{
 "name": "Free LLM API Tiers (2026): Limits Verified Daily",
 "source": "https://gravity.fast/data/free-llm-api-tiers/",
 "license": "CC BY 4.0",
 "updated": "2026-10-04",
 "rows": [
  {
   "provider": "Google AI Studio (Gemini API)",
   "plan": "Free tier",
   "type": "Standing free tier",
   "free_limits": "Free of charge on the listed models. Google no longer publishes free-tier requests or tokens per minute or day in its docs; your project's limits are shown in AI Studio. Requests per day reset at midnight Pacific.",
   "requests_per_minute": "",
   "requests_per_day": "",
   "tokens_per_day": "",
   "models": "Gemini 3.8, 3.7, 3.6 and 3.5 Flash, 3.5 and 3.1 Flash-Lite, 2.5 Pro, 2.5 Flash, 2.5 Flash-Lite, Gemma 4. Gemini 3.1 Pro is not free.",
   "card_needed": "No billing account (inferred from the tier table)",
   "caveats": "Free-tier content is used to improve Google's products. Grounding with Google Search is not available on the free tier.",
   "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "verified": "2026-10-04",
   "wording_check": "matched 2026-10-04"
  },
  {
   "provider": "Groq",
   "plan": "Free plan",
   "type": "Standing free tier",
   "free_limits": "gpt-oss-120b, gpt-oss-20b and Qwen3.8 27B: 30 requests a minute, 1,000 a day, 8,000 tokens a minute, 200,000 tokens a day each.",
   "requests_per_minute": "30",
   "requests_per_day": "1000",
   "tokens_per_day": "200000",
   "models": "gpt-oss-120b, gpt-oss-20b, Qwen3.8 27B (plus Whisper speech-to-text)",
   "card_needed": "Not stated",
   "caveats": "Groq calls the table a high-level summary with possible exceptions; your organisation's exact limits are on the console Limits page.",
   "source_url": "https://console.groq.com/docs/rate-limits",
   "verified": "2026-10-04",
   "wording_check": "matched 2026-10-04"
  },
  {
   "provider": "OpenRouter",
   "plan": "Free model variants (IDs ending in :free)",
   "type": "Standing free tier",
   "free_limits": "20 requests a minute. 50 requests a day if you have bought less than 10 credits in total, 1,000 a day once you have bought 10 or more.",
   "requests_per_minute": "20",
   "requests_per_day": "50",
   "tokens_per_day": "",
   "models": "Every model variant whose ID ends in :free; see the model table below",
   "card_needed": "Not stated; buying 10 credits lifts the daily cap to 1,000",
   "caveats": "A negative balance can cause errors even on free models. Free variants can be added or withdrawn by the model host at any time.",
   "source_url": "https://openrouter.ai/docs/api-reference/limits",
   "verified": "2026-10-04",
   "wording_check": "matched 2026-10-04"
  },
  {
   "provider": "Cloudflare Workers AI",
   "plan": "Workers Free allocation",
   "type": "Standing free tier",
   "free_limits": "10,000 Neurons a day free (Neurons are Cloudflare's compute unit, converted to tokens per model on the pricing page). Text generation is capped at 300 requests a minute on every plan.",
   "requests_per_minute": "300",
   "requests_per_day": "",
   "tokens_per_day": "",
   "models": "Workers AI catalog, except models Cloudflare marks as needing a paid plan (Kimi K2.6 and K2.7 Code, GLM 5.2 and 5.3, DeepSeek V4 among them)",
   "card_needed": "Not stated",
   "caveats": "Above the daily allocation you need Workers Paid at $0.011 per 1,000 Neurons.",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "verified": "2026-10-04",
   "wording_check": "matched 2026-10-04"
  },
  {
   "provider": "Mistral AI",
   "plan": "Free plan",
   "type": "Monthly free credit",
   "free_limits": "$10 a month in API credits. Rate limits apply but are shown only in the console.",
   "requests_per_minute": "",
   "requests_per_day": "",
   "tokens_per_day": "",
   "models": "Mistral's models through Studio and the API",
   "card_needed": "No card required (per Mistral's docs)",
   "caveats": "The free plan's model-training setting could not be read from the public pricing table.",
   "source_url": "https://mistral.ai/pricing",
   "verified": "2026-10-04",
   "wording_check": "matched 2026-10-04"
  },
  {
   "provider": "Cohere",
   "plan": "Trial key",
   "type": "Standing free tier",
   "free_limits": "1,000 API calls a month in total; chat is limited to 20 requests a minute per model.",
   "requests_per_minute": "20",
   "requests_per_day": "",
   "tokens_per_day": "",
   "models": "Command A family, Command R+, Command R, Command R7B, North Mini Code",
   "card_needed": "Not stated",
