Skip to main content

Novita AI

Inference host

Novita AI runs open and licensed models on its own hardware and sells them by usage, often faster or cheaper than the maker.

PricingDocssupport@novita.ai
Visit novita.ai
Models83
Cheapest for
5 models
Serves
3 model types
Visits in September 2026303K−4.1%Unique visitors 122K
  1. Apr
  2. May
  3. Jun
  4. Jul
  5. Aug
  6. Sep
Models by type

Models on Novita AI

ModelInputOutputvs officialContext
Kimi K3$3/1M$15/1M
from $8.28 at Kenari
+8%—
GLM-5.3$1.40/1M$4.40/1M
from $1.10 at NanoGPT
±0%—
Qwen3.8 2.4T A95B$2/1M$6/1M
from $4.11 at APIMart
±0%—
DeepSeek V4.1 Flash$0.30/1M$1.20/1M
from $0.03 at UnoRouter
+3900%—
GLM-5.3-Flash$0.15/1M$0.50/1M
from $0.20 at APIMart
±0%—
Qwen3.8 27B$0.42/1M$3/1M
from $0.50 at EmpirioLabs AI
±0%—
GLM-5.2$1.40/1M$4.40/1M
from $1.80 at Deep Infra
±0%—
MiMo-V2.6-Pro$0.435/1M$0.87/1M
from $0.696 at CometAPI
+25%—
DeepSeek V4 Flash Vision Exp$0.30/1M$1.20/1M
from $0.294 at Deep Infra
+100%—
DeepSeek V4 Pro$1.60/1M$3.20/1M
from $0.418 at OpenRouter
+666%—
Ling 3.1 Flash$0.30/1M$0.90/1M
from $0.225 at Deep Infra
+300%—
GPT OSS 120B$0.05/1M$0.25/1M
from $0.14 at Requesty
+79%—
MiniMax-M3.1-Flash$0.15/1M$0.60/1M
from $0.45 at EmpirioLabs AI
±0%—
MiMo-V2.6-Flash$0.14/1M$0.28/1M
from $0.10 at UnoRouter
+180%—
Kimi K2 Instruct$0.57/1M$2.30/1M
from $1.68 at APIMart
+37%—
MiniMax-M3$0.30/1MFrom$1.20/1M
from $0.90 at EmpirioLabs AI
±0%—
Qwen3.8 Max$2/1M$6/1M
from $4.11 at APIMart
+21%—
GLM-5$1/1M$3.20/1M
from $1.28 at APIMart
±0%—
DeepSeek R1$0.70/1M$2.50/1M
from $1.79 at APIMart
+40%—
Kimi K2.5$0.60/1M$3/1M
from $0.555 at APIMart
+440%—
Qwen3.8 Flash$0.15/1M$0.47/1M
from $0.309 at APIMart
+23%—
BGE M3$0.01/1M$0.01/1M——
Qwen3.6 35B-A3B$0.248/1M$1.49/1M
from $0.95 at Deep Infra
-34%—
Kimi K2.6$0.80/1M$3.40/1M
from $2.40 at APIYI
-9%—
MiniMax M2.5$0.30/1M$1.20/1M
from $0.95 at Venice AI
+26%—
Llama 4 Maverick$0.27/1M$0.85/1M
from $0.20 at AIHubMix
+325%—
Llama 4 Scout 17B Instruct$0.18/1M$0.59/1M
from $0.20 at AIHubMix
+195%—
GLM-4.7-Flash$0.07/1M$0.40/1M——
GLM-5.1$1.38/1M$4.40/1M
from $1.44 at APIMart
±0%—
Ling 3.0 Flash (free)$0.06/1M$0.18/1M
from $0.063 at OpenRouter
+186%—
GLM-4.7$0.60/1M$2.20/1M
from $1.10 at AIHubMix
±0%—
GLM-4.6$0.55/1M$2.20/1M
from $1.10 at AIHubMix
±0%—
Gemma 4$0.14/1M$0.40/1M
from $0.30 at FastRouter
+33%—
Kimi K2.7 Code HighSpeed$0.95/1M$4/1M
from $2.76 at Kenari
+7%—
Llama-3.3-70B-Instruct$0.135/1M$0.40/1M
from $0.32 at Deep Infra
+25%—
Qwen3.6 27B$0.60/1M$3.60/1M
from $2 at OpenRouter
±0%—
DeepSeek V4 Flash 0731$0.44/1M$1.32/1M
from $0.133 at OpenRouter
+890%—
Qwen3.5 397B-A17B$0.60/1M$3.60/1M
from $0.986 at AIHubMix
+249%—
Llama 3.1 8B Instruct$0.02/1M$0.05/1M——
Qwen3.7 Max$1.25/1M$3.75/1M-24%—
Qwen3.5 35B-A3B$0.25/1M$2/1M
from $0.451 at AIHubMix
±0%—
Gemma 3 27B$0.119/1M$0.20/1M
from $0.16 at Deep Infra
+25%—
GLM-4.5-Air$0.13/1M$0.85/1M
from $0.291 at ZenMux
-23%—
Gemma 4 26B A4B IT$0.13/1M$0.40/1M
from $0.225 at OpenRouter
-33%—
Qwen3.5 27B$0.30/1M$2.40/1M
from $0.677 at AIHubMix
±0%—
BGE Reranker v2 M3$0.01/1M$0.01/1M——
Gemma 3 12B IT$0.05/1M$0.10/1M——
GLM-4.6V$0.30/1M$0.90/1M
from $0.411 at AIHubMix
±0%—
Nemotron 3 Nano 30B A3BCheapest$0.05/1M$0.20/1M——
AutoGLM Phone 9B Multilingual$0.035/1M$0.138/1M——

Novita AI at a glance

83 models in total: 80 text, 2 reranking, 1 embedding. The cheapest is BGE M3 at $0.01 /1M. Llama 4 Scout 17B Instruct has the largest context window, 1.31M tokens. The most searched is Kimi K3, with about 658K Google searches a month. The newest is Kimi K3.1 Pro Highspeed, released Oct 23, 2026.

Cheapest

  1. BGE M3$0.01/1M
  2. BGE Reranker v2 M3$0.01/1M
  3. PaddleOCR VL$0.02/1M
  4. DeepSeek OCR 2$0.03/1M
  5. Llama 3.1 8B Instruct$0.05/1M

Largest context

  1. Llama 4 Scout 17B Instruct1.31M
  2. Kimi K31.05M
  3. GLM-5.31.05M
  4. DeepSeek V4.1 Flash1.05M
  5. GLM-5.3-Flash1.05M

Most searched

  1. Kimi K3658K
  2. GLM-5.3276K
  3. Qwen3.8 2.4T A95B234K
  4. DeepSeek V4.1 Flash138K
  5. GLM-5.3-Flash121K

Newest

  1. Kimi K3.1 Pro HighspeedOct 23, 2026
  2. Ling 3.0 Flash SanteOct 19, 2026
  3. DeepSeek V4 Flash Vision ExpOct 17, 2026
  4. MiniMax-M3.1-FlashOct 17, 2026
  5. Ling 3.1 FlashOct 13, 2026