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 →
32 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 | Varies by model: 5-30 RPM and 15-1,000 RPD (e.g. 2.5 Pro: 5 RPM/100 RPD; 2.5 Flash: 10/250; 2.5 Flash-Lite: 15/1,000; embeddings: 100 RPD; TTS: 15 RPD) | no cardno phonecommercial OKOpenAI-compatible |
| Groq | Open-weight models (Llama, Qwen, GPT-OSS) plus Whisper, no credit card required | e.g. llama-3.1-8b-instant: 30 RPM/14.4K RPD/6K TPM/500K TPD; llama-3.3-70b-versatile: 30 RPM/1K RPD/12K TPM/100K TPD; qwen/qwen3.6-27b: 30 RPM/1K RPD/8K TPM/200K TPD; similar for GPT-OSS and Whisper models | no cardphone requiredcommercial OKOpenAI-compatible |
| OpenRouter | A rotating set of models with a :free suffix (~14 today; 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 | 30+ models: LLMs (Llama, Mistral, DeepSeek, Qwen...), embeddings, image, audio | 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) | "Restrictive" free tier explicitly for "try and explore" — official docs say to upgrade for "actual projects and production use" | Not published publicly; exact caps only visible in-console after login (admin.mistral.ai) | no cardphone requiredeval onlyOpenAI-compatible |
| HuggingFace | Free CPU Basic + ZeroGPU for Spaces; Inference Providers has a monthly credit ($0.10/mo on Free plan, $2.00/mo on PRO/Team/Enterprise) | No RPM/TPM published, only credit amounts | no cardOpenAI-compatible |
| SiliconFlow | Several models permanently free (e.g. Qwen2.5-7B-Instruct and others) at $0 cost, plus a $1 welcome credit for paid models | 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 |
| SambaNova Cloud | Rate-limited free tier (applies when no payment method is linked) across all models | Free Tier: 20 RPM / 20 RPD / 200,000 TPD across all models; Developer Tier (card required): 60-240 RPM depending on model | no cardcommercial OKOpenAI-compatible |
| Ollama Cloud | $0 Free plan: access to cloud-hosted open models (Qwen, GPT-OSS, DeepSeek, etc.) via API | Session limits reset every 5 hours and weekly limits every 7 days; 1 concurrent cloud model on the free plan (exact token caps not published) | no cardno phonecommercial OKOpenAI-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) | ~2,000 free API calls/day across open-weight models (Qwen3, DeepSeek, GLM, Llama, etc.) via API-Inference | ~2,000 calls/day; concurrency/QPS caps applied and dynamically adjusted | no cardeval onlyOpenAI-compatible |
| Pollinations.ai | Free hosted image models (Flux, Turbo, Stable Diffusion) via a simple GET URL; also text and audio. No signup required to start | Anonymous ~1 request / 15s; free registration (Seed tier) ~1 request / 5s | no cardno phone |
| Pinecone Inference | Starter (free) plan: 5M tokens/mo for embedding models (llama-text-embed-v2, multilingual-e5-large) and 500 requests/mo for the bge-reranker-v2-m3 rerank model | 5M embedding tokens/mo; 500 rerank requests/mo on Starter | no card |
| Twelve Labs (Marengo Embed) | Free plan: the Marengo Embed API for all input types (video, audio, image, text) at no cost, plus ~600 min indexing | 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 2,500 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 (~10,000 pages in balanced parse mode at 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 | Bounded by the $5/month credit | no cardOpenAI-compatible |
| Speechify API | 50,000 characters/month TTS (hard cap) + 60 min/month voice agents | 3 concurrent calls; hard cap pauses at the limit (no overages) | no cardno phonecommercial OK |
| Hume AI (Octave TTS) | 10,000 characters/month TTS (~10 minutes) on the Free plan | 15 requests per minute | no cardcommercial OK |
| Unreal Speech | 250,000 characters/month TTS (~6 hours of audio) | Tiered endpoints for different text lengths; specific caps not documented | no cardcommercial OK |
| ElevenLabs | 10,000 credits/month shared across Text-to-Speech, Speech-to-Text and more (~10 min TTS/month) | Concurrency tied to the Free plan (not numerically published) | 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 |
| LMNT | 15,000 characters/month of TTS, with unlimited voice clones | 15,000 characters/month | no cardeval only |
| Fish Audio | 8,000 credits/month (~7 min of generation, up to 500 characters per generation); TTS, STT and voice cloning | 500 characters per generation; 8,000 credits/month | no cardeval only |
| Unstructured | 15,000 pages/month, resets monthly — document parsing/OCR across 50+ file types (layout, tables, generative OCR enrichment) | 15,000 pages/month | no card |
| 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; per-page cost varies by parse mode (1-18 credits) | 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 |
| W&B Inference | $100/month of Serverless Inference credits on the Free plan (default spending cap; offer for a limited time) | No RPM/TPM published; default cap of $100/month on the Free tier; concurrency limits per project/user | no cardcommercial OKOpenAI-compatible |
| Typhoon (SCB 10X) | Free to use research showcase API — all Typhoon models at $0 | typhoon-asr-realtime: 100 reqs/minute (documented on the ASR page); LLM/OCR models: no published quotas (beta service) | 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.