AALLM
Get an API key

inference cloud

Novita

Models, pricing and feature compatibility available through Novita.

Provider website

Deployments

135

Models

135

Labs

12

With pricing

135

Models on Novita

Follow any model to compare this deployment with the same model through other providers.

ModelProvider model IDModeRegionInputOutputContextTools
Baai Bge M3baai/bge-m3Embeddingglobal$0.01 / 1M$0.01 / 1M8.2Knot_applicable
Baai Bge Reranker V2 M3baai/bge-reranker-v2-m3Rerankglobal$0.01 / 1M$0.01 / 1M8Knot_applicable
Baichuan Baichuan M2 32Bbaichuan/baichuan-m2-32bChatglobal$0.07 / 1M$0.07 / 1M131.1Kunknown
Cobuddybaidu/cobuddyChatglobal$0.28 / 1M$1.13 / 1M131.1Ksupported
Ernie 4 5 21B A3Bbaidu/ernie-4.5-21B-a3bChatglobal$0.07 / 1M$0.28 / 1M120Ksupported
Ernie 4 5 21B A3B Thinkingbaidu/ernie-4.5-21B-a3b-thinkingChatglobal$0.07 / 1M$0.28 / 1M131.1Kunknown
Ernie 4 5 300B A47B Paddlebaidu/ernie-4.5-300b-a47b-paddleChatglobal$0.28 / 1M$1.10 / 1M123Kunknown
Ernie 4 5 VL 28B A3Bbaidu/ernie-4.5-vl-28b-a3bChatglobal$0.14 / 1M$0.56 / 1M30Ksupported
Ernie 4 5 VL 28B A3B Thinkingbaidu/ernie-4.5-vl-28b-a3b-thinkingChatglobal$0.39 / 1M$0.39 / 1M131.1Ksupported
Ernie 4 5 VL 424B A47Bbaidu/ernie-4.5-vl-424b-a47bChatglobal$0.42 / 1M$1.25 / 1M123Kunknown
DeepSeek-OCRdeepseek/deepseek-ocrChatglobal$0.03 / 1M$0.03 / 1M8.2Kunknown
DeepSeek-OCR 2deepseek/deepseek-ocr-2Chatglobal$0.03 / 1M$0.03 / 1M8.2Kunknown
DeepSeek-Prover V2 671Bdeepseek/deepseek-prover-v2-671bChatglobal$0.70 / 1M$2.50 / 1M160Kunknown
DeepSeek-R1deepseek/deepseek-r1Chatglobal$4.00 / 1M$4.00 / 1M64Ksupported
DeepSeek-R1 0528deepseek/deepseek-r1-0528Chatglobal$0.70 / 1M$2.50 / 1M163.8Ksupported
DeepSeek-R1 0528 Qwen3 8Bdeepseek/deepseek-r1-0528-qwen3-8bChatglobal$0.06 / 1M$0.09 / 1M128Kunknown
DeepSeek-R1 Communitydeepseek/deepseek-r1/communityChatglobal$4.00 / 1M$4.00 / 1M64Ksupported
Deepseek Deepseek R1 Distill Llama 70Bdeepseek/deepseek-r1-distill-llama-70bChatglobal$0.80 / 1M$0.80 / 1M8.2Kunknown
DeepSeek-R1 Distill Qwen 14Bdeepseek/deepseek-r1-distill-qwen-14bChatglobal$0.15 / 1M$0.15 / 1M32.8Kunknown
DeepSeek-R1 Distill Qwen 32Bdeepseek/deepseek-r1-distill-qwen-32bChatglobal$0.30 / 1M$0.30 / 1M64Kunknown
DeepSeek-R1 Turbodeepseek/deepseek-r1-turboChatglobal$0.70 / 1M$2.50 / 1M64Ksupported
V3deepseek/deepseek_v3Chatglobal$0.89 / 1M$0.89 / 1M64Ksupported
DeepSeek-V3.0324deepseek/deepseek-v3-0324Chatglobal$0.27 / 1M$1.12 / 1M163.8Ksupported
DeepSeek-V3.1deepseek/deepseek-v3.1Chatglobal$0.27 / 1M$1.00 / 1M131.1Ksupported
DeepSeek-V3.1 Terminusdeepseek/deepseek-v3.1-terminusChatglobal$0.27 / 1M$1.00 / 1M131.1Ksupported
DeepSeek-V3.2deepseek/deepseek-v3.2Chatglobal$0.27 / 1M$0.40 / 1M163.8Ksupported
DeepSeek-V3.2 Experimentaldeepseek/deepseek-v3.2-expChatglobal$0.27 / 1M$0.41 / 1M163.8Ksupported
DeepSeek-V3 Communitydeepseek/deepseek-v3/communityChatglobal$0.89 / 1M$0.89 / 1M64Ksupported
DeepSeek-V3 Turbodeepseek/deepseek-v3-turboChatglobal$0.40 / 1M$1.30 / 1M64Ksupported
DeepSeek-V4 Flashdeepseek/deepseek-v4-flashChatglobal$0.14 / 1M$0.28 / 1M1.05Msupported
DeepSeek-V4 Flash 0731deepseek/deepseek-v4-flash-0731Chatglobal$0.44 / 1M$1.32 / 1M1.05Msupported
DeepSeek-V4 Flash Vision Experimentaldeepseek/deepseek-v4-flash-vision-expChatglobal$0.44 / 1M$1.32 / 1M1.05Msupported
