Nvidia

Mistral Medium 3

Mistral Medium 3 is listed by Nvidia at $0 input and $0 output per million tokens. The recorded context window is 131,072 tokens. Release date on file: 2025-05-07. LMArena's text board published 2026-10-20 gives it an overall rating of 1370.2 (rank 185, 32,783 votes). Price source: models.dev (MIT).

  • Context12
  • Inverse price—
  • Arena60
  • GPQA—
  • Tools15
  • Modalities50

List price

Input / 1M$0.00Output / 1M$0.00Cache read / 1M—Blended$0.000Value index—Last move—

models.dev · MIT · retrieved Oct 25, 2026

Price history

Input and output list price. A missing day stays a gap in the line. The series is not a quality history.

$2.00 / 1M2026-06-252026-10-18
Input Output32 observationsModelPriceWatch LLM Token Price History · CC-BY-4.0

Benchmarks

LMArena is CC-BY-4.0. Epoch scores, including LiveBench where Epoch publishes it, are CC-BY-4.0. A blank cell means this snapshot has no match. Nothing here is estimated.

BenchmarkScoreDetailSource
LMArena overall1370.2rank 185 · 32,783 votesLMArena leaderboard dataset · CC-BY-4.0
LMArena coding1385.4rank 187 · 5,844 votesLMArena leaderboard dataset · CC-BY-4.0
LMArena math1352.7rank 215 · 2,233 votesLMArena leaderboard dataset · CC-BY-4.0
GPQA Diamond———
LiveBench———
SWE-bench Verified———
Epoch Capability Index134.02130.38–135.36Epoch AI Capabilities & benchmarking · CC-BY-4.0

Provider prices

The list row is the price used for the value index. Other rows are the same model id on models.dev, plus the LiteLLM catalog price when we have one. A split quote is kept beside the list price.

QuoteProviderInput / 1MOutput / 1MBlendedSource
ListNvidia$0.00$0.00$0.000models.dev · MIT
Also listedMerge Gateway$0.40$2.00$1.600models.dev · MIT
Also listedNanoGPT$0.40$2.00$1.600models.dev · MIT
Also listedEden AI$0.40$2.00$1.600models.dev · MIT
LiteLLMmistral$1.50$7.50$6.000LiteLLM model_prices_and_context_window.json · MIT

Spec

Context131,072Max output32,768Inputtext, imageOutputtextReleased2025-05-07Open weightsNo

Spec fields are from the models.dev row for Nvidia.

Also from Nvidia