Skip to content
ModelCap

Mistral Medium 3

All-versions archive #180Arena #168API only

Mistral AI·mistralai/mistral-medium-3

Mistral Medium 3 is ModelCap archive rank #180 (Measured), from the ModelCap Index as of 22 Sept 2026, 02:49 UTC.

Mistral Medium 3 listed OpenRouter input price is $0.40 per 1M tokens and listed output price is $2.00 per 1M tokens, from OpenRouter listed prices as of 22 Sept 2026, 02:49 UTC.

Mistral Medium 3 has a published context limit of 131K tokens in the ModelCap catalogue as of 22 Sept 2026, 02:49 UTC.

Mistral Medium 3 has 3 published OpenRouter serving endpoints, from OpenRouter as of 22 Sept 2026, 02:49 UTC.

Mistral Medium 3 weight access is api only, from ModelCap classification of published repository metadata as of 22 Sept 2026, 02:49 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index · All-versions archive
49.0#180
Measured · 62% support · score interval 44.0–54.0
Evidence as of 13 Sept 2026, 00:00 UTC
Market Gravity
34.8Increased by 0.1
Secondary market signal

Superseded by Mistral Medium 3.5. It no longer holds a current-board position; its all-versions archive rank is #180.

Input
$0.40
per 1M tokens
Output
$2.00
per 1M tokens
Context
131K
tokens
Providers
3
endpoints
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
MistralzdrCheapest$0.40$2.00131K
Mistral$0.40$2.00131K
Mistraleu$0.44$2.20131K

Other versions (2)

ModelCap Index · All-versions archive

Methodology
49.0
Measured · 2 public benchmark observations across 2 boards
All-versions archive
#180
Public rank basis
Measured (measured)
Index support
61.9% · strong
Index interval
44.0–54.0
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Evidence as of
13 Sept 2026, 00:00 UTC
Identity binding
Exact catalogue product · mistralai/mistralai/mistral-medium-3 · aggregates disclosed benchmark configurations · endpoint configuration not claimed
Index observations used
2
Qualified Index evidence point
49.0
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
49.0
Evidence status
confirmed · 77% mass
General preference
49.2
Coding
47.3
Agents & tools
Reasoning
Evidence breadth
92%
Evidence coverage
62%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
4.0
Liquidity (providers × uptime)
97.4
Open reach (HF downloads)
Surface (context / tools / modalities)
60.2
Freshness
14.8
  • · OpenRouter popularity #256
  • · 1 live provider
  • · Catalogue: context 131072, tools, modalities Text/Image/File
  • · First seen 2025-05-07

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
40.7
limited · 56% metadata coverage
Not capability
Artifact reproducibility
0.0
Access & legal clarity
30.3
Deployability
80.0
Evaluation provenance
53.0

Missing: artifactReproducibility.revision-sha, artifactReproducibility.architecture-and-model-type, artifactReproducibility.parameter-count, artifactReproducibility.serialized-weight-format, artifactReproducibility.base-lineage, accessLegalClarity.declared-license, accessLegalClarity.resolvable-license-terms, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
34.8
OpenRouter weekly popularity
#256 of 322

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
LMArena
Official rank
#168 of 402
Rating
1387.4
95% confidence interval
1383–1392
Votes
33K
Source published at
13 Sept 2026, 00:00 UTC
Category
overall
Identity match confidence
98%

Market Gravity breakdown

Usage55%
4.0

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
97.4

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
14.8

Time since first public availability, on a six-month half-life.

Specification

Context window
131K tokens
Max output
105K tokens
Inputs
Text, Image, File
Outputs
Text
Tokenizer
Mistral
Cached input tokens
$0.04 / 1M
First seen on OpenRouter
7 May 2025
Knowledge cutoff
2025-03-31

Capabilities

  • Not supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Benchmark leaderboards featuring Mistral Medium 3

All leaderboards
Public benchmark boards on which Mistral Medium 3 has a published result
LeaderboardScoreSource rankConfigurationPublished
Arena coding leaderboardArena (LMArena)14331425–1441#167 of 397Default13 Sept 2026
BFCL V4 function-calling leaderboardUC Berkeley (Gorilla)37.7#36 of 83Default12 Apr 2026
τ²-Bench Telecom (Artificial Analysis run)Artificial Analysis24.3%#318 of 436tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Mistral Medium 3":reasoning=false5 Sept 2026
Humanity's Last Exam (Artificial Analysis run)Artificial Analysis4.1%#531 of 615hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Mistral Medium 3":reasoning=false5 Sept 2026

Mistral Medium 3: common questions

How does Mistral Medium 3 rank among AI models?

Mistral Medium 3 is a superseded version and is not on the current board as of 22 September 2026. Its archive position, where one exists, is shown on the page; the newer version carries the current rank.

How much does Mistral Medium 3 cost per 1M tokens?

Mistral Medium 3 is listed at $0.40 per 1M input tokens and $2.00 per 1M output tokens as of 22 September 2026. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $1.80 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.

What is the context window of Mistral Medium 3?

Mistral Medium 3 has a published context window of 131K tokens (131,072) and a maximum output of 105K tokens. Individual providers can serve less than the published maximum; the providers table lists each endpoint's own limit.

Is Mistral Medium 3 open-weight?

API only. No downloadable model weights are linked in the current source data; access is through a hosted API or product.

Which API providers serve Mistral Medium 3?

One provider serves Mistral Medium 3 through OpenRouter as of 22 September 2026: Mistral. Each provider's price, context limit, quantization and measured uptime are in the providers table above.

Which benchmarks has Mistral Medium 3 been evaluated on?

Mistral Medium 3 has published results on 4 public boards tracked by ModelCap as of 22 September 2026: Arena coding 1433 (#167 of 397), BFCL V4 37.7 (#36 of 83), AA τ²-Bench Telecom 24.3% (#318 of 436) and AA Humanity's Last Exam 4.1% (#531 of 615). Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.

When was Mistral Medium 3 released?

Mistral Medium 3 first appeared in the catalogue on 7 May 2025, with a published knowledge cutoff of 2025-03-31. It has since been superseded by Mistral Medium 3.5. Rank and price movements since then are recorded on the site's changes feed.