Google DeepMind

Gemini 2.5 Pro Preview 0506

Type
language model
Context
1,049K tokens
Max output
66K
Released
6 May 2025
Knowledge cutoff
January 2025
API string
gemini-2.5-pro-preview-05-06

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Kilo Code $1.25 $10 31 Jul 2026
OpenRouter $1.25 $10 31 Jul 2026
NanoGPT $2.5 $10 31 Jul 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
MATH, difficulty level five 95.9 % · with a tuned harness Epoch evaluations
GeoBench — locating a place from a photograph 86 % GeoBench leaderboard
Creative writing (Lech Mazur’s evaluation) 80.9 % lechmazur/writing Github repository
Aider Polyglot — code edits in six languages 76.9 % · with a tuned harness Aider LLM Leaderboards
Fiction.LiveBench — holding a long context 66.7 % Fiction.live leaderboard
GPQA Diamond — graduate-level questions 55.56 % · with a tuned harness Epoch evaluations
DeepResearch Bench — deep research 31.9 %
The Agent Company — work tasks in an office environment 30.3 % TheAgentCompany leaderboard
Humanity’s Last Exam — expert-level questions 13.66 %