Inkling-SmallThinking Machines Lab
|
Ling 3.0 FlashAnt Group
|
|||||
Related Products
|
||||||
About
Inkling-Small is an efficient model that offers performance comparable to Inkling at a quarter of its size. It is a Mixture-of-Experts transformer with 276 billion total parameters and 12 billion active parameters, trained on NVIDIA GB300 NVL72 systems. It supports native reasoning across text, images, and audio, variable thinking effort, and context windows of up to one million tokens. Users adjust reasoning effort from minimal to extra high to balance performance and compute. Improved pre-training data, post-training with on-policy distillation from Inkling, and extended agentic coding reinforcement learning helped Inkling-Small surpass its larger counterpart on reasoning and coding benchmarks. It performs well in coding and tool-use harnesses, exceeds 80% on SWE-bench Verified, and combines strong reasoning with efficient output. Its encoder-free multimodal architecture processes audio as dMel spectrograms and images as 40-by-40-pixel patches alongside text tokens.
|
About
Ling 3.0 Flash is a next-generation efficient language model designed for long-horizon agent workflows, combining fast response, low activation, and stable tool use. It uses a Mixture-of-Experts architecture with 124 billion total parameters and 5.1 billion activated parameters per token, providing capability while keeping inference efficient. The model supports a native 256K context window that can be extended up to 1 million tokens, with reliable retrieval across information placed at the beginning, middle, or end of long contexts. Compared with the previous Flash model, Ling 3.0 Flash improves stability on extended tasks, tool-calling accuracy, instruction following, compatibility with agent harnesses, and coding performance. Its optimized spatial understanding can construct physical scene grids and reason about relative positions, while hybrid reasoning improves success rates across tasks of varying difficulty.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
Developers, AI agent builders, software engineering teams, research teams, enterprise AI teams, multimodal application developers, coding assistant builders, tool-use workflow teams, and organizations that need efficient reasoning, long-context processing, text-image-audio understanding, adjustable thinking effort, coding performance, and scalable Mixture-of-Experts inference
|
Audience
Autonomous software testing teams that need a fast model for long-running tool-based coding and verification workflows
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
$0.30 per million input tokens
$0.30 per million input tokens and $1.20 per million output tokens
Free Version
Free Trial
|
Pricing
No information available.
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Pros & Cons from Real UsersPros
Cons
|
||||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationThinking Machines Lab
Founded: 2025
United States
thinkingmachines.ai/news/inkling-small/
|
Company InformationAnt Group
Founded: 2014
China
www.ant-ling.com
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
|
|
|
|||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
Claude Code
Hermes Agent
Kilo Code
Model Context Protocol (MCP)
OpenClaw
OpenRouter
Tinker
ZenMux
|
Integrations
Claude Code
Hermes Agent
Kilo Code
Model Context Protocol (MCP)
OpenClaw
OpenRouter
Tinker
ZenMux
|
|||||
|
|
|