Google DeepMind

Google: Gemma 2 27B

Type
language model
Context
8K tokens
Max output
2K
Released
24 June 2024
Knowledge cutoff
June 2024
API string
google/gemma-2-27b-it
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Kilo Code $0.65 $0.65 31 Jul 2026
OpenRouter $0.65 $0.65 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
Arena Score in French 1,246.19 1,223–1,269 — —
Arena Score in English 1,242.04 1,238–1,246 — —
Arena Score, creative writing 1,241.04 1,234–1,248 — —
Arena Score in Russian 1,232.95 1,226–1,240 — —
Arena Score, overall 1,231.54 1,228–1,235 — —
Arena Score, long queries 1,230.8 1,224–1,238 — —
Arena Score in Spanish 1,227.3 1,205–1,250 — —
Arena Score, multi-turn dialogue 1,223.77 1,217–1,230 — —
Arena Score, mathematics 1,212.02 1,205–1,219 — —
Arena Score, programming 1,211.41 1,205–1,218 — —
Arena Score, instruction following 1,206.47 1,202–1,211 — —
Arena Score, hard prompts 1,198.64 1,193–1,204 — —
Arena Score, expert questions 1,171.03 1,161–1,181 — —
MATH, difficulty level five 27.89 % · with a tuned harness Epoch evaluations
GPQA Diamond — graduate-level questions 15.32 % · with a tuned harness Epoch evaluations
Mock AIME 2024–2025 — olympiad problems 1.29 % · with a tuned harness Epoch evaluations