 | 2026-10-05 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. OpenRouter's model list gives an expiration_date of 2026-10-31; the row is retired t… |
| Laguna XS 2.1 (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on poolside/laguna-xs-2.1:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 262,144 tokens; input: text. | expires 2026-10-31 | 2026-10-05 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. OpenRouter's model list gives an expiration_date of 2026-10-31; the row is retired t… |
| LFM2.5-2.6B (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on liquid/lfm-2.5-2.6b:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 65,536 tokens; input: text. | no stated expiry | 2026-10-05 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. End rule: when OpenRouter stops listing this slug at $0, the row is retired to a dat… |
| Ling 3.0 Flash Sante (free) on Novita | inclusionAI (via Novita AI) | available | Ling 3.0 Flash Sante (health) priced $0 for input and output on Novita: its pricing page lists it at "Free" / "Free", 256K context (read 2026-10-06). | no stated expiry | 2026-10-06 | source | A domain-specialised (health) model, not general-purpose chat. The same model is also $0 on OpenRouter as inclusionai/ling-3.0-flash-sante:free (afr-0073; still listed at prompt 0 and completion 0 on 2026-10-06). Its… |
| Ling 3.0 Flash Sante (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on inclusionai/ling-3.0-flash-sante:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 262,144 tokens; input: t… | no stated expiry | 2026-10-05 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. End rule: when OpenRouter stops listing this slug at $0, the row is retired to a dat… |
| Ling 3.1 Flash on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on inclusionai/ling-3.1-flash, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 262,144 tokens; input: text. | no stated expiry | 2026-10-08 | source | Not a :free variant: OpenRouter's model page says "The pricing shown on this page for Ling 3.1 Flash is zero, so you are not charged for prompt or completion tokens." No end date is stated for the $0 price. End rule: wh… |
| LLM7.io free API token | LLM7.io | available | A free API token: "Free token: 100,000 tokens per 24 hours", with rate limits per free token of 1 / 60 / 250 requests per second / minute / hour. "turbo models are fast models available with free A… | no stated expiry | 2026-10-06 | source | A token is required: "The OpenAI SDK requires an API token from dash.llm7.io", and issuing a token stores an email address, so this is NOT a no-signup API. Whether a card is needed for the free token is not stated publi… |
| Model Studio new-user free quota | Alibaba Cloud | available | Typically 1,000,000 tokens per eligible model (qwen-max, Qwen3-Coder-Plus, etc. each get their own quota, not transferable between models), valid 90 days from the later of activation, model release o… | no stated expiry | 2026-08-26 | source | International (Singapore) endpoint only; enable 'Free Quota Only' mode to prevent auto-billing after exhaustion; 90-day expiry |
| Nebius Builder Program credits | Nebius | available | On registration and email verification: USD $25 in Nebius Token Factory credits plus USD $25 in Tavily partner credits. | no stated expiry | 2026-09-16 | source | CREDITS EXPIRE 90 DAYS FROM ISSUANCE, verbatim: "All promotional credits are nonrefundable, nontransferable, and expire 90 days from the date of issuance. Expired credits are forfeited." Registration is limited to one a… |
| Nemotron 3 Nano Omni (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 256,000 tok… | no stated expiry | 2026-10-08 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. The model page carries NVIDIA's notice for the free endpoint: "For the free endpoint… |
| Nemotron 3 Super (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on nvidia/nemotron-3-super-120b-a12b:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 262,144 tokens; input:… | no stated expiry | 2026-10-05 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. End rule: when OpenRouter stops listing this slug at $0, the row is retired to a dat… |
| Nemotron 3 Ultra (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on nvidia/nemotron-3-ultra-550b-a55b:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 1,000,000 tokens; input… | no stated expiry | 2026-10-08 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. The model page carries NVIDIA's notice for the free endpoint: "For the free endpoint… |
| Nemotron 3.5 Content Safety (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on nvidia/nemotron-3.5-content-safety:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 128,000 tokens; input:… | no stated expiry | 2026-10-08 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. The model page says use of the free endpoint is logged: "The logged session data for… |
| Nemotron 3.5 Lightning (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on nvidia/nemotron-3.5-lightning:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 1,000,000 tokens; input: te… | no stated expiry | 2026-10-08 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. The model page carries NVIDIA's notice for the free endpoint: "For the free endpoint… |
