modelbenchmark.io

Gemini 2.5 Pro Preview 0506

Google · gemini-2-5-pro-preview-05-06

Compare

Compact GPT model for low-latency assistance and high-volume workloads

Specification

most-agreed values

Context
1M
Max output
66K
Released
2025-05-06
Knowledge cutoff
Retires
Open weights
no
Input
text, image, audio
Output
text

Price

US dollars per million tokens · most-agreed

Input
$2.50
Output
$10.00
Cache read
$0.25
Cache write
$0.375

Long-context price tiers

the rate above each context threshold

AbovePrice$/M
200KCache read$0.25
200KInput$2.50
200KOutput$15.00

Quality

1 benchmark · 1 source

Composite
95th
percentile of 334 scored models
Rank
18 / 334
±0.11 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
one configuration only
coding95th1/3 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
Aider polyglot76.9default · aider diff-fencedAider2025-05-07

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openrouter$1.25$10.00$0.125$0.3751M66K
nano-gpt$2.50$10.00$0.251M66K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02openrouterCache read$0.125
2026-09-06openrouterCache read$0.125
2026-09-15openrouterCache read$0.125
2026-09-02openrouterCache write$0.375
2026-09-06openrouterCache write$0.375
2026-09-15openrouterCache write$0.375
2026-09-02openrouterInput$1.25
2026-09-06openrouterInput$1.25
2026-09-15openrouterInput$1.25
2026-09-02openrouterOutput$10.00
2026-09-06openrouterOutput$10.00
2026-09-15openrouterOutput$10.00

More from Google

most-hosted first