Skip to content
ModelCap

Mixtral 8x22B Instruct

Current board #86Arena #301Open weights

Mistral AI·mistralai/mixtral-8x22b-instruct

Mixtral 8x22B Instruct is a language model published by Mistral AI. 1 OpenRouter endpoint is published in the latest snapshot. It accepts text, file input and returns text. The published context limit is 66K tokens. The catalogue declares support for tool use, structured outputs.

ModelCap Index · Current board
27.2#86
Measured · 82% support · score interval 27.2–34.2
Market Gravity
10.5
Secondary market signal
Input
$2.00
per 1M tokens
Output
$6.00
per 1M tokens
Context
66K
tokens
Providers
1
endpoint
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Mistral$2.00$6.0066K——

Reported evaluation leads (1)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
TIGER-Lab/MMLU-Pro
mmlu_pro
—56.33
Unpinned
not published
Reported
Quarantined

ModelCap Index · Current board

Methodology
27.2
Measured · 2 public benchmark observations across 2 boards
Current board
#86
Public rank basis
Measured (measured)
Index support
81.8% · strong
Index interval
27.2–34.2
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · mistralai/mistralai/mixtral-8x22b-instruct · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata mistralai/Mixtral-8x22B-Instruct-v0.1@cc88a6cc19fbd17d9f1c0ee0b0d70a748dce698d (not the evaluation revision)
Direct benchmark observations
2
Breadth-adjusted BES point estimate
30.7
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
30.7
Evidence status
confirmed · 83% mass
General preference
30.3
Coding
32.0
Agents & tools
—
Reasoning
—
Evidence breadth
92%
Evidence coverage
82%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
4.3
Liquidity (providers × uptime)
16.2
Open reach (HF downloads)
25.7
Surface (context / tools / modalities)
55.2
Freshness
4.0
  • · OpenRouter popularity #233
  • · 1 live provider
  • · HF 30d downloads 61294
  • · Catalogue: context 65536, tools, modalities Text/File
  • · First seen 2024-04-17

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
82.9
strong · 98% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
100.0
Deployability
74.7
Evaluation provenance
52.5

Missing: 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
10.5
OpenRouter weekly popularity
#233 of 298

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
Arena
Official rank
#301 of 385
Rating
1229.0
95% confidence interval
1224–1234
Votes
51K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
98%

Market Gravity breakdown

Usage55%
4.3

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
16.2

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

Open reach15%
25.7

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

Freshness5%
4.0

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

Specification

Context window
66K tokens
Max output
—
Inputs
Text, File
Outputs
Text
Tokenizer
Mistral
Cached input tokens
$0.20 / 1M
First seen on OpenRouter
17 Apr 2024
Knowledge cutoff
2024-01-31

Capabilities

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

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
apache-2.0
Pinned revision
cc88a6cc19fb
Parameters
140.6B
Architecture
MixtralForCausalLM
Model type
mixtral
Hugging Face downloads (30d)
61K
Downloads (all time)
6.2M
Likes
756
Repository
mistralai/Mixtral-8x22B-Instruct-v0.1
Repository updated
24 Jul 2025, 16:41 UTC
Base lineage
mistralai/Mixtral-8x22B-v0.1