The fastest way to start building is an API that doesn't gate its free tier behind a payment method. Every provider below was verified to require no credit card at signup for its free access — so there's no risk of a surprise charge when you cross a limit; you simply get rate-limited.
Watch two things as you choose: the per-minute / per-day rate limits (fine for prototypes, tight for production) and whether commercial use is allowed on the free tier. Both are in the table.
Top pick — Typhoon (SCB 10X)
Thai-language LLMs, OCR and speech via an OpenAI-compatible research API Details →
29 verified providers
| Provider | Free tier | Rate limits | Gotchas |
|---|---|---|---|
| Google Gemini API (AI Studio) | Gemini 2.5 Flash, 2.5 Flash-Lite, 2.5 Pro (limited), embeddings, TTS models | Per-model; Google no longer publishes the free-tier numbers in its public docs — they are shown only on the AI Studio rate-limit page after sign-in | no cardno phonecommercial OKOpenAI-compatible |
| Groq | Open-weight models (GPT-OSS, Qwen) plus Whisper, no credit card required | Free plan examples: openai/gpt-oss-120b, openai/gpt-oss-20b and qwen/qwen3.8-27b: 30 RPM/1K RPD/8K TPM/200K TPD; Whisper models: 20 RPM/2K RPD/7.2K audio seconds/hour and 28.8K/day; limits vary by model | no cardphone requiredcommercial OKOpenAI-compatible |
| OpenRouter | A rotating set of models with a :free suffix (16 on 2026-10-08; count fluctuates), single API across many providers | 20 req/min; 50 req/day under 10 credits purchased lifetime, 1000 req/day once 10+ credits purchased (one-time, not a subscription) | no cardno phonecommercial OKOpenAI-compatible |
| Cloudflare Workers AI | 10,000 Neurons/day, all account plans | 10,000 Neurons/day (free allocation). Per-task request limits: text generation 300 requests/min (models that require Workers Paid: 20 requests/min per model); text embeddings 3,000/min; speech recognition, text-to-image, translation, image-to-text 720/min | no cardno phonecommercial OKOpenAI-compatible |
| Cohere | Trial (evaluation) API keys covering chat, embed and rerank | 1,000 API calls/month total; 20 req/min chat; 2,000 inputs/min embed; 10 req/min rerank | no cardno phoneeval onlyOpenAI-compatible |
| Mistral (La Plateforme) | "Free mode" (default for new accounts): API keys with included monthly usage and the lowest limits, "intended for evaluation and prototyping" | Not published publicly; per-model requests/second, tokens/minute and tokens/month caps are shown only in-console (Admin Panel > API > Limits) | no cardphone requiredeval onlyOpenAI-compatible |
| HuggingFace | Free CPU Basic + ZeroGPU for Spaces; Inference Providers has no included credit on the Free plan (credits must be purchased) — $2.00/mo is included only on PRO/Team/Enterprise | No RPM/TPM published, only credit amounts | no cardOpenAI-compatible |
| SiliconFlow | China platform (siliconflow.cn): several models permanently free at ¥0 (e.g. Qwen/Qwen2.5-7B-Instruct, tencent/Hunyuan-MT-7B, BAAI embeddings and rerankers). The international platform (siliconflow.com) lists no $0 LLMs and gives $1 in free credits instead | Fixed per-model limits for free models; generic docs cite ranges of 1,000-10,000 RPM and 50,000-5,000,000 TPM depending on model tier — exact limits shown in-account | no cardphone requiredOpenAI-compatible |
| Z.ai (Zhipu AI / GLM) | GLM-4.5-Flash, GLM-4.7-Flash (text), and GLM-4.6V-Flash (vision) are officially listed as $0 cost (input, cached input, and output) on a permanent basis | Not specified with concrete RPM/TPM figures in public docs | no cardno phonecommercial OKOpenAI-compatible |
| OVHcloud AI Endpoints | Seven models are currently listed as Free: two Qwen3Guard moderation models, Stable Diffusion XL and four NVIDIA Riva TTS voices; access is available anonymously or with an API key tied to a Public Cloud project | Anonymous access: 2 requests/min per IP per model. Authenticated (API key): 400 requests/min per project per model. Exceeding either returns HTTP 429 | no cardOpenAI-compatible |
| Vercel AI Gateway | Free tier: a monthly free credit covering a subset of models (Free Tier eligible models) at lower rate limits | No numeric free-tier limit published: the free tier has a lower per-model limit than paid (HTTP 429 when exceeded); Vercel documents behavior, not numbers | no cardOpenAI-compatible |
| AI Horde | Free crowdsourced text & image generation; anonymous API key '0000000000' (no registration), or register to earn kudos for priority | Queue-based priority via kudos (no fixed quota); anonymous requests get lowest priority under load | no cardno phone |
| ModelScope (API-Inference) | Free API-Inference calls paid with daily 'Magicubes': 200/day for signing in + 50/day after linking an Alibaba Cloud account (do not roll over); calls cost ~0.5 / 1 / 2 Magicubes for lightweight / standard / flagship models | Bounded by the daily Magicubes: ~250/day from signing in and linking an Alibaba Cloud account, plus any earned by other actions (~125-500 calls depending on model tier); concurrency dynamically limited, single concurrency guaranteed | no cardeval onlyOpenAI-compatible |
