Microsoft

Phi 4

Launched 2024-12-11 · Knowledge up to 2023-10 · Listed on OpenRouter 2025-01-10

Prices updated . Benchmarks updated .

Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

You send / 1M

$0.070

tokens in

It replies / 1M

$0.140

tokens out

Context

128K

tokens it can read at once

Typical request

$0.0002

1,000 words in, 400 out

Benchmarks

BenchmarkScoreKindDateSource
Epoch Capabilities Index130.6Independent2024-12-12Epoch AI
GPQA Diamond56.1%Independent2025-01-31Epoch AI
OTIS Mock AIME13.8%Independent2025-02-25Epoch AI
CritPt0.0%Independent2024-12-12CritPt, republished by Epoch AI
Arena Elo (text)1,217Independent2026-10-28LMArena

Rankings on this site use the Epoch Capabilities Index, an independent composite. Lab-reported rows are the lab's own figures and are kept separate.

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

ProviderYou send / 1MIt replies / 1MUptimePrivacy policy
DeepInfra · bf16$0.056$0.112n/aRead
DeepInfra · bf16$0.070$0.140100%Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: text
  • Writes: text
  • Weights: Open weights
  • Reasoning: No
  • Tool calling: No
  • Longest reply: 4K tokens

Compare with

Appears in

Estimate your monthly cost with Phi 4

Sources and licenses

  • OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
  • Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
  • models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
  • Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
  • LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
  • Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
  • What a score measures: the benchmark guide.