Skip to content

Novita AI

Pricing page

454 listings across 174 models

Page 2 of 8. The lists below split this page's listings into those sold by Novita AI, run by Novita AI, or sent to Novita AI by a marketplace.

Sold by Novita AI

25 listings on this page sold by Novita AI.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
DeepSeek V4 Flash 0731fp8
$0.44cache read $0.028$1.321M
Hy4 Flash
$0.035cache read $0.0015$0.14051MNot measured
Not enough data yet$0.07—33KNot enough data yetNot measuredNot measured
GLM 5.1fp8
$1.38cache read $0.26$4.40205K
$1.60cache read $0.135$3.201M
$0.60$3.60262K
GLM 5fp8
$1.00cache read $0.20$3.20203K
Qwen 3.8 27B
$0.42cache read $0.085$3.001MNot measured
DeepSeek V4 Flash
$0.14cache read $0.028$0.281M
Kimi K2.5
$0.60cache read $0.10$3.00262K
Gemma 4 31B ITbf16
$0.14$0.40262K
MiMo V2.5 Pro
$0.522cache read $0.0043$1.0441MNot measured
Hy3 (Deep Infra)tencent/hy3
$0.14cache read $0.035$0.58262KNot measuredNot measured
GLM 4.7fp8
$0.60cache read $0.11$2.20205K
MiMo V2.5fp8
$0.168cache read $0.0034$0.3361MNot measured
Kimi K2.7 Codeint4
$0.95cache read $0.19$4.00262K
GLM 5 Turbo
$1.20cache read $0.24$4.00203KNot measuredNot measured
GLM 5V Turbo
$1.20cache read $0.24$4.00205KNot measuredNot measured
MiniMax M3
$0.30cache read $0.06$1.201M
Qwen3.5 122B-A10Bbf16
$0.40$3.20262KNot measuredNot measured
Not enough data yet$0.075cache read $0.015$0.22262KNot measuredNot measured
Ling 3.0 Flashnovita/inclusionai/ling-3.0-flash-fast · fast
Not enough data yet$0.06cache read $0.012$0.18262KNot measuredNot measured
Ling 3.0 Flash
Not enough data yet$0.06cache read $0.012$0.18262KNot measuredNot measured
Qwen3.5 27Bbf16
$0.30$2.40262KNot measured
Not enough data yet$1.00cache read $0.014$1.00262KNot measuredNot measured

Run by Novita AI

74 listings on this page where Novita AI runs the model. Another provider sells these listings.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
DeepSeek V4 Flash 0731
 Hugging Face$0.44$1.321M
Hy4 Flash🇺🇸 US
 NanoGPT$0.0368cache read $0.0016$0.1475Not published by the providerNot measured
DeepSeek V4.1 Flash 0910deepseek/deepseek-v4.1-flash · fp8
 OpenRouterNot enough data yet$0.15cache read $0.003$0.601MNot enough data yetNot measuredNot measured
GLM 5.1
 Llmgateway$1.38cache read $0.26$4.40Not published by the provider
 Hugging Face$1.60$3.201M
 Hugging Face$0.60$3.60262K
GLM 5
 Hugging Face$1.00$3.20203K
Qwen 3.8 27B
 Hugging Face$0.42$3.001MNot measured
DeepSeek V4 Flashdeepseek/deepseek-v4-flash-0731
 Llmgateway$0.14cache read $0.028$0.28Not published by the provider
Kimi K2.5
 Hugging Face$0.60$3.00262K
 Hugging Face$0.14$0.40262K
Hy3 (Deep Infra)tencent/hy3
 Llmgateway$0.14cache read $0.035$0.58Not published by the providerNot measuredNot measured
GLM 4.7
 Hugging Face$0.60$2.20205K
 Hugging Face$0.95$4.00262K
MiniMax M3
 Llmgateway$0.30cache read $0.06$1.20Not published by the provider
 Hugging Face$0.40$3.20262KNot measuredNot measured
 Hugging FaceNot enough data yet$0.075$0.22262KNot measuredNot measured
Ling 3.0 Flash
 Hugging FaceNot enough data yet$0.06$0.18262KNot measuredNot measured
Qwen3.5 27B
 Hugging Face$0.30$2.40262KNot measured
Show all 74 listings

Showing 19 of 74: one listing for each model.

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works