Novita AI

Model Libraries & GPU Cloud - Deploy, Scale & Innovate

Visit Website Write a review

Starting price: $0.01/Mt -
Pricing: Free plan

Novita AIVisit Website

About Novita AI

Novita AI is the AI-native cloud for builders and agents. It lets teams run models, scale GPUs, and build AI agents from a single platform without managing infrastructure.

Key Features

For teams evaluating AI workloads, the platform combines model access, GPU resources, and agent tooling to support end-to-end development and deployment:

Serverless Model APIs

Run 200+ models through a single API. No infrastructure to manage. Text, image, audio, and video — all serverless and production-ready. You call it, we run it. Billed by the token, not the hour.

GPU Cloud & Scaling

Elastic GPU capacity to run large models and agent workloads, with auto-scaling and isolated environments. Pay-as-you-go pricing.

Agent Sandbox & Builder Tools

Build and test AI agents on the platform; includes a sandbox, access to agent docs, and straightforward deployment workflows.

Model Catalog & Integrations

Access 200+ models across LLM, image, audio, and video via one API; examples include GLM, Qwen, DeepSeek, and Kimi; per-model pricing shown in the catalog.

Summary

Best for data science teams, AI product engineers, and platform-ops teams deploying AI agents and models at scale.

Pricing

View pricing

Plans and prices as listed on novita.ai as of Oct 3, 2026.

