aitoolcompass.

Find your next AI tool

Search by product name or task. Press Escape to close.

PeriFlow

● Identity checked

Assistant · Vendor site 2026-10-04

PeriFlow is the former name for Friendli Inference, FriendliAI’s optimized serving engine and cloud for large generative models. Teams now deploy through Friendli Model APIs, Dedicated Endpoints, and Serverless Endpoints with the same low-latency stack described in Friendli engineering posts.

Updated 2026-10-04View sources
Official website
Category
Assistant
Free access
Not confirmed
API access
Friendli pricing centers on Model APIs, Dedicated Endpoints, and BYOG deployments with token or GPU-hour billing and documented API keys.

Is PeriFlow right for you?

A good fit for

ML engineers and agent builders who need high-throughput LLM inference rather than a general writing assistant UI.

Before you choose

FriendliAI pricing is usage- and infrastructure-based with per-token or GPU rates instead of flat monthly SaaS tiers on the public pricing page.

From PeriFlow to Friendli Inference

FriendliAI now brands its PeriFlow serving engine as Friendli Inference, exposing the same optimized LLM deployment stack through APIs and managed endpoints.

What it can do

Features & capabilities

Unknown is different from unavailable. Each fact carries its own evidence.

CapabilityValueEvidenceChecked
PeriFlow lineageFriendli blog states Friendli Inference was also known as PeriFlow or Orca for transformer serving.Facts sourced2026-10-04
Inference cloudFriendli homepage markets a frontier inference cloud with model APIs and dedicated GPU endpoints.Facts sourced2026-10-04
API keysPricing FAQ explains issuing API keys from FriendliAI settings for Model API access.Facts sourced2026-10-04

Understand the total cost

PeriFlow pricing & plans

Pricing

Not listed

Official monthly price not confirmed

API
Friendli pricing centers on Model APIs, Dedicated Endpoints, and BYOG deployments with token or GPU-hour billing and documented API keys.
PeriFlow pricing, plans and price history

Alternatives to PeriFlow

View all ↗

The practical questions

Frequently asked questions

How can I issue an API Key?

FriendliAI’s pricing FAQ directs users to the API Keys settings page to create a personal key tied to their default team limits.

What is PeriFlow used for?

PeriFlow is the former name for Friendli Inference, FriendliAI’s optimized serving engine and cloud for large generative models. Teams now deploy through Friendli Model APIs, Dedicated Endpoints, and Serverless Endpoints with the same low-latency stack described in Friendli engineering posts.

Does PeriFlow have a free plan?

Not confirmed. This record does not confirm an ongoing free plan.

How much does PeriFlow cost?

A listed monthly price has not been confirmed. See the plan cards for entitlements, billing commitments and seat minimums.

Can I use PeriFlow through an API?

Friendli pricing centers on Model APIs, Dedicated Endpoints, and BYOG deployments with token or GPU-hour billing and documented API keys.. API access and subscription access may have different terms; consult the linked sources.

What should I check before choosing it?

FriendliAI pricing is usage- and infrastructure-based with per-token or GPU rates instead of flat monthly SaaS tiers on the public pricing page.

Price history

No retained pricing changes yet. A current price alone does not establish a historical trend.

How this profile is supported

Facts apply to the named version and check date. Send a sourced correction if something changed.