Model Markets
Get Free API KeyAPI

Microsoftphi-4

External Link

phi-4 is an open-weight language model published by Microsoft.

Token context
16K tokens
Inputs
Text
Outputs
Text
Released
Dec 12, 2024

Benchmark Market Position

Intelligence, Cost, and Efficiency

All rankings →

Intelligence

Rank #43 of 57

  1. 100.0*Claude Opus 5.5
  2. 99.0Claude Fable 5.1
  3. 90.9*GPT-5.5 Pro
  4. 90.0Gemini 3.8 Flash
  5. 85.9GPT-6.1 Sol
  6. 84.6GPT-6 Astra
  7. 83.4*Qwen3.8 Max
  8. 83.3*DeepSeek V4.1 Flash
  9. 82.1Gemini 3.1 Pro
  10. 77.3GPT-5.6 Terra
  11. 74.0*Grok 4.7
  12. 73.5*ERNIE 5.1
  13. 73.3Kimi K3
  14. 71.9*GLM 5.3
  15. 67.5*Qwen3.8 Flash
  16. 64.3*Grok 4.20 Multi Agent
  17. 63.3*Qwen3.7 Plus
  18. 63.1*Claude Sonnet 5
  19. 57.9*DeepSeek V4 Pro
  20. 56.2*GLM 5.3 Flash
  21. 54.6*Mistral Large 4
  22. 54.3*Gemma 4 31B
  23. 52.2Qwen3.8 27B
  24. 50.5*Qwen3.5 397B A17B
  25. 50.1*Hy3
  26. 47.4*Gemma 4 26B A4B
  27. 47.4Inkling
  28. 43.0*Mistral Large 3
  29. 42.3GPT-6 Luna
  30. 37.8*NVIDIA Nemotron 3 Ultra 550B A55B BF16
  31. 35.2*Inkling Small
  32. 33.9*MiniMax M3
  33. 27.0*Kimi K2.7 Code
  34. 25.1*Grok Build 0.1
  35. 20.8GPT-5.4 Mini
  36. 17.8Gemini 3.5 Flash Lite
  37. 17.2*Qwen3.5 35B A3B
  38. 15.7GPT-5.4 Nano
  39. 12.8*Muse Glimmer 30B
  40. 11.7*Solar Pro 4
  41. 9.3*Claude Haiku 4.5
  42. 0.4*DeepSeek R1
  43. 0.0*Olmo 3 32B Think
  44. 0.0*Nova 2 Lite
  45. 0.0*Command A
  46. 0.0*Granite 4.2 30B
  47. 0.0*Granite 4.2 3B
  48. 0.0*Granite 4.2 8B
  49. 0.0*Llama 4 Maverick 17B 128E Instruct
  50. 0.0*Llama 4 Scout 17B 16E Instruct
  51. 0.0*phi-4
  52. 0.0*NVIDIA Nemotron 3 Nano 30B A3B BF16
  53. 0.0*NVIDIA Nemotron 3.5 Lightning 30B A3B
  54. 0.0*GPT-4o
  55. 0.0*GPT-4o Mini
  56. 0.0*gpt-oss-120b
  57. 0.0*gpt-oss-20b
* Provisional: fewer than 3 sources
View full ranking →

Cost

Not ranked in current cohort

Cost not rankedPublished LiveBench output tokens and a current USD output rate are both required.
View full ranking →

Efficiency

Not ranked in current cohort

Efficiency not rankedBoth an eligible intelligence score and a comparable cost estimate are required.
* Provisional: fewer than 3 sources
View full ranking →

The orange outline marks phi-4. Each available panel preserves its real rank and value; missing benchmark or pricing inputs remain explicitly unranked.

