Google DeepMind

Gemma 4 26B-A4B

Type
language model
Context
262K tokens
Max output
33K
Released
2 April 2026
API string
gemma-4-26b-a4b
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
EmpirioLabs AI $0.05 $0.29 31 Jul 2026
bedrock_mantle $0.13 $0.4 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 1,466.68 1,426–1,507 — —
Arena Score, mathematics 1,466.5 1,438–1,495 — —
Arena Score, expert questions 1,448.38 1,421–1,475 — —
Arena Score in Russian 1,444.27 1,423–1,465 — —
Arena Score, programming 1,444.01 1,429–1,459 — —
Arena Score in English 1,442.26 1,431–1,454 — —
Arena Score, hard prompts 1,439.84 1,430–1,450 — —
Arena Score, multi-turn dialogue 1,438.6 1,421–1,456 — —
Arena Score, overall 1,434.69 1,427–1,442 — —
Arena Score, long queries 1,429.53 1,415–1,444 — —
Arena Score, instruction following 1,422.54 1,408–1,437 — —
Arena Score, creative writing 1,404.92 1,386–1,424 — —
Arena Score, web development 1,366.59 1,349–1,384 — —
Arena Score, text recognition in images 1,266.49 1,260–1,273 — —
Arena Score, understanding diagrams 1,263.36 1,254–1,273 — —
Arena Score, working with images 1,256.71 1,250–1,264 — —