Novita AI API Pricing 2026

Compare pricing for all Novita AI LLM models. See input/output costs, context windows, and features.

Showing 80 models from Novita AI. Prices are per 1 million tokens. Data sourced from official pricing pages via LiteLLM.

Models

80

Cheapest Input

$0.02

/1M tokens

Cheapest Output

$0.02

/1M tokens

Max Context

1.0M

tokens

80 models
Features
meta-llama/llama-3.1-8b-instruct$0.020$0.05016.4K16.4K
paddlepaddle/paddleocr-vl$0.020$0.02016.4K16.4K
deepseek/deepseek-ocr$0.030$0.0308.2K8.2K
meta-llama/llama-3.2-3b-instruct$0.030$0.05032.8K32K
qwen/qwen3-4b-fp8$0.030$0.030128K20K
qwen/qwen3-8b-fp8$0.035$0.138128K20K
zai-org/autoglm-phone-9b-multilingual$0.035$0.13865.5K65.5K
meta-llama/llama-3-8b-instruct$0.040$0.0408.2K8.2K
mistralai/mistral-nemo$0.040$0.17060.3K16K
openai/gpt-oss-20b$0.040$0.150131.1K32.8K
google/gemma-3-12b-it$0.050$0.100131.1K8.2K
openai/gpt-oss-120b$0.050$0.250131.1K32.8K
sao10k/l3-8b-lunaris$0.050$0.0508.2K8.2K
Sao10K/L3-8B-Stheno-v3.2$0.050$0.0508.2K32K
deepseek/deepseek-r1-0528-qwen3-8b$0.060$0.090128K32K
baichuan/baichuan-m2-32b$0.070$0.070131.1K131.1K
baidu/ernie-4.5-21B-a3b$0.070$0.280120K8K
baidu/ernie-4.5-21B-a3b-thinking$0.070$0.280131.1K65.5K
qwen/qwen2.5-7b-instruct$0.070$0.07032K32K
qwen/qwen3-coder-30b-a3b-instruct$0.070$0.270160K32.8K
qwen/qwen3-vl-8b-instruct$0.080$0.500131.1K32.8K
gryphe/mythomax-l2-13b$0.090$0.0904.1K3.2K
qwen/qwen3-235b-a22b-instruct-2507$0.090$0.580131.1K16.4K
qwen/qwen3-30b-a3b-fp8$0.090$0.45041.0K20K
qwen/qwen3-32b-fp8$0.100$0.45041.0K20K
xiaomimimo/mimo-v2-flash$0.100$0.300262.1K32K
google/gemma-3-27b-it$0.119$0.20098.3K16.4K
zai-org/glm-4.5-air$0.130$0.850131.1K98.3K
meta-llama/llama-3.3-70b-instruct$0.135$0.400131.1K120K
baidu/ernie-4.5-vl-28b-a3b$0.140$0.56030K8K
nousresearch/hermes-2-pro-llama-3-8b$0.140$0.1408.2K8.2K
deepseek/deepseek-r1-distill-qwen-14b$0.150$0.15032.8K16.4K
qwen/qwen3-next-80b-a3b-instruct$0.150$1.50131.1K32.8K
qwen/qwen3-next-80b-a3b-thinking$0.150$1.50131.1K32.8K
meta-llama/llama-4-scout-17b-16e-instruct$0.180$0.590131.1K131.1K
qwen/qwen3-235b-a22b-fp8$0.200$0.80041.0K20K
qwen/qwen3-vl-30b-a3b-instruct$0.200$0.700131.1K32.8K
qwen/qwen3-vl-30b-a3b-thinking$0.200$1.00131.1K32.8K
skywork/r1v4-lite$0.200$0.600262.1K65.5K
qwen/qwen-mt-plus$0.250$0.75016.4K8.2K
qwen/qwen3-omni-30b-a3b-instruct$0.250$0.97065.5K16.4K
qwen/qwen3-omni-30b-a3b-thinking$0.250$0.97065.5K16.4K
deepseek/deepseek-v3.2$0.269$0.400163.8K65.5K
deepseek/deepseek-v3-0324$0.270$1.12163.8K163.8K
deepseek/deepseek-v3.1$0.270$1.00131.1K32.8K
deepseek/deepseek-v3.1-terminus$0.270$1.00131.1K32.8K
deepseek/deepseek-v3.2-exp$0.270$0.410163.8K65.5K
meta-llama/llama-4-maverick-17b-128e-instruct-fp8$0.270$0.8501.0M8.2K
baidu/ernie-4.5-300b-a47b-paddle$0.280$1.10123K12K
deepseek/deepseek-r1-distill-qwen-32b$0.300$0.30064K32K
kwaipilot/kat-coder-pro$0.300$1.20256K128K
minimax/minimax-m2$0.300$1.20204.8K131.1K
minimax/minimax-m2.1$0.300$1.20204.8K131.1K
qwen/qwen3-235b-a22b-thinking-2507$0.300$3.00131.1K32.8K
qwen/qwen3-coder-480b-a35b-instruct$0.300$1.30262.1K65.5K
qwen/qwen3-vl-235b-a22b-instruct$0.300$1.50131.1K32.8K
zai-org/glm-4.6v$0.300$0.900131.1K32.8K
qwen/qwen-2.5-72b-instruct$0.380$0.40032K8.2K
baidu/ernie-4.5-vl-28b-a3b-thinking$0.390$0.390131.1K65.5K
deepseek/deepseek-v3-turbo$0.400$1.3064K16K
baidu/ernie-4.5-vl-424b-a47b$0.420$1.25123K16K
meta-llama/llama-3-70b-instruct$0.510$0.7408.2K8K
minimaxai/minimax-m1-80k$0.550$2.201M40K
zai-org/glm-4.6$0.550$2.20204.8K131.1K
moonshotai/kimi-k2-instruct$0.570$2.30131.1K131.1K
moonshotai/kimi-k2-0905$0.600$2.50262.1K262.1K
moonshotai/kimi-k2-thinking$0.600$2.50262.1K262.1K
zai-org/glm-4.5$0.600$2.20131.1K98.3K
zai-org/glm-4.5v$0.600$1.8065.5K16.4K
zai-org/glm-4.7$0.600$2.20204.8K131.1K
microsoft/wizardlm-2-8x22b$0.620$0.62065.5K8K
deepseek/deepseek-prover-v2-671b$0.700$2.50160K160K
deepseek/deepseek-r1-0528$0.700$2.50163.8K32.8K
deepseek/deepseek-r1-turbo$0.700$2.5064K16K
deepseek/deepseek-r1-distill-llama-70b$0.800$0.8008.2K8.2K
qwen/qwen2.5-vl-72b-instruct$0.800$0.80032.8K32.8K
qwen/qwen3-vl-235b-a22b-thinking$0.980$3.95131.1K32.8K
sao10k/l3-70b-euryale-v2.1$1.48$1.488.2K8.2K
sao10k/l31-70b-euryale-v2.2$1.48$1.488.2K8.2K
qwen/qwen3-max$2.11$8.45262.1K65.5K

每周大模型价格速递

AI Model 调价时第一时间通知你。免费、不发垃圾邮件、随时退订。