Guides

The cheapest LLM APIs right now.

Ranked by real monthly cost, not headline price. Checked Oct 20, 2026.

Headline input prices hide the real bill. Most chat apps send far more input than they get back, but output tokens cost 4 to 8 times more. So we ranked every model on the same workload: 100,000 requests a month, 1,000 input and 500 output tokens each.

  1. GPT-OSS 20B on Groq (Groq): $22.50/month. About 1,000 tokens/sec according to Groq.
  2. GPT-5 nano (OpenAI): $25.00/month.
  3. Gemini 2.5 Flash-Lite (Google Gemini): $30.00/month. Free tier available.
  4. GPT-6 Luna (OpenAI): $35.00/month. Prompts over 272K input tokens bill at $0.20 in / $0.75 out.
  5. Claude Haiku 5.5 (Anthropic): $35.00/month. For prompts up to 100K tokens. Over 100K: $0.50 in / $2.50 out.

Google also offers a free tier on several Gemini models, including Gemini 3.8 Flash, Gemini 3.5 Flash-Lite, Gemini 3.1 Flash-Lite, which is useful for prototypes. Free-tier content may be used to improve Google's products, according to its pricing page.

All prices from official provider pages, checked Oct 20, 2026. See sources.