Deca

Deca

Smarter, Faster, Cheaper: Deca 2.5 now available. Surpasses Grok-4 and Gemini 2.5 Pro on major benchmarks. Available now via the API.

Deca 2.5
Smarter
GPT 5:
Deca 2.5 Ultra:
Grok 4:
Deca 2.5 Pro:
Gemini 2.5 Pro:
Claude Opus 4.1:
GPT-5-nano:
Deca 2.5 Mini:
GPT-4.1:
Gemini 2.5 Flash:
View Benchmark Methodology
Faster
Deca 2.5 Pro Turbo:
Gemini 2.5 Pro:
Deca 2.5 Pro:
GPT 5:
Deca 2.5 Mini:
Grok 4:
Claude 4.1 Opus:
Cheaper
Claude 4.1 Opus:
Grok 4:
Claude 4 Sonnet:
GPT 4.1:
GPT 5:
Gemini 2.5 Pro:
Deca 2.5 Pro:
GPT 5 Mini:
Deca 2.5 Mini:
-->

Meet the models

Deca 2.5 mini

deca-2.5-mini

Small but intelligent model for everyday tasks.

Normal:
$0.35 /MTok in
$0.99 /MTok out
Turbo:
Up to 4000 tokens per second at zero load
$0.99 /MTok in
$0.99 /MTok out
160K context window

$2.50 free credits when you sign up

Deca 2.5 Pro

deca-2.5-pro

For power users who need more intelligence for less cost.

Normal:
$1.25 /MTok in
$4.00 /MTok out
Turbo:

Up to 700 tokens per second at zero load

$2.00 /MTok in
$5.50 /MTok out
160K context window

$2.50 free credits when you sign up

Deca 2.5 Ultra

deca-2.5-ultra-preview
BETA

Our bleeding-edge model for tasks requiring extreme intelligence.

Complex queries might take a long time to process, as we are scaling up our infrastructure.

Standard Pricing (Coming soon):
$7.50 /MTok in
$30.00 /MTok out
Preview Pricing:
$30.00 /MTok in
$120.00 /MTok out
1M context window

$2.50 free credits when you sign up

Deca 3 Alpha Ultra

ALPHA

Coming soon.

Latest from Deca

Deca 2.5 Series Now Available!

Experience the power and efficiency of Deca 2.5 Mini, Pro and Ultra models, designed for a wide range of applications.

Read Announcement →

Deca 2.5 Ultra: Private Beta

Our most powerful model, Deca 2.5 Ultra, is now in private beta for advanced AI research.

Learn More →

API Updates for Scalability

We've rolled out new API enhancements for even greater performance and seamless integration.

View API Docs →

Sponsored by GenLabs

Support: email [email protected]