DEDICATED ENDPOINT

Run Your Models,
We Handle the Rest

Deploy models on dedicated GPUs. Per-second billing on running replicas only, affordable GPU options starting at $0.61/hr, and inference issues are on us.

Start Deploying See Price

Pay only for what's running

Per-second billing on active replicas. Scale to zero, pay zero. No charges for idle endpoints, no minimum commitments.

Billing preview

3 replicas 4090 × 2h 15m 42s running

= 3 × 8,142s × $0.000608/s

= $14.85

GPUs for every budget

Not every workload needs an H200. Choose from RTX 4090, RTX 5090, H100 — match the GPU to your model size and your budget.

RTX 4090

24 GB

from $0.61/hr

RTX 5090

32 GB

from $0.73/hr

H100

80 GB

from $1.99/hr

H200

141 GB

from $2.99/hr

Inference breaks? That's on us.

OOM, CUDA errors, model loading failures — our team diagnoses and resolves. You get a clear explanation, not a cryptic stack trace.

Report via console or email

Our team investigates root cause

You get diagnosis + resolution

Deployment options

Serverless vs Dedicated

Choose the right deployment model for your workload

Serverless Endpoints

Pay per token
600+ models available
Zero infrastructure management
Auto-scaling included
Best for variable workloads

Recommended for production

Dedicated Endpoints

Isolated GPU resources
Guaranteed latency SLA
Custom models & LoRA adapters
Scale-to-zero support
Best for predictable, high-throughput workloads

Platform

Built for Production Workloads

Everything you need to deploy, scale, and manage AI inference in production.

Blazing-Fast Inference

Powered by optimized serving engines on NVIDIA H200, H100, and RTX 4090 GPUs. Sub-second latency for real-time applications.

Dynamic Auto-Scaling

Scale from 0 to N replicas automatically based on traffic. Set min/max replicas and scale-down delay to match your traffic patterns.

LoRA Adapter Support

Hot-swap LoRA adapters on running endpoints without restarts. Deploy multiple fine-tuned variants on a single base model.

Flexible GPU Options

Choose from NVIDIA H200, H100, and RTX 4090. Select tensor parallelism and GPU count to match your model requirements.

Pay-Per-Hour Billing

Billed by GPU-hour with per-second granularity. Scale to zero when idle — no minimum commitment, no idle GPU costs.

Enterprise Support

Dedicated technical support, custom SLAs, and priority access to new GPU types. Volume discounts for large deployments.

Catalog

Deploy Popular Open-Source Models

One-click deploy the most popular LLMs, or bring your own Hugging Face model.

Workflow

Deploy in 3 Steps

Everything you need to deploy, scale, and manage AI inference in production.

001

Pick your model

Search 50K+ models from Hugging Face, or paste your private repo URL.

Search models... e.g. Qwen2.5-7B

OCR Models: PaddleOCR、GOT-OCR、...

Reranker Models: BGE-Reranker、...

LLM Models: DeepSeek、GLM、...

002

Choose your GPU

See the recommended GPU for your model. Pick the one that fits your budget.

RTX 4090 · $0.61/hr

H100 · $1.99/hr

H200 · $2.99/hr

Replicas

003

Deploy

Your endpoint is live in minutes. OpenAI-compatible URL ready to use.

Endpoint

Live

POST

api.example.com/v1/chat/completions

Pricing

Transparent GPU Pricing

GPU	VRAM	Price / GPU-hour
NVIDIA H200 SXMPopular	141 GB	$2.99
NVIDIA H100 SXM	80 GB	$1.99
NVIDIA RTX 4090	24 GB	$0.61

Need reserved capacity or custom pricing?

Talk to our team

FAQ

Frequently Asked Questions

Per-second on running replicas only. When your endpoint is scaled to zero or stopped, you pay nothing. No minimum commitments, no idle charges.

Still have questions? Contact support

Everything you need to build production AI.

200+ models, on-demand GPUs, and secure agent runtimes — unified under one API. Free to start, scales as you grow.

Name	Provider	Purpose	Maximum Storage Duration	Type
cf.turnstile.u	Cloudflare	This cookie is used to distinguish between humans and bots.	Persistent	HTML Local Storage
__cf_bm [x3]	novita.cyou Twitter Inc.	This cookie is used to distinguish between humans and bots. This is beneficial for the website, in order to make valid reports on the use of their website.	1 day	HTTP Cookie
CookieConsent	Cookiebot	Stores the user's cookie consent state for the current domain	1 year	HTTP Cookie
dmn_chk_#	us-assets.i.posthog.com	Used to maintain the overall functionality of the website: Assigns the user to a server and detects potential errors on specific servers, allowing the website to reassign the users to another server.	Session	HTTP Cookie
redirect	novita.cyou	Used to redirect the user to the same page on the website before and after the login-process.	Session	HTTP Cookie
token	novita.cyou	Ensures visitor browsing-security by preventing cross-site request forgery. This cookie is essential for the security of the website and visitor.	Session	HTTP Cookie

