Free AI usage, compared by what you actually get.

Amazon Q Developer Free includes 50 agentic requests per month and 1,000 lines of Java transformation per month.

Bolt's Free plan publishes a 300K-token daily limit and 1M-token monthly allowance for AI app building.

Cerebras gives new accounts $5 in free inference credits after a verified payment method is added.

Cloudflare Workers AI includes 10,000 Neurons of AI inference per day at no charge on Workers Free.

Cohere evaluation/trial keys are free and limited to 1,000 API calls per month, with endpoint-specific per-minute limits.

Exa's Starter plan gives new accounts $20 in signup credits and adds $10 in credits every month without requiring a payment method.

Fireworks AI says serverless inference starts with $1 in free credits for pay-per-token model usage.

Copilot Free includes 2,000 inline code completions per month plus a limited allowance of GitHub AI Credits.

Eligible Gemini models have free-of-charge input and output tokens within model-specific rate limits.

Groq publishes a Free-plan table. Listed GPT-OSS and Qwen text models currently show 200,000 tokens and 1,000 requests per day.

Every free Hugging Face user receives a small monthly credit for routed Inference Providers requests.

The official JetBrains AI plan gives the free tier 3 AI Credits per 30-days.

Kiro's perpetual Free tier includes 50 credits for prompts, specs, tasks, and hooks.

Modal's free Starter plan includes $30 per month of compute for serverless AI workloads.

OpenCode Zen lists seven models with free input and output pricing. No fixed token quota is published.

Use free model variants through OpenRouter chat or its API, with a published Free-plan limit of 50 requests per day.

Tavily's free plan includes 1,000 API credits per month for AI web search and extraction.

The v0 Free plan includes $5 of monthly credits and limits free users to seven messages per day.