Compare free API keys for modern large language models across Google Gemini, Groq, NVIDIA NIM, OpenRouter, Mistral, and Cloudflare. Check daily request caps, credit card requirements, OpenAI SDK drop-in compatibility, and prompt privacy policies.
Provider | Tier | Free Limits & Quota | Credit Card | OpenAI Compatible | Prompt Privacy | Get Key |
|---|---|---|---|---|---|---|
Cerebras Inference gpt-oss-120bQwen 3.8 27BLlama 3.3 70B | Free Trial | $5 of credits for 30 days; 5 requests/min, 1M tokens/day per model | Yes (post-trial) | Yes | Not stated | Get Key |
Cloudflare Workers AI gpt-oss-20bgpt-oss-120bLlama 3.1 8B Instruct+2 more | Ongoing Free Tier | 10,000 Neurons a day on the Workers Free plan, reset at 00:00 UTC | No | Yes | Not stated | Get Key |
Cohere (trial key) Command R+Command REmbed v3 English/Multilingual+1 more | Ongoing Free Tier | Trial key: 20 requests/min on chat, 1,000 API calls a month | No | Custom SDK | Not stated | Get Key |
Google Gemini APITop Pick Gemini 3.8 FlashGemini 3.1 Flash-LiteGemma 2+1 more | Ongoing Free Tier | Free input and output tokens on Flash models, with per-model RPM, TPM, and RPD limits shown in AI Studio | No | Yes | Yes: free-tier prompts are used to improve Google products | Get Key |
GroqTop Pick gpt-oss-120bgpt-oss-20bQwen 3.8 27B+1 more | Ongoing Free Tier | 30 requests/min, 1,000 requests/day, 8K tokens/min, 200K tokens/day on the main models | No | Yes | No: inputs and outputs are not retained by default | Get Key |
Mistral AI Mistral SmallMistral MediumMistral Large 2+2 more | Ongoing Free Tier | Free mode with included monthly usage; exact limits shown after login in console | No | Yes | Not stated for the free API | Get Key |
NVIDIA API Catalog (NIM)Top Pick DeepSeek V4.1 FlashNemotron 70BLlama 3.3 70B+2 more | Ongoing Free Tier | Free hosted endpoints with a free NVIDIA Developer Program account; generous prototyping limits | No | Yes | Not stated | Get Key |
Ollama DeepSeek R1Llama 3.3Qwen 2.5 Coder+2 more | Local / Self-Hosted | Unlimited on your own hardware; free account adds small cloud usage on starter models | No | Yes | No: runs locally; Ollama says cloud prompts are not logged or trained on | Get Key |
OpenRouter (free models) meta-llama/llama-3.3-70b-instruct:freedeepseek/deepseek-r1:freegoogle/gemini-2.0-flash-exp:free | Ongoing Free Tier | 20 requests/min; 50 requests/day, or 1,000/day once you have bought $10 of credits | No | Yes | Depends on the upstream provider of each free model | Get Key |
SambaNova Cloud DeepSeek V3Llama 3.3 70Bgpt-oss-120b | Ongoing Free Tier | 20 requests/min, 20 requests/day and 200K tokens/day per model, with no card linked | No | Yes | Not stated | Get Key |