All LLM prices / OpenAI
o1 price per 1M tokens
o1 costs $15.00 per 1M input tokens and $60.00 per 1M output tokens, and $7.50 per 1M cached input tokens read.
| Per 1M tokens | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| o1 | $15.00 | $60.00 | $7.50 | — |
What a call costs
A typical agent step of 20,000 input and 1,500 output tokens costs $0.39 on o1, so 10,000 of them a month is $3,900.00. Serving the repeated part of the prompt from cache cuts the input side to $7.50 per 1M.
o1 on other providers
| Listed as | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| azure/eu/o1 | $16.50 | $66.00 | $8.25 | — |
| azure/o1 | $15.00 | $60.00 | $7.50 | — |
| azure/us/o1 | $16.50 | $66.00 | $8.25 | — |
| openrouter/openai/o1 | $15.00 | $60.00 | $7.50 | — |
| replicate/openai/o1 | $15.00 | $60.00 | — | — |
| vercel_ai_gateway/openai/o1 | $15.00 | $60.00 | $7.50 | — |
Price history
No change to the listed rates since this log began on 2026-10-04.
Price a call with the free API
No key, no account. It uses this same table, and with "usage_shape": "openai" it takes the cached tokens out of prompt_tokens first, so they aren't billed twice.
curl -s https://api.aight.studio/api/cost \
-H 'content-type: application/json' \
-d '{"model": "o1", "input_tokens": 20000, "output_tokens": 1500, "cache_read_tokens": 12000}'
Returns cost_usd, a breakdown per token type, the rates per 1M, and when the table last changed. Rates only: GET https://api.aight.studio/api/pricing?models=a,b. Rate-limited per client; an unknown model is a 404, never $0. Full API docs.
pip install aight && aight-collect --report prices your Claude Code, Codex or Gemini CLI history locally with no account.