| Pinecone Inference | Starter (free) plan: 5M embedding tokens/month per model (llama-text-embed-v2, multilingual-e5-large, pinecone-sparse-english-v0) and 500 rerank requests/month (bge-reranker-v2-m3; the rate-limits doc also lists pinecone-rerank-v0 at 500) | Starter: 5M embedding tokens/mo per model; 250K embedding tokens/min per model (passage); 500 rerank requests/mo and 60 rerank requests/min per model; 100 inference requests/s and 2,000/min per project | no card |
| Twelve Labs (Marengo Embed) | Free plan: the Marengo 3.5 Embed API (video, audio, image, text and document inputs) and the Pegasus Analyze API at no cost, plus 600 minutes (10 hours) of video indexing in total | Embed video/audio: 3,000 RPD, 25 RPM; embed text/image: 3,000 RPD, 600 RPM | no card |
| OCR.space | 25,000 conversions/month (Engine 1 & 2) plus 1,000 Engine 3 conversions/month; max 1 MB file, PDFs up to 3 pages | 500 requests per day per IP address | no cardno phonecommercial OK |
| LlamaParse (LlamaCloud) | Free plan: 10,000 credits/month (up to ~10,000 pages at the cheapest parse tier, as low as 1 credit/page) | 5 concurrent jobs; 1 project; 5 indexes on the free plan | no cardno phonecommercial OK |
| Moondream Cloud | $5/month usage credits in every workspace (Free plan) for the Moondream vision model — caption, query (VQA), detect, point | 2 requests/sec on the free tier (10 req/sec with ≥$10 account balance); usage bounded by the $5/month credit | no cardOpenAI-compatible |
| Speechify API | 500K characters/month TTS (hard cap; pauses until next month), catalog voices, streaming and SSML | Free: 3 concurrent requests, 1 request/s sustained (burst 10); hard monthly cap, no top-ups | no cardno phonecommercial OK |
| Hume AI (Octave TTS) | Free tier for Octave TTS and EVI; new accounts start with $20 in credits | Rate set by subscription tier, numbers not published; max 5,000 characters per utterance and 5 generations per request | no cardeval only |
| Unreal Speech | 250,000 characters/month TTS (~6 hours of audio) | No rate limit published in the current V8 API docs (legacy v7 docs listed 2 requests/second on Free). Per-request size: /stream up to 1,000 characters, /speech up to 3,000, /synthesisTasks up to 500,000 | no cardcommercial OK |
| ElevenLabs | 10,000 credits/month shared across Text-to-Speech, Speech-to-Text and more (~10 min TTS/month) | 2 concurrent requests on the Free plan | no cardno phoneeval only |
| Cartesia | 20,000 credits/month (~27 min of Sonic TTS or ~1h51 of Ink speech-to-text) | 2 concurrent TTS requests, 8 concurrent STT; 20,000 credits/month | no cardeval only |
| Fish Audio | App Free plan: 8,000 credits/month (~7 min, up to 500 characters per generation). API: the s2.1-pro-free TTS model is $0 through 2026-11-30 under fair-use limits (pay-as-you-go API, no subscription) | API: 5 concurrent requests (Starter tier, <$100 paid); s2.1-pro-free under unpublished fair-use limits. App Free plan: 500 characters per generation, 8,000 credits/month | no cardeval only |
| Nutrient (Data Extraction API) | 5,000 credits/month (renews; no rollover) — ~5,000 text-parse pages, fewer for OCR-heavy 'Understand'/'Agentic' parsing (9-18 credits/page) | 5,000 credits/month; Parse costs 1-18 credits/page by mode (Extract 7-24) | no card |
| Photoroom | 10 free production calls on the Remove Background API (one-time) plus 1,000 sandbox calls/month on the Image Editing API (watermarked) | 1,000 sandbox calls/month; 10 one-time production calls | no card |
| Veryfi | Free Forever plan: up to 100 documents/month — OCR plus structured data extraction (receipts, invoices, and 100+ document types) | 100 documents/month on the free plan | no cardcommercial OK |
| Datalab (Marker / Surya) | $20/month (work email) or $10/month (personal email) free usage allowance — OCR in 90+ languages, PDF-to-markdown, tables, forms and structured extraction | 10 requests/min and 5 concurrent requests on the free tier; per-page pricing (see datalab.to/pricing) | no cardno phone |
| Typhoon (SCB 10X) | Free to use research showcase API — all Typhoon models at $0 | typhoon-v2.5-30b-a3b-instruct: 5 requests/second, 200 requests/minute; typhoon-ocr: 2 requests/second, 20 requests/minute; typhoon-asr-realtime: 100 requests/minute | no cardno phonecommercial OKOpenAI-compatible |
FAQ
Can I use an LLM API for free without a credit card?
Yes. Providers such as Google Gemini, Groq, Cloudflare Workers AI and OpenRouter give a free tier with no card required — you are limited by rate, not billing, so you cannot be charged by surprise.
Will I be charged if I exceed the free limits?
No. On a no-card free tier you get rate-limited (HTTP 429) rather than billed. You would have to explicitly add a payment method before any spend is possible.
Are these free tiers okay for commercial use?
Some are, some are not — each row shows a commercial-use flag, confirmed against the provider’s own terms.