Free AI APIs
Which AI APIs you can still call for free, what each one asks for (a card, a phone number, nothing), and which model IDs actually answered when we called them.
Which one should you use?
At a glance
The short version. Quotas, rate limits and every model ID are in the full comparison.
| Provider | Status | Card? | Phone? | Models that answered | Fastest first token | Checked |
|---|---|---|---|---|---|---|
| Groq | Free, works | No | — | 4 | 0.88 s qwen/qwen3.8-27b |
review due |
| Google Gemini | Free, works | No | — | 10 | 1.25 s gemini-3.5-flash-lite |
review due |
| Mistral | Free, works | No | — | 12 | 0.69 s ministral-8b-latest |
review due |
| OpenRouter | Free, works | No | — | 8 | 1.22 s nvidia/nemotron-3-super-120b-a12b:free |
review due |
| NVIDIA NIM | Free, works | No | — | 13 | 0.54 s nvidia/nemotron-3-super-120b-a12b |
review due |
| Zhipu GLM | Free, phone check | No | Yes | 3 | 0.65 s glm-4-flash-250414 |
review due |
| Gonka Broker | Free, phone check | No | Yes | 3 | 2 s deepseek-ai/DeepSeek-V4-Flash-0731 |
review due |
| Cloudflare Workers AI | Free, works | — | — | 6 | — | review due |
| Cohere | Trial only | — | — | — | — | review due |
| Cerebras | Card required | Yes | — | — | — | review due |
| SambaNova Cloud | Card required | Yes | — | — | — | review due |
| DeepSeek API | Closed since 2026-08-31 | Yes | — | — | — | review due |
| Together AI | Closed since 2026-08-31 | Yes | — | — | — | |
| GitHub Models | Closed since 2026-07-30 | — | — | — | — | review due |
"—" means not stated by the provider or not measured by us.
Tests, one provider at a time
- Groq Free, works Groq Free API Tested: Speed, Rate Limits and What You Can Build
- Google Gemini Free, works Google Gemini Free API Tested: 34s to First Token
- Mistral Free, works Mistral Free API Tested: 167 tok/s, No Credit Card
- OpenRouter Free, works OpenRouter Free Tier Tested: 16 Free Models, One API Key
- NVIDIA NIM Free, works NVIDIA NIM Free API Tested: Which Models Still Answer
- Zhipu GLM Free, phone check GLM Free API Tested: Slow at 20 tok/s, Still Useful
- Gonka Broker Free, phone check Gonka Broker Free LLM API: 1M Tokens a Month, Tested
- Cloudflare Workers AI Free, works Cloudflare Workers AI Free Tier: 10,000 Neurons a Day, Tested
- Cohere Trial only Cohere Free API: Embedding and Rerank for RAG
- Cerebras Card required Cerebras API: Fast, But the Free Tier Now Needs a Card
- SambaNova Cloud Card required SambaNova Cloud: The Free Tier Is Gone (What It Costs Now)
- DeepSeek API Closed DeepSeek API Is No Longer Free: We Checked the Balance
- Together AI Closed Together AI Free Tier Is Gone: What It Costs Now
- GitHub Models Closed GitHub Models API Is Retired: What to Use Instead
Roundups and head-to-head tests
-
Best Free AI APIs: Which Ones Still Work, Tested
Every free LLM API we track, including Groq, Gemini, Mistral, OpenRouter and NVIDIA NIM: free allowance, card and phone rules, and the model IDs that answered, each with the date we checked.
-
Groq vs Cerebras vs Gemini Free API: Limits and Speed, Tested
Groq, Cerebras and Gemini re-checked on 2026-09-29: only Groq is free with no card and no expiry; Cerebras is a $5, 30-day trial; Gemini is free but unpublished. Working model IDs and US speeds.
Running agents on free tiers
One chat completion is the wrong unit for an agent. These tests count rounds, tokens and the errors that only show up in a loop.
-
How Many Tokens One Agent Task Costs on Free AI APIs
We ran one bug-fix agent task on 9 free AI API models and counted every token. Solved runs cost 1,911 to 16,399 tokens; round count, not speed, sets the bill.