   "caveats": "Trial keys are for evaluation; production use needs a paid production key.",
   "source_url": "https://docs.cohere.com/docs/rate-limits",
   "verified": "2026-10-04",
   "wording_check": "matched 2026-10-04"
  },
  {
   "provider": "SambaNova Cloud",
   "plan": "Free tier",
   "type": "Standing free tier",
   "free_limits": "20 requests a minute, 20 a day and 200,000 tokens a day per model.",
   "requests_per_minute": "20",
   "requests_per_day": "20",
   "tokens_per_day": "200000",
   "models": "DeepSeek-V3.1, Llama 3.3 70B, gpt-oss-120b; DeepSeek-V3.2 and Gemma 4 31B in preview",
   "card_needed": "No payment method (the free tier applies until one is linked)",
   "caveats": "Preview models are for evaluation only, not production, and can be removed at short notice.",
   "source_url": "https://docs.sambanova.ai/docs/en/models/rate-limits",
   "verified": "2026-10-04",
   "wording_check": "matched 2026-10-04"
  },
  {
   "provider": "Hugging Face Inference Providers",
   "plan": "Free account monthly credits",
   "type": "Monthly free credit",
   "free_limits": "$0.10 of credit a month, which Hugging Face says is subject to change. PRO accounts get $2.00.",
   "requests_per_minute": "",
   "requests_per_day": "",
   "tokens_per_day": "",
   "models": "Models served through Inference Providers when requests are routed by Hugging Face",
   "card_needed": "Not stated",
   "caveats": "Credits do not apply when you use your own key for a provider.",
   "source_url": "https://huggingface.co/docs/inference-providers/pricing",
   "verified": "2026-10-04",
   "wording_check": "matched 2026-10-04"
  },
  {
   "provider": "Alibaba Cloud Model Studio (international)",
   "plan": "New-user free quota",
   "type": "One-time free quota",
   "free_limits": "Typically 1,000,000 tokens per model, input and output combined, valid for 90 days from activation.",
   "requests_per_minute": "",
   "requests_per_day": "",
   "tokens_per_day": "",
   "models": "Qwen models in the Singapore region (each model and dated snapshot has its own quota)",
   "card_needed": "Not stated",
   "caveats": "Usage is billed automatically after the quota runs out unless the Free Quota Only switch is turned on (it is off by default). Real-time inference only.",
   "source_url": "https://www.alibabacloud.com/help/en/model-studio/new-free-quota",
   "verified": "2026-10-04",
   "wording_check": "matched 2026-10-04"
  },
  {
   "provider": "Scaleway Generative APIs",
   "plan": "Free tier (serverless)",
   "type": "One-time free quota",
   "free_limits": "Up to 1,000,000 tokens and 60 minutes of audio transcription at no cost, applied to the most expensive tokens first. The FAQ does not say whether this is one-time or monthly.",
   "requests_per_minute": "",
   "requests_per_day": "",
   "tokens_per_day": "",
   "models": "Serverless models billed by tokens",
   "card_needed": "Not stated",
   "caveats": "Read from Scaleway's own documentation source because the live docs page blocked automated reads on the verification date.",
   "source_url": "https://www.scaleway.com/en/docs/generative-apis/faq/",
   "verified": "2026-10-04",
   "wording_check": "matched 2026-10-04"
  },
  {
   "provider": "NVIDIA API Catalog",
   "plan": "Free trial credits (NVIDIA Developer Program)",
   "type": "Trial",
   "free_limits": "Free credits for prototyping. NVIDIA's docs state no credit amount and no rate limit.",
   "requests_per_minute": "",
   "requests_per_day": "",
   "tokens_per_day": "",
   "models": "NVIDIA-hosted NIM endpoints on build.nvidia.com",
   "card_needed": "Not stated",
   "caveats": "Positioned for prototyping, not production.",
   "source_url": "https://docs.api.nvidia.com/nim/docs/faq",
   "verified": "2026-10-04",
   "wording_check": "matched 2026-10-04"
  },
  {
   "provider": "Cerebras",
   "plan": "Free trial",
   "type": "Trial",
   "free_limits": "$5 of credit that expires 30 days after it is granted. 5 requests a minute, 30,000 uncached tokens a minute, 1,000,000 tokens a day per model.",
   "requests_per_minute": "5",
   "requests_per_day": "",
   "tokens_per_day": "1000000",
   "models": "gpt-oss-120b, Qwen 3.8 27B",
   "card_needed": "Card required (verified payment method)",
   "caveats": "Cerebras's own FAQ answers \"Is there a permanently free tier?\" with no.",
   "source_url": "https://inference-docs.cerebras.ai/support/rate-limits",
   "verified": "2026-10-04",
   "wording_check": "matched 2026-10-04"
  }
 ]
}