Pass IndexThe State of AISign in

Mistral-7B-Instruct-v0.3

Mistral-7B-Instruct-v0.3 is an instruction-tuned model, next iteration of of Mistral 7B that has larger vocabulary, newer tokenizer and supports function calling.

text → text · made by Mistral AI

$0.028$0.054per Mtok in / out
DeepInfra · 2 sellers

Sold by 2 ways

SellerLaneRate
DeepInfra aggregatorstandard$0.028per Mtok in$0.054per Mtok outapi.deepinfra.com · read 2026-08-25
Together AI aggregatorstandard$0.2per Mtok in$0.2per Mtok outraw.githubusercontent.com · read 2026-09-16

Measured 6 standings

PlaceBoardMetricScore
107thof 108Math level 5 — Epoch AImean_score3.597
119thof 217Mmlu — Epoch AIEM0.599
202ndof 222Chess puzzles — Epoch AImean_score0
288thof 290OTIS Mock AIME 2024-2025mean_score0.278
309thof 313GPQA Diamondmean_score15.183
619thof 656Epoch capabilities index — Epoch AIECI Score108.75

About

Mistral-7B-Instruct-v0.3 — a text model from Mistral AI, sold by 2 companies from $0.028 in and $0.054 out per million tokens, placed 119th of 217 on Mmlu — Epoch AI.

It takes text and returns text, with a context window of 32,768 tokens. It was published in April 2023. Its sellers say it can call a tool. The catalogue files it under reasoning. Two companies sell it. The cheapest is $0.028 in and $0.054 out per million tokens at DeepInfra. It has been measured on 6 boards, and stands best at 119th of 217 on Mmlu — Epoch AI.

Every current figure

Maker
Mistral AI
Register
model
Takes
text
Returns
text
Context
32,768 tokens
Published
April 2023
Parameters
7 billion · read from its own name
Licence
not read
Sellers
2
Maker's own price
not read
Price
$0.028 in and $0.054 out per million tokens — DeepInfra
Boards
6
Best place
119th of 217 — Mmlu — Epoch AI

Known as 1 name

mistralai/Mistral-7B-Instruct-v0.3