Google DeepMind

Gemma 7B IT

Type
language model
Context
8K tokens
Max output
8K
API string
anyscale/google/gemma-7b-it

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Groq $0.05 $0.08 31 Jul 2026
anyscale $0.15 $0.15 31 Jul 2026
Fireworks AI $0.2 $0.2 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 English 1,090.21 1,079–1,101 — —
Arena Score, mathematics 1,066.38 1,050–1,083 — —
Arena Score, overall 1,056.31 1,047–1,066 — —
Arena Score, programming 1,048.62 1,032–1,065 — —
Arena Score, hard prompts 1,041.93 1,029–1,055 — —
Arena Score, creative writing 1,023.9 1,006–1,042 — —
Arena Score in French 1,023.81 976–1,072 — —
Arena Score, long queries 1,021.93 1,000–1,044 — —
Arena Score, instruction following 1,017.49 1,005–1,030 — —
Arena Score, expert questions 1,001 970–1,032 — —
Arena Score in Russian 992.35 969–1,016 — —
Arena Score, multi-turn dialogue 963.27 945–982 — —