Apodex 1.1 Mini

Free / -

Input Free
Output Free

Ling 3.1 Flash

Free / -

Input Free
Output Free

Ling 3.0 Flash Sante

Free / -

Input Free
Output Free

BAAI:BGE-M3

$0.01 /Mt / -

Llama 3.1 8B Instruct

$0.02 /Mt / -

Input $0.02 /Mt
Output $0.05 /Mt

DeepSeek OCR 2

$0.03 /Mt / -

Input $0.03 /Mt
Output $0.03 /Mt

AutoGLM Phone 9B Multilingual

$0.035 /Mt / -

Input $0.035 /Mt
Output $0.138 /Mt

Mistral Nemo

$0.04 /Mt / -

Input $0.04 /Mt
Output $0.17 /Mt

OpenAI GPT OSS 20B

$0.04 /Mt / -

Input $0.04 /Mt
Output $0.15 /Mt

NVIDIA Nemotron 3 Nano 30B A3B

$0.05 /Mt / -

Input $0.05 /Mt
Output $0.2 /Mt

OpenAI GPT OSS 120B

$0.05 /Mt / -

Input $0.05 /Mt
Output $0.25 /Mt

Llama 3 8B Lunaris

$0.05 /Mt / -

Input $0.05 /Mt
Output $0.05 /Mt

Llama 3 8B Stheno V3.2

$0.05 /Mt / -

Input $0.05 /Mt
Output $0.05 /Mt

Ling 3.0 Flash

$0.06 /Mt / -

Input $0.06 /Mt
Cache Read $0.012 /Mt
Output $0.18 /Mt

GLM 4.7 Flash

$0.07 /Mt / -

Input $0.07 /Mt
Cache Read $0.01 /Mt
Output $0.4 /Mt

Qwen3 Coder 30B A3B Instruct

$0.07 /Mt / -

Input $0.07 /Mt
Output $0.27 /Mt

qwen/qwen3-embedding-0.6b

$0.07 /Mt / -

Qwen3 Embedding 8B

$0.07 /Mt / -

Ling 3.0 Flash Fin

$0.075 /Mt / -

Input $0.075 /Mt
Cache Read $0.015 /Mt
Output $0.22 /Mt

Ling 3.0 Flash VL

$0.075 /Mt / -

Input $0.075 /Mt
Cache Read $0.015 /Mt
Output $0.22 /Mt

Qwen3 235B A22B Instruct 2507

$0.09 /Mt / -

Input $0.09 /Mt
Output $0.58 /Mt

Gemma 3 27B

$0.119 /Mt / -

Input $0.119 /Mt
Output $0.2 /Mt

GLM 4.5 Air

$0.13 /Mt / -

Input $0.13 /Mt
Cache Read $0.025 /Mt
Output $0.85 /Mt

Gemma 4 26B A4B

$0.13 /Mt / -

Input $0.13 /Mt
Output $0.4 /Mt

Llama 3.3 70B Instruct

$0.135 /Mt / -

Input $0.135 /Mt
Output $0.4 /Mt

DeepSeek V4 Flash

$0.14 /Mt / -

Input $0.14 /Mt
Cache Read $0.028 /Mt
Output $0.28 /Mt

Gemma 4 31B

$0.14 /Mt / -

Input $0.14 /Mt
Output $0.4 /Mt

Hy3

$0.14 /Mt / -

Input $0.14 /Mt
Cache Read $0.035 /Mt
Output $0.58 /Mt

MiMo V2.6 Flash

$0.14 /Mt / -

Input $0.14 /Mt
Cache Read $0.0028 /Mt
Output $0.28 /Mt

GLM 5.3 Flash

$0.15 /Mt / -

Input $0.15 /Mt
Cache Read $0.03 /Mt
Output $0.5 /Mt

Qwen3.8 Flash

$0.15 /Mt / -

Input $0.15 /Mt
Cache Read $0.016 /Mt
Output $0.47 /Mt

Qwen3 Next 80B A3B Instruct

$0.15 /Mt / -

Input $0.15 /Mt
Output $1.5 /Mt

Llama 4 Scout Instruct

$0.18 /Mt / -

Input $0.18 /Mt
Output $0.59 /Mt

Qwen3 Coder Next

$0.2 /Mt / -

Input $0.2 /Mt
Output $1.5 /Mt

Qwen3 235B A22B

$0.2 /Mt / -

Input $0.2 /Mt
Output $0.8 /Mt

Qwen3 VL 30B A3B Instruct

$0.2 /Mt / -

Input $0.2 /Mt
Output $0.7 /Mt

Step 3.7 Flash

$0.2 /Mt / -

Input $0.2 /Mt
Cache Read $0.04 /Mt
Output $1.15 /Mt

Macaron V1 Tall

$0.2475 /Mt / -

Input $0.2475 /Mt
Cache Read $0.044 /Mt
Output $1.43 /Mt

Qwen3.6 35B A3B

$0.248 /Mt / -

Input $0.248 /Mt
Output $1.485 /Mt

Qwen3.5 35B A3B

$0.25 /Mt / -

Input $0.25 /Mt
Output $2 /Mt

Qwen MT Plus

$0.25 /Mt / -

Input $0.25 /Mt
Output $0.75 /Mt

Llama 4 Maverick Instruct

$0.27 /Mt / -

Input $0.27 /Mt
Output $0.85 /Mt

DeepSeek V4.1 Flash

$0.3 /Mt / -

Input $0.3 /Mt
Cache Read $0.006 /Mt
Output $1.2 /Mt

GLM 4.6V

$0.3 /Mt / -

Input $0.3 /Mt
Cache Read $0.055 /Mt
Output $0.9 /Mt

Qwen3.5 27B

$0.3 /Mt / -

Input $0.3 /Mt
Output $2.4 /Mt

Qwen3 VL 235B A22B Instruct

$0.3 /Mt / -

Input $0.3 /Mt
Output $1.5 /Mt

Qwen3 235B A22B Thinking 2507

$0.3 /Mt / -

Input $0.3 /Mt
Output $3 /Mt

MiniMax M2.7

$0.3 /Mt / -

Input $0.3 /Mt
Cache Read $0.06 /Mt
Output $1.2 /Mt

MiniMax M2.5

$0.3 /Mt / -

Input $0.3 /Mt
Cache Read $0.03 /Mt
Output $1.2 /Mt

MiniMax M2.1

$0.3 /Mt / -

Input $0.3 /Mt
Cache Read $0.03 /Mt
Output $1.2 /Mt

MiniMax M2

$0.3 /Mt / -

Input $0.3 /Mt
Cache Read $0.03 /Mt
Output $1.2 /Mt

Qwen3 Coder 480B A35B Instruct