| NIM / build.nvidia.com developer credits | NVIDIA | available | Free credits for NVIDIA-hosted NIM endpoints on build.nvidia.com (“anyone can sign up to the NVIDIA API Catalog for free credits”; free Developer Program membership gives “free access to NIM API endp… | no stated expiry | 2026-10-06 | source | PROVENANCE CORRECTION 2026-09-08 (second of three; see afr-0004 and afr-0016): this row carried access: "phone-verification" at confidence: verified and its source_url does not support it. That URL is a launch BLOG POST… |
| NLP Cloud $15 free credit | NLP Cloud | available | Pay-as-you-go plan: "Automatically get a $15 FREE credit". | no stated expiry | 2026-10-08 | source | The credit is on the pay-as-you-go plan, which invoices usage after the fact ("You are invoiced after the fact, based on usage."). Whether a payment card is needed to start is not stated on the page. |
| North Mini Code (free) on OpenRouter | OpenRouter | available | $0 prompt and $0 completion tokens on cohere/north-mini-code:free, as listed on openrouter.ai/api/v1/models (prompt 0, completion 0) when read 2026-10-05. Context 256,000 tokens; input: text. | no stated expiry | 2026-10-05 | source | Limits are OpenRouter's policy for :free variants (see afr-0010, and afr-0047 for the one-off $10 unlock); they are not restated here. End rule: when OpenRouter stops listing this slug at $0, the row is retired to a dat… |
| Nous Portal free plan (free models only) | Nous Research | available | Free plan: "Free $0 Free models only Standard rate limits $0 monthly credits". When read 2026-10-06, the portal's public catalog listed at $0.00/1M: inclusionAI Ling 3.1 Flash, Ling 3.0 Flash Fin, Li… | no stated expiry | 2026-10-06 | source | The rate-limit figures for "Standard rate limits" are not stated publicly. An account is needed: "All API access is authenticated by key or session" (portal.nousresearch.com/llms.txt). Whether a card is needed is not st… |
| Novita new-user trial voucher | Novita AI | available | New-user credit voucher for Novita's model APIs. Novita's own FAQ refers to “my $1 credit voucher” and says vouchers are revoked when “suspicious registration activity is detected”; there is no stand… | no stated expiry | 2026-10-06 | source | PROVENANCE FIX 2026-09-08: source_url was previously a third-party aggregator (mintlify.com/cheahjs/free-llm-api-resources/providers/trial/novita), which violates this catalog's absolute first-party provenance rule; rep… |
| OpenCode Zen free models | OpenCode | available | Six models served at no cost through one OpenAI-compatible endpoint (https://opencode.ai/zen/v1/chat/completions), listed as "Free" for input, output and cached read in the published price table: Big… | no stated expiry | 2026-09-16 | source | A ROTATING SET, NOT AN ENTITLEMENT — treat the model list as a dated snapshot, the same way afr-0010 treats OpenRouter's :free variants. The free models are offered during feedback-collection periods and the table says… |
| OpenRouter :free model variants | OpenRouter | available | Rotating set of :free model variants — 16 of 467 models carried a :free suffix at $0 prompt and completion when read from openrouter.ai/api/v1/models on 2026-10-08: NVIDIA Nemotron 3 (nano-omni-30b r… | no stated expiry | 2026-10-08 | source | ROSTER MOVED 2026-09-27 → 2026-10-08: 17 of 458 became 16 of 467. Gone: InclusionAI Ling 3.0 Flash Fin, Qwen 3.8 27B. New: Apodex 1.1 Mini. Earlier, 2026-09-16 → 2026-09-27: 20 of 443 became 17 of 458. Gone: InclusionAI… |
| OVHcloud AI Endpoints anonymous tier | OVHcloud | available | Anonymous, unauthenticated inference against the AI Endpoints model catalogue at 2 requests per minute, per IP and per model — no API key, no account, no signup of any kind. Verbatim: "Anonymous: 2 r… | no stated expiry | 2026-09-16 | source | 2 req/min is a trickle — this is for evaluation and fallback, not workload. Exceeding it returns 429; an API access key raises it to 400 req/min per PCI project per model. RATE-LIMITED PER IP, WHICH IS THE TRAP FOR AGEN… |
| Pollinations free Pollen from Quests | Pollinations.ai | available | "Free Pollen from Quests to start": Pollen is Pollinations' credit unit, spent across its text, image, audio and video API. The amount is not stated publicly. | no stated expiry | 2026-10-08 | source | Not keyless: the API docs say "All generation requests require an API key". How much Pollen a Quest gives is not stated publicly. |
| Ramp Router | Ramp | available | Free routing through 2026 on an OpenAI/Anthropic-compatible endpoint fronting 26+ models (Claude, GPT, Gemini, Kimi, DeepSeek, Qwen, GLM, Grok); you pay provider list price for the tokens themselves… | no stated expiry | 2026-08-23 | source | launched 2026-08-20, so the terms are new and unproven; free routing is time-boxed — “free through 2026” — and the $26 credit is “subject to offer terms” that the landing page does not state; US-only (“individual develo… |
| Replicate free runs on select models | Replicate | available | "You can run select models on Replicate for free, but after a bit you’ll be asked to set up billing." The amount is not stated publicly. | no stated expiry | 2026-10-08 | source | How much free use before billing is required is not stated publicly. "Some features are only available to customers with billing set up." |
