$ AICostSaverbeta
Sign in
NA

Novita AI

synced

Website ↗ API docs ↗
ModelTypeInputOutputContextLast sync
L3 Llama 3.1 8B Instruct meta-llama LLM $0.02 $0.05 16,384
L3 Llama 3.2 1B Instruct meta-llama LLM $0.02 $0.02 131,000
PV paddlepaddle/paddleocr-vl None LLM $0.02 $0.02 16,384
DO deepseek/deepseek-ocr-2 None LLM $0.03 $0.03 8,192
ZO zai-org/autoglm-phone-9b-multilingual None LLM $0.035 $0.138 65,536
MN Mistral Nemo mistralai LLM $0.04 $0.17 60,288
GO gpt-oss-20b (batch) openai LLM $0.04 $0.15 131,072
G3 Gemma 3 12B google LLM $0.05 $0.1 131,072
N3 Nemotron 3 Nano 30B A3B nvidia LLM $0.05 $0.2 262,144
S8 Sao10K/L3-8B-Stheno-v3.2 None LLM $0.05 $0.05 8,192
GO gpt-oss-120b (batch) openai LLM $0.05 $0.25 131,072
S8 sao10k/l3-8b-lunaris None LLM $0.05 $0.05 8,192
L3 Ling 3.0 Flash inclusionai LLM $0.06 $0.18 262,144
DR deepseek/deepseek-r1-0528-qwen3-8b None LLM $0.06 $0.09 128,000
G4 GLM 4.7 Flash z-ai LLM $0.07 $0.4 200,000
QC Qwen3 Coder 30B A3B Instruct qwen LLM $0.07 $0.27 160,000
BM baichuan/baichuan-m2-32b None LLM $0.07 $0.07 131,072
B4 baidu/ernie-4.5-21B-a3b None LLM $0.07 $0.28 120,000
L3 Ling 3.0 Flash Fin inclusionai LLM $0.075 $0.22 262,144
L3 Ling 3.0 Flash VL inclusionai LLM $0.075 $0.22 262,144
M1 MythoMax 13B gryphe LLM $0.09 $0.09 4,096
Q2 Qwen3 235B A22B Instruct 2507 qwen LLM $0.09 $0.58 131,072
G3 Gemma 3 27B google LLM $0.119 $0.2 98,304
G4 GLM 4.5 Air z-ai LLM $0.13 $0.85 131,072
G4 google/gemma-4-26B-A4B-it None LLM $0.13 $0.4 262,144
L3 Llama 3.3 70B Instruct meta-llama LLM $0.135 $0.4 12,288
H Hy3 tencent LLM $0.14 $0.58 262,144
MV MiMo-V2.6-Flash xiaomi Transcription $0.14 $0.28 1,048,576
DV deepseek/deepseek-v4-flash None LLM $0.14 $0.28 1,048,576
G4 google/gemma-4-31B-it None LLM $0.14 $0.4 262,144
N2 nousresearch/hermes-2-pro-llama-3-8b None LLM $0.14 $0.14 8,192
QN Qwen3 Next 80B A3B Instruct qwen LLM $0.15 $1.5 131,072
Q8 Qwen3.8 Flash qwen LLM $0.15 $0.47 1,000,000
ZO zai-org/GLM-5.3-Flash None LLM $0.15 $0.5 1,048,576
MV MiMo-V2.5 xiaomi Transcription $0.168 $0.336 1,048,576
L4 Llama 4 Scout meta-llama LLM $0.18 $0.59 131,072
QC Qwen3 Coder Next qwen LLM $0.2 $1.5 262,144
QV Qwen3 VL 30B A3B Instruct qwen LLM $0.2 $0.7 131,072
S3 Step 3.7 Flash stepfun LLM $0.2 $1.15 262,144
Q2 qwen/qwen3-235b-a22b-fp8 None LLM $0.2 $0.8 40,960
MV mindai/macaron-v1-tall None LLM $0.2475 $1.43 262,144
Q6 Qwen3.6 35B A3B qwen LLM $0.248 $1.485 262,144
Q5 Qwen3.5-35B-A3B qwen LLM $0.25 $2 262,144
QM qwen/qwen-mt-plus None LLM $0.25 $0.75 16,384
QO qwen/qwen3-omni-30b-a3b-instruct None LLM $0.25 $0.97 65,536
QO qwen/qwen3-omni-30b-a3b-thinking None LLM $0.25 $0.97 65,536
ML meta-llama/llama-4-maverick-17b-128e-instruct-fp8 None LLM $0.27 $0.85 1,048,576
B baidu/cobuddy None LLM $0.28 $1.13 131,072
G4 GLM 4.6V z-ai LLM $0.3 $0.9 131,072
MM MiniMax M2 minimax LLM $0.3 $1.2 204,800
MM MiniMax M2.1 minimax LLM $0.3 $1.2 204,800
MM MiniMax M2.5 minimax LLM $0.3 $1.2 204,800
MM MiniMax M2.7 minimax LLM $0.3 $1.2 204,800
MM MiniMax M3 minimax LLM $0.3 $1.2 1,000,000
Q2 Qwen3 235B A22B Thinking 2507 qwen LLM $0.3 $3 131,072
QV Qwen3 VL 235B A22B Instruct qwen LLM $0.3 $1.5 131,072
Q5 Qwen3.5-27B qwen LLM $0.3 $2.4 262,144
