Web & Dev

AI Token Limits & Costs

Context windows and per-token prices for major LLM APIs — ballpark figures for cost estimation.

Updated Apr 19, 2026 2 min read

Prices are USD per 1 M tokens. Check provider docs for latest — these change often.

OpenAI

ModelContextInput / 1MOutput / 1M
GPT-4o128K$2.50$10.00
GPT-4o mini128K$0.15$0.60
GPT-4.11M$2.00$8.00
GPT-4.1 mini1M$0.40$1.60
GPT-4.1 nano1M$0.10$0.40
o1200K$15.00$60.00
o3-mini200K$1.10$4.40

Anthropic

ModelContextInput / 1MOutput / 1M
Claude 3.5 Haiku200K$0.80$4.00
Claude 3.5 Sonnet200K$3.00$15.00
Claude 3 Opus200K$15.00$75.00
Claude 4 Sonnet200K$3.00$15.00
Claude 4 Opus200K$15.00$75.00

Google

ModelContextInput / 1MOutput / 1M
Gemini 2.0 Flash1M$0.10$0.40
Gemini 2.5 Flash1M$0.15$0.60
Gemini 2.5 Pro1M$1.25 (≤200K) / $2.50$10.00 / $15.00

Notes

  • Cached input can drop prices by 50–90% — investigate prompt caching when reusing system prompts.
  • Batch pricing offers ~50% off at 24 h latency on OpenAI and Anthropic.
  • 1 token ≈ 4 English characters / 0.75 word on average. Code and non-English languages use more tokens.
Was this article helpful?