Mistral AI

Mistral 7B Instruct V0.2

Type
language model
Context
33K tokens
Max output
8K
API string
bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Replicate $0.05 $0.25 31 Jul 2026
Fireworks AI $0.2 $0.2 1 Aug 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 1,133.64 1,126–1,141 — —
Arena Score, overall 1,089.72 1,083–1,096 — —
Arena Score, mathematics 1,085.4 1,073–1,097 — —
Arena Score, programming 1,082.19 1,071–1,094 — —
Arena Score, creative writing 1,068.08 1,056–1,081 — —
Arena Score, hard prompts 1,067.46 1,058–1,077 — —
Arena Score, multi-turn dialogue 1,062.47 1,049–1,076 — —
Arena Score, long queries 1,060.49 1,045–1,076 — —
Arena Score, instruction following 1,060.46 1,052–1,069 — —
Arena Score in French 1,035.65 1,003–1,068 — —
Arena Score, expert questions 1,035.49 1,015–1,056 — —
Arena Score in Spanish 1,025.58 980–1,071 — —
Arena Score in Russian 1,017.33 1,000–1,035 — —