Inkling 2 Small

Inkling 2 Small

Thinking Machines Lab
Phi-4-reasoning

Phi-4-reasoning

Microsoft
+
+

Related Products

  • Gemini Enterprise Agent Platform
    4.3 out of 5 stars 1,178 Ratings
    Visit Website for Gemini Enterprise Agent Platform
  • LTX
    4.4 out of 5 stars 182 Ratings
    Visit Website for LTX
  • Nexo
    4.4 out of 5 stars 18,841 Ratings
    Visit Website for Nexo
  • Josys
    4.4 out of 5 stars 263 Ratings
    Visit Website for Josys
  • Checksum.ai
    5.0 out of 5 stars 2 Ratings
    Visit Website for Checksum.ai
  • Dialpad Support
    4.4 out of 5 stars 1,629 Ratings
    Visit Website for Dialpad Support
  • Creatio
    4.6 out of 5 stars 589 Ratings
    Visit Website for Creatio
  • SearchUnify
    4.5 out of 5 stars 150 Ratings
    Visit Website for SearchUnify
  • Cloverleaf
    4.8 out of 5 stars 189 Ratings
    Visit Website for Cloverleaf
  • GWI
    4.4 out of 5 stars 201 Ratings
    Visit Website for GWI

About

Inkling 2 Small is a multimodal AI model developed by Thinking Machines Lab for advanced reasoning, autonomous software engineering, visual understanding, and AI agent development. The model uses a mixture-of-experts architecture with 594 billion total parameters and 17 billion active parameters to balance intelligence and computational efficiency. It supports text and image inputs, a context window of up to one million tokens, and configurable reasoning effort for tasks requiring different levels of analysis. Its agentic capabilities enable autonomous code generation, debugging, website development, scientific research, and complex multistep workflows involving external tools. Inkling 2 Small also supports fine-tuning and reinforcement learning through Thinking Machines Lab's Tinker platform, allowing developers to customize the model for specialized applications.

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.

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

AI developers, machine learning engineers, software developers, autonomous agent researchers, data scientists, AI research laboratories, DevOps professionals, computational scientists, enterprise AI teams, and organizations seeking multimodal language models, long-context reasoning, AI coding agents, reinforcement learning, model fine-tuning, visual understanding, and autonomous research capabilities

Audience

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

Support

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

Support

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

API

Offers API Supported

API

Offers API Not Supported

Screenshots and Videos

Screenshots and Videos

Pricing

$0.30 per million input tokens
$0.30 per million input tokens, $0.03 per million cached input tokens, and $1.00 per million output tokens
Free Version Not Supported
Free Trial Not Supported

Pricing

No information available.
Free Version Not Supported
Free Trial Not 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 Not Supported
Live Online Not Supported
In Person Not Supported

Training

Documentation Supported
Webinars Supported
Live Online Supported
In Person Supported

Company Information

Thinking Machines Lab
Founded: 2025
United States
thinkingmachines.ai/

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/

Alternatives

GPT-6 Luna

GPT-6 Luna

OpenAI
5.0 out of 5 stars

Alternatives

Kimi K3.1 Pro

Kimi K3.1 Pro

Moonshot AI
5.0 out of 5 stars
DeepSeek R1

DeepSeek R1

DeepSeek
5.0 out of 5 stars
Inkling-Small

Inkling-Small

Thinking Machines Lab
5.0 out of 5 stars
Open R1

Open R1

Open R1
Inkling

Inkling

Thinking Machines Lab
DeepSeek-V4.1-Flash-1017

DeepSeek-V4.1-Flash-1017

DeepSeek
5.0 out of 5 stars

Categories

Categories

Integrations

Hugging Face Not Supported
Microsoft Azure Not Supported
Microsoft Foundry Not Supported
Microsoft Foundry Models Not Supported
Model Context Protocol (MCP) Supported
Tinker Supported

Integrations

Hugging Face Supported
Microsoft Azure Supported
Microsoft Foundry Supported
Microsoft Foundry Models Supported
Model Context Protocol (MCP) Not Supported
Tinker Not Supported
Claim Inkling 2 Small and update features and information
Claim Inkling 2 Small and update features and information
Claim Phi-4-reasoning and update features and information
Claim Phi-4-reasoning and update features and information