-
We Gave Free AI Models Real Agent Jobs: Most Failed
We plugged four free AI models into a real agent harness and gave them real jobs. Nemotron was fastest at debugging but silently did nothing on file tasks; Kimi K3 was most reliable.
-
Groq Free Tier Gives You Throughput, Not Context
Groq's free tier advertises 131k context. We measured 7,500 usable tokens: the 8,000 TPM budget is the real limit, and it counts the max_tokens you request.
-
Free LLM API Keys: Why Your Agent Still Fails
Four free API keys, all returning 200 from curl, and not one working agent. The five failures that are never the key, and a six-step checklist.
Speech, vision and safety APIs
-
Free Whisper API Tested: 160x Realtime on Groq
We timed Groq free Whisper on real speech: 4 minutes of audio transcribed in 1.53 seconds, 160x realtime. Turbo was 21% faster than large-v3 with identical output.
-
Free Text-to-Speech APIs Tested: Groq Hits 4.4x Realtime
We measured Groq free TTS at 4.4x realtime with 6 voices and no card, plus two traps: the model needs manual terms acceptance, and its WAV header reports 24 hours for a 10-second clip.
-
Free Speech-to-Speech API: Gemini Live and 3 Others
Gemini Live's preview models are the only speech-to-speech API listed as free. OpenAI Realtime has none; Hume gives 5 min/month. Limits and code inside.
-
Free AI Image Generation API: 4 Options Compared
Free AI image generation APIs compared: Pollinations (no key), Cloudflare Workers AI (~230 FLUX images/day) and Hugging Face are $0; Gemini's Nano Banana models returned 429 on a new free key.
-
Free OCR API for PDFs and Scanned Documents
Six free ways to OCR PDFs and scans: OCR.space, Cloudflare, Gemini, Cloud Vision, Mistral OCR 4 and self-hosted Docling. Real quotas, license traps, code.
-
Free Content Moderation API: What Still Costs $0
OpenAI Moderation is still free: 5,000 checks/day, text and images. Plus Groq free safeguard models, and why Perspective API shuts down Dec 31, 2026.
Search, scraping and gateways
-
Tavily vs Brave vs Exa: Free Search APIs for AI Agents
Tavily, Brave Search and Exa MCP servers compared: exact tool names (tavily-search, brave_web_search, web_search_exa), install command and API key env var, plus what each free tier gives you.
-
Firecrawl: Free Web Scraping API for LLMs & Agents
Firecrawl turns any URL into clean, LLM-ready Markdown or JSON via one API. Free tier: 1,000 credits/month, no card. Scrape, crawl, map & extract.
-
Crawl4AI: Free Open-Source Web Crawler for LLMs
Crawl4AI is the free, open-source (Apache 2.0) web crawler that turns any site into clean, LLM-ready Markdown — self-hosted, no API key, no quota.
-
LiteLLM: One Free API for OpenAI, Claude & 100+ LLMs
LiteLLM is a free, open-source gateway to call OpenAI, Claude, Gemini and 100+ LLMs through one API. SDK, self-hosted proxy, fallbacks, budgets.
More in this category
-
Kimi K2 Free API Status
Kimi K2 has no verified free hosted API: Moonshot and OpenRouter charge, and current Cloudflare Kimi models require paid access. Free chat is separate from API access.
-
Qwen3-Coder API: 3 Ways to Use It Free in 2026
Qwen's free OAuth tier ended April 2026, but Qwen3-Coder is Apache 2.0. Run it free via self-hosting or Puter.js, or paid on OpenRouter — with runnable code.
-
Is the Grok API Free? Credits, Pricing and Setup
The Grok API has no permanent free tier, and xAI's $150/month data-sharing credit is no longer documented. How it worked, pricing, and OpenAI-SDK setup.
-
Alibaba Cloud Bailian API: Free Access to Qwen, DeepSeek and More
Alibaba Cloud Bailian offers 1 million free tokens per AI model with no credit card required. Learn how to get your free API key and connect it to...
How this page stays current
Status, card and phone rules, model counts and first-token times come from one data file per provider. We test selected APIs with a free key and check other claims against provider documentation. Each row shows its own verification date; that date is not the last time we edited this page.