Meta AI

Llama 2 7B Chat

Type
language model
Context
128K tokens
Max output
4K
Released
3 April 2025
API string
replicate/meta/llama-2-7b-chat

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Replicate $0.05 $0.25 31 Jul 2026
Cloudflare AI Gateway $0.56 $6.67 31 Jul 2026
Cloudflare Workers AI $1.923 $1.923 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 1,096.01 1,088–1,104 — —
Arena Score, overall 1,053.56 1,047–1,061 — —
Arena Score, mathematics 1,041.95 1,028–1,056 — —
Arena Score, expert questions 1,035.66 1,008–1,064 — —
Arena Score, creative writing 1,033.64 1,020–1,047 — —
Arena Score, multi-turn dialogue 1,029.13 1,014–1,044 — —
Arena Score, hard prompts 1,009.5 999–1,020 — —
Arena Score in Spanish 1,006.58 956–1,057 — —
Arena Score, instruction following 1,006.31 997–1,016 — —
Arena Score, programming 1,002.4 988–1,016 — —
Arena Score, long queries 999.3 979–1,019 — —
Arena Score in Russian 994.08 971–1,017 — —
Arena Score in French 968.46 925–1,012 — —