Deca

AI will touch every problem worth solving. Deca builds frontier models that are just as capable as they are efficient.

Scroll to explore the future of agentic AI.

Introducing Deca 2.6

Deca 2.6

Introducing Deca 2.6

Deca 2.6 is our most capable model family yet. Use it in , with the API,

Deca Chat

Deca 2.6 is our most capable model family yet.

Tool Use

Deca natively hooks into web browsing, terminal, and file systems to accomplish complex multi-step workflows.

Fast & Efficient

Engineered from the ground up to minimize latency and token costs without sacrificing reasoning quality.

API Access

Integrate Deca into your own products. Fully compatible with OpenAI standards for drop-in replacement.

Meet the Models

Choose the perfect model for your needs. From everyday tasks to complex research.

Deca 2.6 Micro

deca-2.6-micro

Ultra-efficient for simple tasks and high-volume pipelines.

Input
$0.05 /MTok
Output
$0.25 /MTok
Cached input
$0.0125 /MTok
Context: 128K tokens

Deca 2.6 Mini

deca-2.6-mini

Balanced cost and capability for everyday coding and analysis.

Input
$0.20 /MTok
Output
$1.00 /MTok
Cached input
$0.05 /MTok
Context: 1M tokens

Input tokens beyond 128k are billed at 2× the standard input rate.

Deca 2.6 Pro

deca-2.6-pro

High intelligence for security audits, architecture, and complex builds.

Input
$0.80 /MTok
Output
$4.00 /MTok
Cached input
$0.20 /MTok
Context: 1M tokens

Input tokens beyond 128k are billed at 2× the standard input rate.

Deca 2.6 Ultra

deca-2.6-ultra

Frontier intelligence for math proofs, research, and the hardest problems.

Input
$3.20 /MTok
Output
$16.00 /MTok
Cached input
$0.80 /MTok
Context: 1M tokens

At Deca, we build AI that does more with less.

The Deca Manifesto Our view on what AI should be, and why the industry is missing the mark.
Mar 2026
Deca