Providers & Pricing

Estimate workload cost →
ProviderInput / 1MOutput / 1MCache read / 1MCache write / 1MObservedEvidence
$0.070$0.14——Oct 19, 2026Provider-reported
$0.070$0.14——Oct 19, 2026Provider-reported

Benchmarks

All benchmark results →
Berkeley Function Calling Leaderboardv4-ede5081a24bc28.79percent——Phi-4 (Prompt)unknownRecomputedwinner eligibleThird-party benchmark
LMArena Text Arenatext-2026-10-15-a64ca3b12b6e1,216.66rating—24,126phi-4; 95% CI [1212.07369450, 1221.23689100]; votes 24126; rank 314unknownOriginal sourcewinner eligibleThird-party benchmark

At a Glance

Model Facts

Identity

Status
active
Developer ID
microsoft/phi-4
Released
Dec 12, 2024
Version
phi-4
License
mit

Capacity

Token context
16K tokens
Maximum output
Unknown
Total parameters
14.7B
Active parameters
Unknown
Knowledge cutoff
Not reported

Interface and Access

Inputs
Text
Outputs
Text
API available
Yes
Open weights
Yes
Self-hostable
Yes
Reasoning
No
Vision
No
Tool calling
No
Capabilities
chat, generation

This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.

Version Lineage

PredecessorUnknown
SuccessorsUnknown
Aliasesmicrosoft/phi-4, microsoft/phi-4

Explicit Unknowns

  • Maximum output
  • Knowledge cutoff

Primary Evidence

Sources and Observation Date

microsoft/phi-4 developer model repositoryMicrosoft · observed Aug 28, 2026Deepinfra catalogDeepinfra · observed Oct 19, 2026OpenRouter microsoft/phi-4 model APIOpenRouter · observed Aug 28, 2026microsoft/phi-4 Hugging Face inference-provider mappingHugging Face · observed Aug 28, 2026microsoft/phi-4 config.json at 2db69c1c3e91Microsoft · observed Aug 28, 2026microsoft/phi-4 immutable Hub API metadataMicrosoft · observed Aug 28, 2026microsoft/phi-4 README.md at 2db69c1c3e91Microsoft · observed Aug 28, 2026microsoft/phi-4 tokenizer_config.json at 2db69c1c3e91Microsoft · observed Aug 28, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026Openrouter catalogOpenrouter · observed Oct 19, 2026

Comparable Peers

Related Model Comparisons

All comparisons →
APairBContext
vsfamily variantstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vsfamily variantstext
vsfamily variantstext
vsfamily variantstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext

Questions

phi-4 FAQs

What is phi-4?+

phi-4 is an open-weight language model published by Microsoft. It is developed by Microsoft and its current sourced lifecycle status is active.

What inputs and outputs does phi-4 support?+

phi-4's current record lists Text as input and Text as output.

How much context does phi-4 support?+

The current record lists a 16K-token context window and does not report a maximum output length.

Is phi-4 available through an API?+

phi-4 is marked as API-available. The directly sourced provider records currently include Deepinfra, Hugging Face, and Openrouter.

How large is phi-4?+

The current record lists 14.7B total parameters and an unknown active parameter count. Its architecture is Phi3ForCausalLM.

What capabilities and tasks does phi-4 support?+

phi-4's recorded capabilities are chat and generation. Its supported tasks are text.

How much does phi-4 cost through an API?+

The lowest directly sourced prices currently attached to phi-4 are $0.070 per million input tokens through Deepinfra and $0.14 per million output tokens through Deepinfra. Prices are provider-specific and should be checked against each cited observation date.

Can phi-4 be self-hosted?+

phi-4 is an open-weight model. Self-hosting is supported, and the recorded license is mit.

Does phi-4 have related versions or aliases?+

No predecessor is recorded. No successor is recorded. Recorded aliases are microsoft/phi-4.

Which models can phi-4 be compared with?+

The current compatible peer set includes Phi-4 Reasoning, Molmo2 8B, MolmoWeb 4B, MolmoWeb 8B, and Olmo 3 7B Instruct. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →

Send Feedback