LLM Reference

Phi-3 Small 128K

Released
2024-05-21
Last refreshed
2026-05-19
Status
Researched 50d ago
Open sourceCommercial use: permittedCodingLong contextClassification

Phi-3 Small 128K is worth evaluating for coding, long context, and classification when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, long context, and classification
  • Workloads that can use a 128k context window
  • Buyers comparing 2 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
  • Strict JSON or tool-calling flows
Specifications
Family
Phi-3
Released
2024-05-21
Context
128k
Parameters
7B
Architecture
Decoder Only
Knowledge cutoff
2023-10
Specialization
general
Openness
Open source
License
MITOSI-approvedCommercial use: permitted
Weights
Unknown
Code
Unknown
Training
Fine-tuned
Created by

Advancing the state-of-the-art in AI and computing.

Redmond, Washington, United States
Founded 1991
Website
Pricing
Output / 1M
$1.05
Input / 1M
$0.350

Cheapest of 2 routes · Microsoft Foundry

About

Phi-3 Small 128K is Microsoft Research's Phi-3 model. It offers a 128K-token context window with weights openly available for self-hosting and scores 51.9 on GPQA.

Phi-3 Small 128K is an open-source model in the Phi-3 family. The structured metadata tracks a 128k-token context window. This page tracks provider routes through Microsoft Foundry and NVIDIA NIM, with the cheapest tracked route listed at $0.35 input and $1.05 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 51.9, HellaSwag 90.8, and HumanEval 73.8.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ C

1 relevant benchmark in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Classification

Q/$ C

2 relevant benchmarks in the decision map.

Provider price ladder

Compare all 2

Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Microsoft Foundry$0.350$1.05
ServerlessProvisioned
NVIDIA NIM--
ProvisionedPartial

Available via routers & gateways(6)

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

Benchmark scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Google-Proof Q&A51.9diamondhttps://arxiv.org/abs/2404.14219
HellaSwag90.810-shothttps://arxiv.org/abs/2404.14219
HumanEval73.8pass@1https://arxiv.org/abs/2404.14219
Massive Multitask Language Understanding78.15-shothttps://arxiv.org/abs/2404.14219

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

What is the context window of Phi-3 Small 128K?

Phi-3 Small 128K has a context window of 128k tokens.

How much does Phi-3 Small 128K cost?

Phi-3 Small 128K is available at $0.35/1M input tokens through Microsoft Foundry.

When was Phi-3 Small 128K released?

Phi-3 Small 128K was released on 2024-05-21.

Which providers offer Phi-3 Small 128K?

Phi-3 Small 128K is available from 2 providers: Microsoft Foundry, NVIDIA NIM.

What benchmarks has Phi-3 Small 128K been tested on?

Phi-3 Small 128K has been evaluated on 4 benchmarks, including Google-Proof Q&A, HellaSwag, HumanEval, Massive Multitask Language Understanding.