Pricing that scales from
idea to enterprise

Start building in seconds on serverless. Upgrade to private, compliant deployments in your cloud or ours.

Confidential Inference

Unlimited autoscaling and priority
compute access

What’s Included:

What’s Included:

What’s Included:

Proof receipts

Instant start, autoscaling

Simple SDKs & API

Enterprise

Full control in your cloud and ours

What’s Included:

What’s Included:

What’s Included:

Atoma’s security platform

Run in your cloud or ours

Custom SLAs & priority support

Pay per token for confidential inference on the most
in-demand models, with autoscaling based on your needs.

Pay per token for confidential inference on the most in-demand models, with autoscaling based on your needs.

Model

Input

Output

GPT OSS 120B

GPT OSS 120B

GPT OSS 120B

$0.10

$0.45

DeepSeek V3 0324

DeepSeek V3 0324

DeepSeek V3 0324

$0.70

$0.70

Qwen 3 Coder 480B

Qwen 3 Coder 480B

Qwen 3 Coder 480B

$0.35

$0.35

Kimi K2

Kimi K2

Kimi K2

$0.50

$2.20

Let’s Build Secure AI Together

Join NVIDIA, Equinix, and others shaping
the next era of confidential AI.

Let’s Build Secure AI Together

Join NVIDIA, Equinix, and others shaping
the next era of confidential AI.

Let’s Build Secure AI Together

Join NVIDIA, Equinix, and others shaping
the next era of confidential AI.

Secure AI infrastructure for
the future of innovation

A secure foundation for GenAI applications powered
by Confidential Computing

A secure foundation for GenAI applications powered by
Confidential Computing

Product

Product

Use cases

Use cases

Docs

Docs

Pricing

Pricing

© 2025 Atoma. All rights reserved.