API AI yang bisa
dipake gratis
Free tier & free credits API LLM — di-aggregate otomatis dari sumber komunitas. Tiap provider nampilin model, context window, rate limit & modality apa adanya dari sumber.
25 provider · 330 model gratisDirektori provider
Last update 30 Agustus 2026. Udah stale? DM @raymondchins suruh gw update.

Free tier, no credit card. Free-tier prompts may be used by Google to improve products.

17 free models (marked with :free suffix). OpenAI SDK-compatible.

Free mode, enabled by default, no credit card required. $10/month in API credits, and free-mode prompts may be used to train Mistral models unless you opt out.

$0.10/month in Inference Provider credits for free users (subject to change). Routes to Fireworks, Together, Hyperbolic, Nebius, Novita, DeepInfra and others. Thousands of models.

Free "Trial" API key, no credit card. 1,000 API calls/month. Non-commercial use only.

10,000 Neurons/day free, no credit card required. 75+ models available on the free tier.

Free with NVIDIA Developer Program membership. 100+ models. Rate-limited per model.

Free tier with usage limits. 16 cloud model families from the Ollama library. OpenAI SDK-compatible via https://ollama.com/v1.

Permanent free models, no credit card required.
Permanently free models, no credit card required. Identity verification required. 100+ models in the catalog, most of them paid.

Free API-Inference for registered users. Requires Alibaba Cloud account binding + real-name verification.

Free anonymous tier (no API key, no signup): 2 RPM per IP per model. 20+ open-weight models hosted in EU. OpenAI SDK-compatible.

Free models with no credit card and no API key required. kilo-auto/free auto-router dynamically routes to models in the free pool.

API gateway with a free tier. Anonymous access needs no key and reaches the turbo models; a free token from token.llm7.io raises the rate and token limits but reaches the same models.
Permanent free tier, no credit card required. 15 RPM, 20K tokens/day. Specialized for roleplay and storytelling.
Menampilkan 25 dari 25 provider
Cara kerja
Aggregator, bukan verifier
Data dikumpulin dari sumber komunitas tepercaya, ditampilin apa adanya — lengkap sama atribusi & link sumbernya.
Synced, bukan “verified”
Tiap provider nampilin terakhir di-sync kapan & dari sumber mana — trust dari transparansi, bukan dari klaim.
Apa adanya, ga nebak
Cuma nampilin yang ada di sumber — model, context, rate limit, modality. Ga ada field tebakan atau kolom kosong.
Kenapa gw bikin ini? Karena ✨gratis✨ itu indah, dan gw tau banyak dev yang baru belajar suka kepentok token. This is for you guys, lets build!
Punya project AI / suka ngulik AI? Daftar di genesis.ceo :)


