Provider model catalog
Novita AI models
Fast and affordable open-source model hosting
83 unique catalog models
Model pricing and capabilities
- bge-m3Not listed input
- baichuan-m2-32b$0.070 / 1M tokens input
- ernie-4.5-21B-a3b$0.070 / 1M tokens input
- ernie-4.5-21B-a3b-thinking$0.070 / 1M tokens input
- ernie-4.5-300b-a47b-paddle$0.280 / 1M tokens input
- ernie-4.5-vl-28b-a3b$0.140 / 1M tokens input
- ernie-4.5-vl-28b-a3b-thinking$0.390 / 1M tokens input
- ernie-4.5-vl-424b-a47b$0.420 / 1M tokens input
- deepseek-ocr$0.030 / 1M tokens input
- deepseek-prover-v2-671b$0.700 / 1M tokens input
- deepseek-r1-0528$0.700 / 1M tokens input
- deepseek-r1-0528-qwen3-8b$0.060 / 1M tokens input
- deepseek-r1-distill-llama-70b$0.800 / 1M tokens input
- deepseek-r1-distill-qwen-14b$0.150 / 1M tokens input
- deepseek-r1-distill-qwen-32b$0.300 / 1M tokens input
- deepseek-r1-turbo$0.700 / 1M tokens input
- deepseek-v3-0324$0.270 / 1M tokens input
- deepseek-v3-turbo$0.400 / 1M tokens input
- deepseek-v3.1$0.270 / 1M tokens input
- deepseek-v3.1-terminus$0.270 / 1M tokens input
- deepseek-v3.2$0.269 / 1M tokens input
- deepseek-v3.2-exp$0.270 / 1M tokens input
- gemma-3-12b-it$0.050 / 1M tokens input
- gemma-3-27b-it$0.119 / 1M tokens input
All 83 Novita AI models
- mythomax-l2-13b$0.090 / 1M tokens
- kat-coder-pro$0.300 / 1M tokens
- llama-3-70b-instruct$0.510 / 1M tokens
- llama-3-8b-instruct$0.040 / 1M tokens
- llama-3.1-8b-instruct$0.020 / 1M tokens
- llama-3.2-3b-instruct$0.030 / 1M tokens
- llama-3.3-70b-instruct$0.135 / 1M tokens
- llama-4-maverick-17b-128e-instruct-fp8$0.270 / 1M tokens
- llama-4-scout-17b-16e-instruct$0.180 / 1M tokens
- wizardlm-2-8x22b$0.620 / 1M tokens
- minimax-m2$0.300 / 1M tokens
- minimax-m2.1$0.300 / 1M tokens
- minimax-m1-80k$0.550 / 1M tokens
- mistral-nemo$0.040 / 1M tokens
- kimi-k2-0905$0.600 / 1M tokens
- kimi-k2-instruct$0.570 / 1M tokens
- kimi-k2-thinking$0.600 / 1M tokens
- hermes-2-pro-llama-3-8b$0.140 / 1M tokens
- gpt-oss-120b$0.050 / 1M tokens
- gpt-oss-20b$0.040 / 1M tokens
- paddleocr-vl$0.020 / 1M tokens
- qwen-2.5-72b-instruct$0.380 / 1M tokens
- qwen-mt-plus$0.250 / 1M tokens
- qwen2.5-7b-instruct$0.070 / 1M tokens
- qwen2.5-vl-72b-instruct$0.800 / 1M tokens
- qwen3-235b-a22b-fp8$0.200 / 1M tokens
- qwen3-235b-a22b-instruct-2507$0.090 / 1M tokens
- qwen3-235b-a22b-thinking-2507$0.300 / 1M tokens
- qwen3-30b-a3b-fp8$0.090 / 1M tokens
- qwen3-32b-fp8$0.100 / 1M tokens
- qwen3-4b-fp8$0.030 / 1M tokens
- qwen3-8b-fp8$0.035 / 1M tokens
- qwen3-coder-30b-a3b-instruct$0.070 / 1M tokens
- qwen3-coder-480b-a35b-instruct$0.300 / 1M tokens
- qwen3-embedding-0.6bNot listed
- qwen3-embedding-8bNot listed
- qwen3-max$2.11 / 1M tokens
- qwen3-next-80b-a3b-instruct$0.150 / 1M tokens
- qwen3-next-80b-a3b-thinking$0.150 / 1M tokens
- qwen3-omni-30b-a3b-instruct$0.250 / 1M tokens
- qwen3-omni-30b-a3b-thinking$0.250 / 1M tokens
- qwen3-vl-235b-a22b-instruct$0.300 / 1M tokens
- qwen3-vl-235b-a22b-thinking$0.980 / 1M tokens
- qwen3-vl-30b-a3b-instruct$0.200 / 1M tokens
- qwen3-vl-30b-a3b-thinking$0.200 / 1M tokens
- qwen3-vl-8b-instruct$0.080 / 1M tokens
- l3-70b-euryale-v2.1$1.48 / 1M tokens
- l3-8b-lunaris$0.050 / 1M tokens
- L3-8B-Stheno-v3.2$0.050 / 1M tokens
- l31-70b-euryale-v2.2$1.48 / 1M tokens
- r1v4-lite$0.200 / 1M tokens
- mimo-v2-flash$0.100 / 1M tokens
- autoglm-phone-9b-multilingual$0.035 / 1M tokens
- glm-4.5$0.600 / 1M tokens
- glm-4.5-air$0.130 / 1M tokens
- glm-4.5v$0.600 / 1M tokens
- glm-4.6$0.550 / 1M tokens
- glm-4.6v$0.300 / 1M tokens
- glm-4.7$0.600 / 1M tokens