LLM Reference

Novita AI Models — Pricing & Benchmarks

110 models available

Novita AI hosts 110 AI models in this catalog. The lowest listed input price is BGE M3 at $0.01/1M input tokens. LLM Reference lets you compare these models across all 65 providers without switching tabs.

ModelInput (per 1M)Output (per 1M)Context
BGE M3$0.018K
BGE Reranker V2 M3$0.018K
Llama 3.1 8B Instruct$0.02$0.05128K
PaddleOCR VL$0.02$0.0216K
DeepSeek OCR$0.03$0.038K
DeepSeek OCR 2$0.03$0.038K
Llama 3.2 3B Instruct$0.03$0.05128K
AutoGLM Phone 9B Multilingual$0.035$0.13866K
Qwen3-8B$0.035$0.138128K
gpt-oss-20b$0.04$0.15131K
Llama 3 8B Instruct$0.04$0.048K
Mistral NeMo (2407)$0.04$0.17128K
Gemma 3 12B$0.05$0.133K
gpt-oss-120b$0.05$0.25131K
L3 8B Lunaris$0.05$0.058K
L3 8B Stheno V3.2$0.05$0.058K
Phi-4 Mini$0.05$0.15128K
Qwen3 Reranker 8B$0.0533K
DeepSeek R1 0528 Qwen3-8B$0.06$0.09160K
Baichuan M2 32B$0.07$0.07131K
ERNIE 4.5 21B A3B$0.07$0.28120K
ERNIE 4.5 21B A3B$0.07$0.28120K
GLM-4.7 Flash$0.07$0.4198K
Qwen2.5-7B-Instruct$0.07$0.07128K
Qwen3 Embedding 0.6B$0.0733K
Qwen3 Embedding 8B$0.0733K
Qwen3-Coder-30B-A3B-Instruct$0.07$0.27
Mistral NeMo Instruct (2407)$0.08$0.24128K
Qwen3 VL 8B Instruct$0.08$0.5128K
MythoMax L2 13B$0.09$0.094K
Qwen3-235B-A22B$0.09$0.58128K
Qwen3-30B-A3B$0.09$0.45128K
Ling-2.6-Flash$0.1$0.3262K
Ling-2.6-Flash$0.1$0.3262K
Qwen3-32B$0.1$0.4540K
Xiaomi MiMo-V2-Flash$0.1$0.3262K
Gemma 3 27B$0.119$0.2131K
DeepSeek Coder V2 Lite Instruct$0.12$0.36128K
Gemma 4 26B A4B IT$0.13$0.4256k
GLM-4.5-Air$0.13$0.85128K
Llama 3.3 70B Instruct (free)$0.135$0.466K
DeepSeek V4 Flash$0.14$0.281M
ERNIE 4.5 VL 28B A3B$0.14$0.5630K
Gemma 4 31B IT$0.14$0.4256k
Hermes 2 Pro Llama 3 8B$0.14$0.148K
DeepSeek R1 Distill Qwen-14B$0.15$0.15128K
Qwen3-Next-80B-A3B$0.15$1.5
Qwen3-Next-80B-A3B$0.15$1.5
Llama 4 Scout 17B-16E Instruct$0.18$0.59328K
Qwen3 VL 30B A3B Instruct$0.2$0.7128K
Qwen3 VL 30B A3B Instruct$0.2$1128K
Qwen3-235B-A22B$0.2$0.8128K
Qwen3-Coder-Next$0.2$1.5256K
Qwen3.6-35B-A3B$0.248$1.485262K
Qwen-MT-Plus$0.25$0.75
Qwen3 Omni 30B A3B$0.25$0.9766K
Qwen3 Omni 30B A3B$0.25$0.9766K
Qwen3.5-35B-A3B$0.25$2262K
DeepSeek V3.2$0.269$0.4160K
DeepSeek V3 0324$0.27$1.12160K
DeepSeek V3.1$0.27$164K
DeepSeek V3.1 Terminus$0.27$1164K
DeepSeek V3.2 Exp$0.27$0.41164K
Llama 4 Maverick 17B Instruct FP8$0.27$0.851M
ERNIE 4.5 300B A47B$0.28$1.1123K
DeepSeek R1 Distill Qwen-32B$0.3$0.3128K
GLM 4.6V$0.3$0.9128K
KAT Coder Pro V2$0.3$1.2256K
Ling-2.6-1T$0.3$2.5262K
MiniMax M2$0.3$1.2197K
MiniMax M2.1$0.3$1.2200k
MiniMax M2.5$0.3$1.2197K
MiniMax M2.7$0.3$1.2205K
Qwen3 VL 235B A22B Instruct$0.3$1.5256K
Qwen3-235B-A22B$0.3$3128K
Qwen3.5-27B$0.3$2.4262K
Ring-2.6-1T$0.3$2.5262K
Qwen2.5-72B-Instruct$0.38$0.4128K
Qwen3-Coder-480B-A35B-Instruct$0.38$1.55256K
ERNIE 4.5 VL 28B A3B$0.39$0.3930K
Qwen3.5-122B-A10B$0.4$3.2262K
ERNIE 4.5 VL 424B A47B$0.42$1.25123K
Llama 3 70B Instruct$0.51$0.748K
GLM-4.6$0.55$2.2198K
MiniMax-M1-80k$0.55$2.280K
Kimi K2 Instruct$0.57$2.3131K
GLM 4.5V$0.6$1.864K
GLM 4.7$0.6$2.2200K
GLM-4.5$0.6$2.2128K
Kimi K2 0905 Preview$0.6$2.5262K
Kimi K2 Thinking$0.6$2.5256K
Kimi K2.5$0.6$3256K
MiniMax M2.5 Highspeed$0.6$2.4205K
Qwen3.5-397B-A17B$0.6$3.6262K
Qwen3.6-27B$0.6$3.6262K
WizardLM-2 8x22B$0.62$0.62
DeepSeek Prover V2$0.7$2.5160K
DeepSeek R1 0528$0.7$2.5130K
DeepSeek R1 Distill Llama 70B$0.8$0.8128K
Kimi K2.6$0.8$3.4262K
Qwen2.5-VL-72B$0.8$0.833K
Qwen3-VL-235B-A22B$0.98$3.95128K
GLM-5$1$3.2200k
Qwen3.7-Max$1.25$3.751M
GLM-5.1$1.38$4.4200k
L3 70B Euryale V2.1$1.48$1.488K
L3.1 70B Euryale V2.2$1.48$1.48131K
DeepSeek V4 Pro$1.64$3.381M
Xiaomi MiMo-V2.5-Pro$2$61M
Qwen3-Max$2.11$8.45128K

Pricing Overview

Cheapest$0.01/1M
Most expensive$2.11/1M