Microsoft·microsoft/phi-4
Phi 4 is ModelCap current-board rank #207 with Index 13.8 (Measured), from the ModelCap Index as of 22 Sept 2026, 02:49 UTC.
Phi 4 listed OpenRouter input price is $0.07 per 1M tokens and listed output price is $0.14 per 1M tokens, from OpenRouter listed prices as of 22 Sept 2026, 02:49 UTC.
Phi 4 has a published context limit of 16K tokens in the ModelCap catalogue as of 22 Sept 2026, 02:49 UTC.
Phi 4 has 1 published OpenRouter serving endpoint, from OpenRouter as of 22 Sept 2026, 02:49 UTC.
Phi 4 weight access is open weights, from ModelCap classification of published repository metadata as of 22 Sept 2026, 02:49 UTC.
Snapshot facts · download the public dataset · methodology
Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.
Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. They remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.
BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.
These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.
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.
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 Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.
OpenRouter weekly popularity across the full model catalogue.
Independent providers versus the model's open or closed cohort, weighted by uptime.
Hugging Face 30-day downloads for open models; neutral for closed models.
Time since first public availability, on a six-month half-life.
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.
Models within 3 places of #207 on the ModelCap Index.
Index score within 3 points of, or above, this model's, with a lower listed blended price (3:1 input:output).
The same publisher's other current models with a public Index position.
Phi 4 holds ModelCap Index position #207 of 248 ranked language models as of 22 September 2026, with an Index score of 13.8 (interval 8.8–18.8); evidence: measured. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.
Phi 4 is listed at $0.07 per 1M input tokens and $0.14 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 $0.21 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.
Phi 4 has a published context window of 16K tokens (16,384) and a maximum output of 15K tokens. Individual providers can serve less than the published maximum; the providers table lists each endpoint's own limit.
Open weights (mit). 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. The repository is microsoft/phi-4 on Hugging Face.
One provider serves Phi 4 through OpenRouter as of 22 September 2026: DeepInfra. Each provider's price, context limit, quantization and measured uptime are in the providers table above.
Phi 4 has published results on 4 public boards tracked by ModelCap as of 22 September 2026: Arena coding 1306 (#292 of 397), BFCL V4 28.8 (#52 of 83), AA τ²-Bench Telecom 0.0% (#414 of 436) and AA Humanity's Last Exam 3.8% (#554 of 615). Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.
Phi 4 ranks #207 (Index 13.8) and Olmo Hybrid 7B ranks #208 (Index 13.7) on the ModelCap Index as of 22 September 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.
Phi 4 first appeared in the catalogue on 10 Jan 2025, with a published knowledge cutoff of 2024-06-30. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.