Average Ratings 1 Rating
Average Ratings 0 Ratings
Description
Inkling-Small is an efficient Mixture-of-Experts transformer model built to provide performance comparable to Inkling while using a much smaller active parameter footprint. The model has 276 billion total parameters and 12 billion active parameters, making it designed for strong capability with more efficient compute usage. Inkling-Small was trained on NVIDIA GB300 NVL72 systems and supports native reasoning across text, images, and audio. It offers context windows of up to one million tokens, making it suitable for long documents, large codebases, multimodal context, and extended agent workflows. Users can set reasoning effort from minimal to extra high to control the balance between speed, cost, compute, and task complexity. The model benefits from improved pre-training data, post-training with on-policy distillation from Inkling, and extended agentic coding reinforcement learning. These improvements helped Inkling-Small surpass its larger counterpart on reasoning and coding benchmarks. Its encoder-free multimodal architecture processes audio as dMel spectrograms and images as 40-by-40-pixel patches alongside text tokens. By combining efficient MoE scaling, long-context reasoning, multimodal input, coding strength, and adjustable thinking effort, Inkling-Small is built for practical high-performance AI deployment.
Description
The Pokee-Isaac text-only agentic model features an impressive context window capable of accommodating up to 10 million tokens. This model is engineered to facilitate reasoning, planning, tool invocation, and the execution of extensive tasks, all while being compact enough for deployment within a Virtual Private Cloud (VPC), on customer premises, on a workstation, or directly on devices. According to Pokee, Isaac excels in long-context performance across the RULER benchmarks, effectively handling token ranges from 256K to 10M and outperforming competitors in multi-needle retrieval tests at 256K, 512K, and 1M tokens. Its agentic framework is specifically designed for reliable function calling, maintaining coherence over multiple turns, executing in real-shell environments, and the ability to discover and integrate tools across live Multi-Cloud Platforms (MCP) servers. In controlled assessments by Pokee, Isaac secured the top position on BFCL v4 and τ³-bench, while placing second in the Terminal-Bench 2.1 text-only subset and third in MCP-Atlas. Furthermore, security evaluations using the DTAP method indicated that it achieved the lowest overall attack success rate in the comparative analysis, all while demonstrating robust performance on benign tasks. This combination of features underscores Isaac's capability as a versatile and secure model in various operational environments.
API Access
Has API
API Access
Has API
Pricing Details
$0.30 per million input tokens
$0.30 per million input tokens and $1.20 per million output tokens
Free Trial
Free Version
Pricing Details
$0.15 per 1M tokens
Free Trial
Free Version
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Vendor Details
Company Name
Thinking Machines Lab
Founded
2025
Country
United States
Website
thinkingmachines.ai/news/inkling-small/
Vendor Details
Company Name
Pokee AI
Founded
2024
Country
United States
Website
console.pokee.ai/model