All LLM prices / OpenAI

gpt-5.6 price per 1M tokens

gpt-5.6 costs $4.00 per 1M input tokens and $20.00 per 1M output tokens, and $0.40 per 1M cached input tokens read.

Per 1M tokens	Input	Output	Cache read	Cache write
gpt-5.6	$4.00	$20.00	$0.40	$5.00

What a call costs

A typical agent step of 20,000 input and 1,500 output tokens costs $0.11 on gpt-5.6, so 10,000 of them a month is $1,100.00. Serving the repeated part of the prompt from cache cuts the input side to $0.40 per 1M, after a one-time write at $5.00.

gpt-5.6 on other providers

Listed as	Input	Output	Cache read	Cache write
azure/eu/gpt-5.6	$4.40	$22.00	$0.44	$5.50
azure/gpt-5.6	$4.00	$20.00	$0.40	$5.00
azure/us/gpt-5.6	$4.40	$22.00	$0.44	$5.50

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": "gpt-5.6", "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.

Which line of your agent spends it? AIght traces each gpt-5.6 call to the line of code that made it. For coding agents, pip install aight && aight-collect --report prices your Claude Code, Codex or Gemini CLI history locally with no account.