DV deepseek/deepseek-v4.1-flash None LLM $0.3 $1.2 1,048,576
DV deepseek/deepseek-v4.1-flash-dst None LLM $0.3 $1.2 1,048,576
DV deepseek/deepseek-v4.1-flash-p None LLM $0.3 $1.2 1,048,576
Q5 Qwen2.5 72B Instruct qwen LLM $0.38 $0.4 32,000
QC qwen/qwen3-coder-480b-a35b-instruct None LLM $0.38 $1.55 262,144
Q5 Qwen3.5-122B-A10B qwen LLM $0.4 $3.2 262,144
E4 ERNIE 4.5 VL 424B A47B baidu LLM $0.42 $1.25 123,000
Q8 Qwen/Qwen3.8-27B None LLM $0.42 $3 1,000,000
MV MiMo-V2.6-Pro xiaomi Transcription $0.435 $0.87 1,048,576
DV DeepSeek V4 Flash 0731 deepseek LLM $0.44 $1.32 1,048,576
DV DeepSeek V4 Flash Vision Exp deepseek LLM $0.44 $1.32 1,048,576
DV deepseek/deepseek-v4-flash-0731-p None LLM $0.44 $1.32 1,048,576
MV MiMo-V2.5-Pro xiaomi LLM $0.522 $1.044 1,048,576
G4 GLM 4.6 z-ai LLM $0.55 $2.2 256,000
MM minimaxai/minimax-m1-80k None LLM $0.55 $2.2 1,000,000
T4 thudm/glm-4-32b-0414 None LLM $0.55 $1.66 32,000
MK moonshotai/kimi-k2-instruct None LLM $0.57 $2.3 131,072
G4 GLM 4.5V z-ai LLM $0.6 $1.8 65,536
G4 GLM 4.7 z-ai LLM $0.6 $2.2 204,800
KK Kimi K2 0905 moonshotai LLM $0.6 $2.5 262,144
KK Kimi K2 Thinking moonshotai LLM $0.6 $2.5 262,144
KK Kimi K2.5 moonshotai LLM $0.6 $3 262,144
Q5 Qwen3.5 397B A17B qwen LLM $0.6 $3.6 262,144
Q6 Qwen3.6 27B qwen LLM $0.6 $3.6 262,144
MM minimax/minimax-m2.5-highspeed None LLM $0.6 $2.4 204,800
MM minimax/minimax-m2.7-highspeed None LLM $0.6 $2.4 204,800
ZO zai-org/glm-4.7-h None LLM $0.6 $2.2 204,800
W2 WizardLM-2 8x22B microsoft LLM $0.62 $0.62 65,535
R0 R1 0528 deepseek LLM $0.7 $2.5 163,840
DR deepseek/deepseek-r1-turbo None LLM $0.7 $2.5 64,000
KK Kimi K2.6 moonshotai LLM $0.8 $3.4 262,144
MV mindai/macaron-v1-venti None LLM $0.825 $2.475 1,048,576
HP Hy4 preview tencent LLM $0.834 $2.501 1,000,000
DV DeepSeek V3 deepseek LLM $0.89 $0.89 64,000
KK Kimi K2.7 Code moonshotai LLM $0.95 $4 262,144
QV Qwen3 VL 235B A22B Thinking qwen LLM $0.98 $3.95 131,072
G5 GLM 5 z-ai LLM $1 $3.2 202,800
MI ming-image-0.1-design None Image $1 $1 —
MI ming-image-0.1-design-layer None Image $1 $1 —
G5 GLM 5 Turbo z-ai LLM $1.2 $4 202,800
G5 GLM 5V Turbo z-ai LLM $1.2 $4 204,800
Q7 Qwen3.7 Max qwen LLM $1.25 $3.75 1,000,000
DV DeepSeek V4 Pro 0813 deepseek LLM $1.32 $3.96 1,048,576
DV deepseek/deepseek-v4-pro-0813-p None LLM $1.32 $3.96 1,048,576
G5 GLM 5.1 z-ai LLM $1.38 $4.4 204,800
G5 GLM 5.2 z-ai LLM $1.4 $4.4 1,048,576
ZO zai-org/GLM-5.3 None LLM $1.4 $4.4 1,048,576
ZO zai-org/glm-5.3-p None LLM $1.4 $4.4 1,048,576
S1 Sao10K/L3.1-70B-Euryale-v2.2 None LLM $1.48 $1.48 8,192
S7 sao10k/l3-70b-euryale-v2.1 None LLM $1.48 $1.48 8,192
DV deepseek/deepseek-v4-pro None LLM $1.6 $3.2 1,048,576
Q8 Qwen/Qwen3.8-Max None LLM $2 $6 1,000,000
Q8 Qwen3.8 2.4T A95B qwen LLM $2 $6 1,000,000
QM Qwen3 Max qwen LLM $2.11 $8.45 262,144
KK Kimi K3 moonshotai LLM $3 $15 1,048,576
MK moonshotai/Kimi-K3 None LLM $3 $15 1,048,576
DR deepseek/deepseek-r1/community None LLM $4 $4 64,000
A1 Apodex 1.1 Mini None LLM — — 262,144
Q6 Qwen3.6 Plus qwen LLM — — 1,000,000
B bunny None LLM — — 262,144
I3 inclusionai/ling-3.0-flash-sante None LLM — — 262,144
I3 inclusionai/ling-3.1-flash None LLM — — 262,144
Q5 qwen/qwen3.5-plus None LLM — — 1,000,000