Skip to content
ModelCap

Phi 4

Current board #81Arena #289Open weights

Microsoft·microsoft/phi-4

Phi 4 is a language model published by Microsoft. 1 OpenRouter endpoint is published in the latest snapshot. It accepts text input and returns text. The published context limit is 16K tokens. The catalogue declares support for structured outputs.

ModelCap Index · Current board
30.3#81
Measured · 84% support · score interval 30.3–36.9
Market Gravity
16.2
Secondary market signal
Input
$0.07
per 1M tokens
Output
$0.14
per 1M tokens
Context
16K
tokens
Providers
1
endpoint
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
DeepInfrabf16$0.07$0.1416Kbf16100.0%

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
deepinfra
live
$0.07$0.1416K280 ms70.8 tok/sstructured
featherless-ai
live
——————

Reported evaluation leads (3)

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
LEXam-Benchmark/LEXam
open_question
—38.54
Unpinned
not published
Reported
Quarantined
LEXam-Benchmark/LEXam
mcq_4_choices
—40.66
Unpinned
not published
Reported
Quarantined
TIGER-Lab/MMLU-Pro
mmlu_pro
—70.4
Unpinned
not published
Reported
Quarantined

ModelCap Index · Current board

Methodology
30.3
Measured · 3 public benchmark observations across 3 boards
Current board
#81
Public rank basis
Measured (measured)
Index support
83.9% · strong
Index interval
30.3–36.9
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · microsoft/microsoft/phi-4 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata microsoft/phi-4@2db69c1c3e91a05d2c64a3185acfbaf36f744e25 (not the evaluation revision)
Direct benchmark observations
3
Breadth-adjusted BES point estimate
33.6
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
33.6
Evidence status
confirmed · 94% mass
General preference
33.1
Coding
35.9
Agents & tools
34.7
Reasoning
—
Evidence breadth
97%
Evidence coverage
84%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
4.9
Liquidity (providers × uptime)
16.2
Open reach (HF downloads)
59.6
Surface (context / tools / modalities)
10.1
Freshness
11.2
  • · OpenRouter popularity #226
  • · 1 live provider
  • · HF 30d downloads 663989
  • · Catalogue: context 16384
  • · First seen 2025-01-10

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
83.3
strong · 94% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
76.5
Evaluation provenance
74.0

Missing: artifactReproducibility.base-lineage, 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
16.2
OpenRouter weekly popularity
#226 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
#289 of 385
Rating
1256.2
95% confidence interval
1252–1261
Votes
24K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
4.9

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%
59.6

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

Freshness5%
11.2

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

Specification

Context window
16K tokens
Max output
16K tokens
Inputs
Text
Outputs
Text
Tokenizer
Other
Cached input tokens
Not offered
First seen on OpenRouter
10 Jan 2025
Knowledge cutoff
2024-06-30

Capabilities

  • Not supported: Reasoning
  • Not 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
mit
Pinned revision
2db69c1c3e91
Parameters
14.7B
Architecture
Phi3ForCausalLM
Model type
phi3
Hugging Face downloads (30d)
664K
Downloads (all time)
13.4M
Likes
2K
Repository
microsoft/phi-4
Repository updated
14 Jul 2026, 14:22 UTC