Skip to content

Novita AI

Pricing page

454 listings across 174 models

Page 4 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

26 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
Kimi K2 0905
$0.60$2.50262KNot measured
Qwen 3 235B A22Bnovita/qwen/qwen3-235b-a22b-fp8 · fp8
$0.20$0.8041KNot measured
MiMo V2 Flash
$0.11cache read $0.024$0.33262KNot measured
Qwen3 Codernovita/qwen/qwen3-coder-480b-a35b-instruct
$0.38$1.55262KNot measured
MiniMax M2
$0.30cache read $0.03$1.20205KNot measuredNot measured
GLM 4.6v
Not enough data yet$0.30cache read $0.055$0.90131KNot measuredNot measured
GPT OSS 120Bfp4
$0.05$0.25131K
$0.20$1.50262KNot measured
$0.15$1.50131KNot measuredNot measured
GLM 4.5 Airbf16
$0.13cache read $0.025$0.85131KNot measuredNot measured
Not enough data yet$0.07$0.27160KNot measuredNot measured
GLM 4.7 Flashbf16
$0.07cache read $0.01$0.40200KNot measuredNot measured
GLM 4.5V
Not enough data yet$0.60cache read $0.11$1.8066KNot measuredNot measured
Qwen3 32Bnovita/qwen/qwen3-32b-fp8 · fp8
$0.10$0.4541KNot measured
DeepSeek V3
$0.89$0.8964K
DeepSeek V3novita/deepseek/deepseek-v3-0324 · 0324
$0.27cache read $0.135$1.12164K
Qwen3 30B A3Bnovita/qwen/qwen3-30b-a3b-fp8 · fp8
$0.09$0.4541KNot measured
GLM 4 32Bnovita/thudm/glm-4-32b-0414 · 0414
Not enough data yet$0.55$1.6632KNot measuredNot measured
Qwen3 8Bnovita/qwen/qwen3-8b-fp8 · fp8
$0.035$0.138128KNot measured
Llama 4 Mavericknovita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8 · fp8
$0.27$0.851M
qwen3-vl-30bnovita/qwen/qwen3-vl-30b-a3b-thinking · thinking
Not enough data yet$0.20$1.00131KNot measuredNot measured
qwen3-vl-30bqwen/qwen3-vl-30b-a3b-instruct
Not enough data yet$0.20$0.70131KNot measuredNot measured
GPT OSS 20bfp4
$0.04$0.15131K
Not enough data yet$0.07—33KNot enough data yetNot measuredNot measured
Not enough data yet$0.06$0.09128KNot measuredNot measured
$0.05$0.20262KNot measuredNot measured

Run by Novita AI

36 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
Kimi K2 0905fp8
 OpenRouter$0.60$2.50262KNot measured
 Hugging Face$0.20$0.8041KNot measured
MiMo V2 Flash
 Hugging Face$0.10$0.30262KNot measured
Qwen3 CoderQwen/Qwen3-Coder-480B-A35B-Instruct
 Hugging Face$0.30$1.30262KNot measured
MiniMax M2
 Hugging Face$0.30$1.20205KNot measuredNot measured
GLM 4.6v
 LlmgatewayNot enough data yet$0.30cache read $0.055$0.90Not published by the providerNot measuredNot measured
GPT OSS 120B
 Hugging Face$0.05$0.25131K
 Hugging Face$0.20$1.50262KNot measured
 Hugging Face$0.15$1.50131KNot measuredNot measured
GLM 4.5 Air
 Hugging Face$0.13$0.85131KNot measuredNot measured
Kimi K2moonshotai/kimi-k2-instruct
 Llmgateway$0.57$2.30Not published by the providerNot measured
GLM 4.7 Flash
 Hugging Face$0.07$0.40200KNot measuredNot measured
GLM 4.5V
 Hugging FaceNot enough data yet$0.60$1.8066KNot measuredNot measured
Qwen3 32B
 Hugging Face$0.10$0.4541KNot measured
DeepSeek V3
 Hugging Face$0.40$1.3064K
 Hugging Face$0.09$0.4541KNot measured
GLM 4 32Bzai-org/GLM-4-32B-0414 · 0414
 Hugging FaceNot enough data yet$0.55$1.6632KNot measuredNot measured
Llama 4 Maverickmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · fp8
 Hugging Face$0.27$0.851M
qwen3-vl-30bQwen/Qwen3-VL-30B-A3B-Thinking · thinking
 Hugging FaceNot enough data yet$0.20$1.00131KNot measuredNot measured
GPT OSS 20b
 Hugging Face$0.04$0.15131K
Show all 36 listings

Showing 20 of 36: one listing for each model.

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

How this data works