Name	Provider	Purpose	Maximum Storage Duration	Type
intercom.intercom-state-# [x2]	Intercom novita.cyou	Remembers whether the user has minimized or closed chat-box or pop-up messages on the website.	Persistent	HTML Local Storage
category	novita.cyou	Necessary in order to optimize the website's search-bar function. The cookie ensures accurate and fast search results.	Persistent	HTML Local Storage
intercom-device-id-#	Intercom	Sets a specific ID for the user which ensures the integrity of the website’s chat function.	271 days	HTTP Cookie
intercom-id-#	Intercom	Allows the website to recoqnise the visitor, in order to optimize the chat-box functionality.	271 days	HTTP Cookie
intercom-session-#	Intercom	Sets a specific ID for the user which ensures the integrity of the website’s chat function.	7 days	HTTP Cookie
novita-theme	novita.cyou	Pending	Persistent	HTML Local Storage

Name	Provider	Purpose	Maximum Storage Duration	Type
c.gif	Microsoft	Collects data on the user’s navigation and behavior on the website. This is used to compile statistical reports and heatmaps for the website owner.	Session	Pixel Tracker
_clck	Microsoft	Collects data on the user’s navigation and behavior on the website. This is used to compile statistical reports and heatmaps for the website owner.	1 year	HTTP Cookie
_clsk	Microsoft	Registers statistical data on users' behaviour on the website. Used for internal analytics by the website operator.	1 day	HTTP Cookie
_ga	Google	Used to send data to Google Analytics about the visitor's device and behavior. Tracks the visitor across devices and marketing channels.	2 years	HTTP Cookie
_ga_#	Google	Used to send data to Google Analytics about the visitor's device and behavior. Tracks the visitor across devices and marketing channels.	2 years	HTTP Cookie
AMP_#	novita.cyou	Registers statistical data on users' behaviour on the website. Used for internal analytics by the website operator.	1 year	HTTP Cookie
AMP_MKTG_#	novita.cyou	Registers statistical data on users' behaviour on the website. Used for internal analytics by the website operator.	1 year	HTTP Cookie
AMP_remote_config_1b7cfa159c	novita.cyou	Pending	Persistent	HTML Local Storage
AMP_TEST	novita.cyou	Registers statistical data on users' behaviour on the website. Used for internal analytics by the website operator.	Session	HTTP Cookie
AMP_TLDTEST	novita.cyou	Registers statistical data on users' behaviour on the website. Used for internal analytics by the website operator.	Session	HTTP Cookie
AMP_unsent_#	novita.cyou	Registers statistical data on users' behaviour on the website. Used for internal analytics by the website operator.	Persistent	HTML Local Storage
landingpage	novita.cyou	Detects and stores which landing page was presented to the user.	Session	HTTP Cookie
ph_#_posthog	us-assets.i.posthog.com	Registers statistical data on users' behaviour on the website. Used for internal analytics by the website operator.	Session	HTTP Cookie
_cltk	Microsoft	Registers statistical data on users' behaviour on the website. Used for internal analytics by the website operator.	Session	HTML Local Storage
personalization_id	Twitter Inc.	This cookie is set by Twitter - The cookie allows the visitor to share content from the website onto their Twitter profile.	400 days	HTTP Cookie
ph_#_primary_window_exists	us-assets.i.posthog.com	Registers statistical data on users' behaviour on the website. Used for internal analytics by the website operator.	Session	HTML Local Storage
ph_#_window_id	us-assets.i.posthog.com	Registers statistical data on users' behaviour on the website. Used for internal analytics by the website operator.	Session	HTML Local Storage