$0.38 /Mt / -

Input $0.38 /Mt
Output $1.55 /Mt

Qwen2.5 72B Instruct

$0.38 /Mt / -

Input $0.38 /Mt
Output $0.4 /Mt

Qwen3.5 122B A10B

$0.4 /Mt / -

Input $0.4 /Mt
Output $3.2 /Mt

Qwen3.8 27B

$0.42 /Mt / -

Input $0.42 /Mt
Cache Read $0.085 /Mt
Output $3 /Mt

MiMo V2.6 Pro

$0.435 /Mt / -

Input $0.435 /Mt
Cache Read $0.0036 /Mt
Output $0.87 /Mt

DeepSeek V4 Flash Vision Exp

$0.44 /Mt / -

Input $0.44 /Mt
Cache Read $0.028 /Mt
Output $1.32 /Mt

DeepSeek V4 Flash 0731

$0.44 /Mt / -

Input $0.44 /Mt
Cache Read $0.028 /Mt
Output $1.32 /Mt

GLM 4.6

$0.55 /Mt / -

Input $0.55 /Mt
Cache Read $0.11 /Mt
Output $2.2 /Mt

MiniMax M1

$0.55 /Mt / -

Input $0.55 /Mt
Output $2.2 /Mt

Kimi K2 Instruct

$0.57 /Mt / -

Input $0.57 /Mt
Output $2.3 /Mt

GLM 4.7

$0.6 /Mt / -

Input $0.6 /Mt
Cache Read $0.11 /Mt
Output $2.2 /Mt

GLM 4.5V

$0.6 /Mt / -

Input $0.6 /Mt
Cache Read $0.11 /Mt
Output $1.8 /Mt

Kimi K2.5

$0.6 /Mt / -

Input $0.6 /Mt
Cache Read $0.1 /Mt
Output $3 /Mt

Kimi K2 Thinking

$0.6 /Mt / -

Input $0.6 /Mt
Cache Read $0.15 /Mt
Output $2.5 /Mt

Kimi K2 Instruct 0905

$0.6 /Mt / -

Input $0.6 /Mt
Output $2.5 /Mt

Qwen3.6 27B

$0.6 /Mt / -

Input $0.6 /Mt
Output $3.6 /Mt

Qwen3.5 397B A17B

$0.6 /Mt / -

Input $0.6 /Mt
Output $3.6 /Mt

MiniMax M2.5 Highspeed

$0.6 /Mt / -

Input $0.6 /Mt
Cache Read $0.03 /Mt
Output $2.4 /Mt

WizardLM 2 8x22B

$0.62 /Mt / -

Input $0.62 /Mt
Output $0.62 /Mt

DeepSeek R1 0528

$0.7 /Mt / -

Input $0.7 /Mt
Cache Read $0.35 /Mt
Output $2.5 /Mt

DeepSeek R1 Turbo

$0.7 /Mt / -

Input $0.7 /Mt
Output $2.5 /Mt

Kimi K2.6

$0.8 /Mt / -

Input $0.8 /Mt
Cache Read $0.16 /Mt
Output $3.4 /Mt

Macaron V1 Venti

$0.825 /Mt / -

Input $0.825 /Mt
Cache Read $0.165 /Mt
Output $2.475 /Mt

Hy4 Preview

$0.834 /Mt / -

Input $0.834 /Mt
Cache Read $0.042 /Mt
Output $2.501 /Mt

Kimi K2.7 Code

$0.95 /Mt / -

Input $0.95 /Mt
Cache Read $0.19 /Mt
Output $4 /Mt

Qwen3 VL 235B A22B Thinking

$0.98 /Mt / -

Input $0.98 /Mt
Output $3.95 /Mt

GLM 5

$1 /Mt / -

Input $1 /Mt
Cache Read $0.2 /Mt
Output $3.2 /Mt

Qwen3.7 Max

$1.25 /Mt / -

Input $1.25 /Mt
Cache Read $0.25 /Mt
Output $3.75 /Mt

DeepSeek V4 Pro 0813

$1.32 /Mt / -

Input $1.32 /Mt
Cache Read $0.044 /Mt
Output $3.96 /Mt

GLM 5.1

$1.38 /Mt / -

Input $1.38 /Mt
Cache Read $0.26 /Mt
Output $4.4 /Mt

GLM 5.3

$1.4 /Mt / -

Input $1.4 /Mt
Cache Read $0.26 /Mt
Output $4.4 /Mt

GLM 5.2

$1.4 /Mt / -

Input $1.4 /Mt
Cache Read $0.26 /Mt
Output $4.4 /Mt

Llama 3.1 70B Euryale V2.2

$1.48 /Mt / -

Input $1.48 /Mt
Output $1.48 /Mt

DeepSeek V4 Pro

$1.6 /Mt / -

Input $1.6 /Mt
Cache Read $0.135 /Mt
Output $3.2 /Mt

Qwen3.8 2.4T A95B

$2 /Mt / -

Input $2 /Mt
Cache Read $0.25 /Mt
Output $6 /Mt

Qwen3.8 Max

$2 /Mt / -

Input $2 /Mt
Cache Read $0.25 /Mt
Output $6 /Mt

Kimi K3

$3 /Mt / -

Input $3 /Mt
Cache Read $0.3 /Mt
Output $15 /Mt

Qwen3 Max

- / -

Input -
Output Tiered pricing

Qwen3 Omni 30B A3B Thinking

- / -

Input -
Output Omnimodal

Qwen3 Omni 30B A3B Instruct

- / -

Input -
Output Omnimodal

MiniMax M3

- / -

Input -
Output Tiered pricing

The company behind Novita AI

Founded: 2024
Headquarters: San Francisco, United States
Employees: 11–50
Website: novita.ai
Social: LinkedIn

More in Inference

See all →

Baseten

Inference Platform: Deploy AI models in production

Cerebras

The world's fastest AI inference on the biggest wafer chip

DeepInfra

Machine Learning Models and Infrastructure

Fireworks AI

Own Your Specialized Intelligence

Modal

High-performance AI infrastructure

Nebius

The Ultimate AI Cloud

The company behind Novita AI

Founded: 2024
Headquarters: San Francisco, United States
Employees: 11–50
Website: novita.ai
Social: LinkedIn