Phi-4-reasoning

Phi-4-reasoning

Microsoft
Span-01

Span-01

Respan
+
+

Related Products

  • Evertune
    1 Rating
    Visit Website
  • Buildium
    2,562 Ratings
    Visit Website
  • Checksum.ai
    2 Ratings
    Visit Website
  • TrustInSoft Analyzer
    6 Ratings
    Visit Website
  • RetailEdge
    201 Ratings
    Visit Website
  • Pipedrive
    12,537 Ratings
    Visit Website
  • AthenaHQ
    50 Ratings
    Visit Website
  • LTX
    182 Ratings
    Visit Website
  • Dialpad Support
    1,607 Ratings
    Visit Website
  • ONLYOFFICE Docs
    715 Ratings
    Visit Website

About

Phi-4-reasoning is a 14-billion parameter transformer-based language model optimized for complex reasoning tasks, including math, coding, algorithmic problem solving, and planning. Trained via supervised fine-tuning of Phi-4 on carefully curated "teachable" prompts and reasoning demonstrations generated using o3-mini, it generates detailed reasoning chains that effectively leverage inference-time compute. Phi-4-reasoning incorporates outcome-based reinforcement learning to produce longer reasoning traces. It outperforms significantly larger open-weight models such as DeepSeek-R1-Distill-Llama-70B and approaches the performance levels of the full DeepSeek-R1 model across a wide range of reasoning tasks. Phi-4-reasoning is designed for environments with constrained computing or latency. Fine-tuned with synthetic data generated by DeepSeek-R1, it provides high-quality, step-by-step problem solving.

About

Span-01 is a hyper-parallel reasoning classifier built to detect complex behaviors across long production traces in a single forward pass. Rather than generating tokens sequentially, it reasons over natural-language behavior definitions and returns direct probabilities for present, absent, and not_observable. The model is trained for general classification reasoning with RLAIF before being specialized for behavior detection, allowing it to apply previously unseen definitions to new behaviors and domains instead of relying on a fixed taxonomy. At inference time, hyper-parallel definition branches evaluate multiple behaviors against the same trace context simultaneously, while hybrid attention helps preserve reasoning over long, complex inputs. Span-01 is designed for production monitoring across safety, reliability, grounding, agent behavior, and response quality, including jailbreak and prompt injection detection, privacy, and secrets.

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Audience

Educators and developers seeking an AI tool offering models for complex reasoning tasks

Audience

AI, safety, evaluation, and observability teams seeking to detect and score complex behaviors across long production traces with fast, probability-based classification

Support

Phone Support Supported
24/7 Live Support Not Supported
Online Supported

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

API

Offers API Not Supported

API

Offers API Supported

Screenshots and Videos

Screenshots and Videos

Pricing

No information available.
Free Version Not Supported
Free Trial Not Supported

Pricing

$199 per month
Free Version Supported
Free Trial Supported

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation Supported
Webinars Supported
Live Online Supported
In Person Supported

Training

Documentation Supported
Webinars Not Supported
Live Online Supported
In Person Not Supported

Company Information

Microsoft
Founded: 1975
United States
azure.microsoft.com/en-us/blog/one-year-of-phi-small-language-models-making-big-leaps-in-ai/

Company Information

Respan
Founded: 2023
United States
www.respan.ai/blog/introducing-span-1

Alternatives

Alternatives

Clef-flash

Clef-flash

Cloudflare
Clef

Clef

Cloudflare
Open R1

Open R1

Open R1
Jev

Jev

TypeSafe AI
DeepSeek R1

DeepSeek R1

DeepSeek
Tev1

Tev1

Together AI
DeepCoder

DeepCoder

Agentica Project

Categories

AI Models Supported

Categories

AI Decision Models Supported

Integrations

AssemblyAI Not Supported
Cognee Not Supported
Google GenAI SDK Not Supported
Hugging Face Supported
JavaScript Not Supported
LangChain Not Supported
LinkUp Not Supported
LlamaIndex Not Supported
Mastra AI Not Supported
Mem0 Not Supported
Microsoft Azure Supported
Microsoft Foundry Supported
Microsoft Foundry Models Supported
OpenAI Not Supported
OpenAI Agents API Not Supported
PostHog Not Supported
Python Not Supported
TypeScript Not Supported
Vercel Not Supported

Integrations

AssemblyAI Supported
Cognee Supported
Google GenAI SDK Supported
Hugging Face Not Supported
JavaScript Supported
LangChain Supported
LinkUp Supported
LlamaIndex Supported
Mastra AI Supported
Mem0 Supported
Microsoft Azure Not Supported
Microsoft Foundry Not Supported
Microsoft Foundry Models Not Supported
OpenAI Supported
OpenAI Agents API Supported
PostHog Supported
Python Supported
TypeScript Supported
Vercel Supported
Claim Phi-4-reasoning and update features and information
Claim Phi-4-reasoning and update features and information
Claim Span-01 and update features and information
Claim Span-01 and update features and information