Name	Provider	Purpose	Maximum Storage Duration	Type
sib_cuid [x2]	Sendinblue novita.cyou	Collects information on the user's website navigation and preferences - This is used to target potential newsletter based upon this information.	6 months	HTTP Cookie
MR [x2]	Microsoft	Used to track visitors on multiple websites, in order to present relevant advertisement based on the visitor's preferences.	7 days	HTTP Cookie
MUID [x2]	Microsoft	Used widely by Microsoft as a unique user ID. The cookie enables user tracking by synchronising the ID across many Microsoft domains.	1 year	HTTP Cookie
SRM_B	Microsoft	Tracks the user’s interaction with the website’s search-bar-function. This data can be used to present the user with relevant products or services.	1 year	HTTP Cookie
ANONCHK	Microsoft	Registers data on visitors from multiple visits and on multiple websites. This information is used to measure the efficiency of advertisement on websites.	1 day	HTTP Cookie
SM	Microsoft	Registers a unique ID that identifies the user's device during return visits across websites that use the same ad network. The ID is used to allow targeted ads.	Session	HTTP Cookie
test_cookie	Google	Pending	1 day	HTTP Cookie
pagead/1p-user-list/#	Google	Tracks if the user has shown interest in specific products or events across multiple websites and detects how the user navigates between sites. This is used for measurement of advertisement efforts and facilitates payment of referral-fees between websites.	Session	Pixel Tracker
_gcl_au	Google	Used to measure the efficiency of the website’s advertisement efforts, by collecting data on the conversion rate of the website’s ads across multiple websites.	3 months	HTTP Cookie
_twpid	static.ads-twitter.com	Pending	Session	HTTP Cookie
landingpage	novita.cyou	Pending	Persistent	HTML Local Storage
source	novita.cyou	Registers how the user has reached the website to enable pay-out of referral commission fees to partners.	Session	HTTP Cookie
source	novita.cyou	Registers how the user has reached the website to enable pay-out of referral commission fees to partners.	Persistent	HTML Local Storage
utm_campaign	novita.cyou	Collects information on user preferences and/or interaction with web-campaign content - This is used on CRM-campaign-platform used by website owners for promoting events or products.	Persistent	HTML Local Storage
utm_campaign	novita.cyou	Collects information on user preferences and/or interaction with web-campaign content - This is used on CRM-campaign-platform used by website owners for promoting events or products.	1 day	HTTP Cookie
utm_medium	novita.cyou	Collects information on user preferences and/or interaction with web-campaign content - This is used on CRM-campaign-platform used by website owners for promoting events or products.	Session	HTTP Cookie
utm_medium	novita.cyou	Detects how the user reached the website by registering their last URL-address.	Persistent	HTML Local Storage
utm_source	novita.cyou	Determines how the user accessed the website. This information is used by the website operator in order to measure the efficiency of their marketing.	Session	HTTP Cookie
utm_source	novita.cyou	Determines how the user accessed the website. This information is used by the website operator in order to measure the efficiency of their marketing.	Persistent	HTML Local Storage
1/i/adsct [x2]	Twitter Inc.	Collects data on user behaviour and interaction in order to optimize the website and make advertisement on the website more relevant.	Session	Pixel Tracker
muc_ads	Twitter Inc.	Collects data on user behaviour and interaction in order to optimize the website and make advertisement on the website more relevant.	400 days	HTTP Cookie
guest_id	Twitter Inc.	Collects data related to the user's visits to the website, such as the number of visits, average time spent on the website and which pages have been loaded, with the purpose of personalising and improving the Twitter service.	400 days	HTTP Cookie
guest_id_ads	Twitter Inc.	Collects information on user behaviour on multiple websites. This information is used in order to optimize the relevance of advertisement on the website.	400 days	HTTP Cookie
guest_id_marketing	Twitter Inc.	Collects information on user behaviour on multiple websites. This information is used in order to optimize the relevance of advertisement on the website.	400 days	HTTP Cookie
_gcl_ls	Google	Tracks the conversion rate between the user and the advertisement banners on the website - This serves to optimise the relevance of the advertisements on the website.	Persistent	HTML Local Storage

Name	Provider	Purpose	Maximum Storage Duration	Type
_twsid	static.ads-twitter.com	Pending	Session	HTTP Cookie
california-privacy	novita.cyou	Pending	1 day	HTTP Cookie
consent-jurisdiction	novita.cyou	Pending	1 day	HTTP Cookie
cookiebot-enabled	novita.cyou	Pending	1 day	HTTP Cookie
de	novita.cyou	Pending	Persistent	HTML Local Storage
from	novita.cyou	Pending	Persistent	HTML Local Storage
gpc-detected	novita.cyou	Pending	1 day	HTTP Cookie
gpu	novita.cyou	Pending	Persistent	HTML Local Storage
model	novita.cyou	Pending	Persistent	HTML Local Storage
modelId	novita.cyou	Pending	Persistent	HTML Local Storage
models-console:multimodal-playground:configs	novita.cyou	Pending	Persistent	HTML Local Storage
ph_phc_akuvuvfL4LTuWUazF1g3PUR22rfQs8UJCKtIZWjIQie_posthog_cpm	us-assets.i.posthog.com	Pending	Session	HTTP Cookie
provider	novita.cyou	Pending	Persistent	HTML Local Storage
redirect	novita.cyou	Pending	Persistent	HTML Local Storage
sandbox	novita.cyou	Pending	Persistent	HTML Local Storage
spot	novita.cyou	Pending	Persistent	HTML Local Storage
type	novita.cyou	Pending	Persistent	HTML Local Storage
ph_phc_akuvuvfL4LTuWUazF1g3PUR22rfQs8UJCKtIZWjIQie_session_registered_properties	us-assets.i.posthog.com	Pending	Session	HTML Local Storage