tokendrift

gpt-5.5-pro

GPT-5.5 Pro — priced by OpenAI.

Published tiers

What the most recent complete run published for this model, one row per priced tier, each with the source it was read from.

Tier Input USD/1M Output USD/1M Last read Read from Flags
batch1590OpenRouter models APIconfirmedsingle source
batch:short_context1590OpenAI API pricing (docs)confirmedsingle source
flat30180OpenRouter models APIconfirmedsingle source
flat:flex_short_context1590OpenAI API pricing (docs)confirmedsingle source
flat:short_context30180OpenAI API pricing (docs)confirmedsingle source
This model on the price scale15 to 180 across 10 published values

The same six decades as the front page, so a price is in the same place here as it is anywhere else on this site. The two marks in the accent colour are this model’s cheapest and dearest published values.

Price history

Every distinct value this price has taken, oldest first — what the price did, not how often we happened to look. Rows marked backfill came from a public git history of a third-party pricing file and were never verified by us; they extend the series backwards and are flagged rather than hidden.

batch

2 distinct values

Held steady173 days — the value published now has been observed to hold for 173 days, which is 100% of the longest run on this page.

inputoutput1 window nobody looked inhorizontal axis is time

  • Input low 15 · high 30 high from backfill
  • Output low 90 · high 180 high from backfill
  • Observed 2026-04-24 21:10Zto 2026-04-27 22:33Z
First seenLast seenInput USD/1MOutput USD/1MReadsSourceLast readFlags
2026-04-24 21:10Z2026-04-25 18:16Z301802LiteLLM model_prices_and_context_window.json (git history)neverbackfillunconfirmed
2026-04-27 22:33Z2026-10-17 12:00Z159070OpenRouter models API2026-10-17 12:00Z

batch:short_context

1 distinct value

One value across the whole archive: this price has not moved in anything we have observed.

Held steady62 days — the value published now has been observed to hold for 62 days, which is 36% of the longest run on this page.

  • Input 15
  • Output 90
  • First seen 2026-08-16 04:15Z
  • Last seen 2026-10-17 12:00Z
  • Reads 68
  • Last read 2026-10-17 12:00Z
  • Source OpenAI API pricing (docs)

flat

2 distinct values

Held steady173 days — the value published now has been observed to hold for 173 days, which is 100% of the longest run on this page.

inputoutput1 window nobody looked inhorizontal axis is time

  • Input low 30 · high 60 high from backfill
  • Output low 180 · high 360 high from backfill
  • Observed 2026-04-24 21:10Zto 2026-04-27 22:33Z
First seenLast seenInput USD/1MOutput USD/1MReadsSourceLast readFlags
2026-04-24 21:10Z2026-04-25 18:16Z603602LiteLLM model_prices_and_context_window.json (git history)neverbackfillunconfirmed
2026-04-27 22:33Z2026-10-17 12:00Z3018074OpenRouter models API2026-10-17 12:00Z

flat:flex_short_context

1 distinct value

One value across the whole archive: this price has not moved in anything we have observed.

Held steady62 days — the value published now has been observed to hold for 62 days, which is 36% of the longest run on this page.

  • Input 15
  • Output 90
  • First seen 2026-08-16 04:15Z
  • Last seen 2026-10-17 12:00Z
  • Reads 68
  • Last read 2026-10-17 12:00Z
  • Source OpenAI API pricing (docs)

flat:short_context

1 distinct value

One value across the whole archive: this price has not moved in anything we have observed.

Held steady62 days — the value published now has been observed to hold for 62 days, which is 36% of the longest run on this page.

  • Input 30
  • Output 180
  • First seen 2026-08-16 04:15Z
  • Last seen 2026-10-17 12:00Z
  • Reads 68
  • Last read 2026-10-17 12:00Z
  • Source OpenAI API pricing (docs)

Provenance

Read by openai_astro_props (batch:short_context, flat:flex_short_context, flat:short_context) and openrouter_json (batch, flat) from OpenAI API pricing (docs), OpenRouter models API. Each row above links to the exact page its number came from. The vendor's page is authoritative: if it and this page disagree, the vendor is right and we are wrong.