| Requesty free plan (free models) | Requesty | available | Free plan at $0 for the platform on free models: "200 requests per day". "No credit card required". | no stated expiry | 2026-10-06 | source | The free model names are not stated publicly on the pricing page. Sign-up is implied ("Start free"), and its details are not stated. Paid use is "what your application spends, plus 5%". |
| Routeway Starter Free plan | Routeway | available | "Starter Free": free model IDs end in :free (e.g. deepseek-r1:free) and "cost $0.00". "200 requests per day", "Single concurrent request", "Shared low-priority queue", "Best-effort availability"… | no stated expiry | 2026-10-06 | source | PER-MINUTE LIMIT: ROUTEWAY'S OWN DOCS DISAGREE. The rate-limits page (docs.routeway.ai/getting-started/rate-limits.md) says "5 Requests Per Minute (RPM)". The FAQ (docs.routeway.ai/faq.md) says "20 requests/minute" and… |
| SambaNova Cloud Free Tier + $5 credit | SambaNova | available | No-card Free Tier: 20 req/min but only 20 requests/DAY, 200K tokens/day (DeepSeek-V3.1, Meta-Llama-3.3-70B-Instruct, gpt-oss-120b); plus $5 signup credit | no stated expiry | 2026-08-28 | source | 20 requests/day makes the no-card tier nearly unusable for agents; credit expiry unclear (30d-3mo reported). Re-read 2026-08-28: every figure above still matches the provider's rate-limit table unchanged. The no-card co… |
| Scaleway Generative APIs free tier | Scaleway | available | Free tier on Generative APIs: "1 million tokens and 60 minutes of audio transcription". Charges start "from token number 1,000,001". | no stated expiry | 2026-10-08 | source | Prices on the page are in euros, before tax. Whether the 1M tokens is one-time or recurring is not stated on the pricing page. Whether a payment card is needed to start is not stated on the page. |
| SiliconFlow $1 free credit | SiliconFlow | available | "$1 in free credits to get you started" on serverless, pay-per-token inference. | no stated expiry | 2026-10-08 | source | One-time starting credit; the page states no expiry. |
| Trial (evaluation) API keys | Cohere | available | Free trial keys, ongoing: 1,000 API calls/month total; Chat 20 req/min, Embed 2,000 inputs/min (image embed 5 inputs/min), Rerank 10 req/min | no stated expiry | 2026-08-27 | source | evaluation only - trial keys are 'not permitted to be used for production or commercial purposes' per cohere.com/pricing; that restriction is no longer stated on the rate-limits page at source_url, so read both. 1,000 c… |
| Workers AI free daily neurons | Cloudflare | available | 10,000 Neurons/day (~$0.11 of compute) at no charge, resetting 00:00 UTC — the same allocation on both the Workers Free and Workers Paid plans. Covers most of the catalog (Llama, DeepSeek distills, G… | no stated expiry | 2026-10-06 | source | 10K neurons is roughly 22K output tokens/day on deepseek-r1-distill-qwen-32b and 49K on llama-3.3-70b (our arithmetic from the page's neuron prices, not a Cloudflare figure); mostly smaller/quantized open models. NOT AL… |
Eligibility isn't recorded as a field. Rows are included on how you sign up, not on who may.
For comparison, 4 available LLM API offers in our catalog do ask for a payment card at signup:
| Offer | Provider | Status | What it offers | Expiry | Verified | Source | Caveats |
|---|---|---|---|---|---|---|---|
| Cerebras Inference free tier | Cerebras | available | Free Trial: $5 in credits granted to new accounts once a verified payment method is added, expiring 30 days later; while credits last, 5 req/min, 30K uncached tokens/min (90K total incl. cached), 1M… | no stated expiry | 2026-10-06 | source | NOT a renewing free tier — Cerebras' docs state it “doesn’t currently offer a no-cost tier that renews automatically” and require you to “add a verified payment method” to use the trial; credits expire 30 days after the… |
| Complimentary daily tokens (data-sharing) | OpenAI | available | Up to 1M tokens/day shared across the large-model group (gpt-5.6-sol, gpt-5.5, gpt-5.4, gpt-5.2, gpt-5.1, gpt-5.1-codex, gpt-5-codex, gpt-5, gpt-5-chat-latest, gpt-4.1, gpt-4o, o3, o1, o1-preview; 25… | no stated expiry | 2026-09-05 | source | NOT READABLE FROM OUR CLIENT SINCE 2026-10-08: the first-party help article returns 403 to our own client, and the 2026-09-05 read behind every figure here went through a third-party text-extraction route that is now re… |
| OpenRouter — $10 credits unlock 1000 free requests/day | OpenRouter | available | Purchasing at least 10 credits (~$10, one-off) raises the daily cap on :free model variants from 50 to 1000 requests/day. The per-minute limit is 20 RPM either way. The credits are yours to spend on… | no stated expiry | 2026-08-24 | source | Not free — it requires a real $10 purchase, which is why it is deal_type spend_unlock and not a free row; the underlying 50/day free tier (afr-0010) needs no spend. OpenRouter's docs state the threshold as "at least 10… |
| Ternary Bonsai 27B free serverless model | Together AI | available | Prism ML's Ternary Bonsai 27B served on Together AI's serverless infrastructure at $0.00/1M tokens for both input and output, with a 262,144-token context window. Reached through Together's ordinary… | limited-time, no date | 2026-10-09 | source | Zero price is confirmed on two first-party pages (the model page and together.ai/pricing) and the model is listed "Free / Free" on docs.together.ai/docs/serverless-models. Not usable without paying first: Together's bil… |
Does a provider have a free tier? A–Z · Machine-readable: ai-deals.json