DeepSeek-V4 Prodeepseek/deepseek-v4-proChatglobal$1.60 / 1M$3.20 / 1M1.05Msupported
DeepSeek-V4 Pro 0813deepseek/deepseek-v4-pro-0813Chatglobal$1.32 / 1M$3.96 / 1M1.05Msupported
Gemma 3 12B ITgoogle/gemma-3-12b-itChatglobal$0.05 / 1M$0.10 / 1M131.1Kunknown
Gemma 3 27B ITgoogle/gemma-3-27b-itChatglobal$0.12 / 1M$0.20 / 1M98.3Kunknown
Gemma 4 26B A4B ITgoogle/gemma-4-26b-a4b-itChatglobal$0.13 / 1M$0.40 / 1M262.1Ksupported
Gemma 4 31B ITgoogle/gemma-4-31b-itChatglobal$0.14 / 1M$0.40 / 1M262.1Ksupported
Gryphe Mythomax L2 13Bgryphe/mythomax-l2-13bChatglobal$0.09 / 1M$0.09 / 1M4.1Kunknown
Inclusionai Ling 3 0 Flashinclusionai/ling-3.0-flashChatglobal$0.06 / 1M$0.18 / 1M262.1Ksupported
Inclusionai Ling 3 0 Flash Fastinclusionai/ling-3.0-flash-fastChatglobal$0.06 / 1M$0.18 / 1M262.1Ksupported
Kwaipilot Kat Coder Prokwaipilot/kat-coder-proChatglobal$0.30 / 1M$1.20 / 1M256Ksupported
Meta Llama Llama 3 1 8B Instructmeta-llama/llama-3.1-8b-instructChatglobal$0.02 / 1M$0.05 / 1M16.4Kunknown
Meta Llama Llama 3 2 1B Instructmeta-llama/llama-3.2-1b-instructChatglobal$0.02 / 1M$0.02 / 1M131Kunknown
Meta Llama Llama 3 2 3B Instructmeta-llama/llama-3.2-3b-instructChatglobal$0.03 / 1M$0.05 / 1M32.8Ksupported
Meta Llama Llama 3 3 70B Instructmeta-llama/llama-3.3-70b-instructChatglobal$0.14 / 1M$0.40 / 1M12.3Ksupported
Meta Llama Llama 3 70B Instructmeta-llama/llama-3-70b-instructChatglobal$0.51 / 1M$0.74 / 1M8.2Kunknown
Meta Llama Llama 3 8B Instructmeta-llama/llama-3-8b-instructChatglobal$0.04 / 1M$0.04 / 1M8.2Kunknown
Meta Llama Llama 4 Maverick 17B 128E Instruct FP8meta-llama/llama-4-maverick-17b-128e-instruct-fp8Chatglobal$0.27 / 1M$0.85 / 1M1.05Munknown
Meta Llama Llama 4 Scout 17B 16E Instructmeta-llama/llama-4-scout-17b-16e-instructChatglobal$0.18 / 1M$0.59 / 1M131.1Kunknown
Microsoft Wizardlm 2 8x22Bmicrosoft/wizardlm-2-8x22bChatglobal$0.62 / 1M$0.62 / 1M65.5Kunknown
Mindai Macaron V1 Tallmindai/macaron-v1-tallChatglobal$0.45 / 1M$2.60 / 1M262.1Ksupported
Mindai Macaron V1 Ventimindai/macaron-v1-ventiChatglobal$1.50 / 1M$4.50 / 1M1.05Msupported
Minimax M2minimax/minimax-m2Chatglobal$0.30 / 1M$1.20 / 1M204.8Ksupported
Minimax M2 1minimax/minimax-m2.1Chatglobal$0.30 / 1M$1.20 / 1M204.8Ksupported
Minimax M2 5minimax/minimax-m2.5Chatglobal$0.30 / 1M$1.20 / 1M204.8Ksupported
Minimax M2 5 Highspeedminimax/minimax-m2.5-highspeedChatglobal$0.60 / 1M$2.40 / 1M204.8Ksupported
Minimax M2 7minimax/minimax-m2.7Chatglobal$0.30 / 1M$1.20 / 1M204.8Ksupported
Minimax M2 7 Highspeedminimax/minimax-m2.7-highspeedChatglobal$0.60 / 1M$2.40 / 1M204.8Ksupported
Minimax M3minimax/minimax-m3Chatglobal$0.30 / 1M$1.20 / 1M1Msupported
Minimaxai Minimax M1 80kminimaxai/minimax-m1-80kChatglobal$0.55 / 1M$2.20 / 1M1Msupported
Mistralai Mistral Nemomistralai/mistral-nemoChatglobal$0.04 / 1M$0.17 / 1M60.3Kunknown
Moonshotai Kimi K2 0905moonshotai/kimi-k2-0905Chatglobal$0.60 / 1M$2.50 / 1M262.1Ksupported
Moonshotai Kimi K2 5moonshotai/kimi-k2.5Chatglobal$0.60 / 1M$3.00 / 1M262.1Ksupported
Moonshotai Kimi K2 6moonshotai/kimi-k2.6Chatglobal$0.80 / 1M$3.40 / 1M262.1Ksupported
Moonshotai Kimi K2 7 Codemoonshotai/kimi-k2.7-codeChatglobal$0.95 / 1M$4.00 / 1M262.1Ksupported
Moonshotai Kimi K2 Instructmoonshotai/kimi-k2-instructChatglobal$0.57 / 1M$2.30 / 1M131.1Ksupported
Moonshotai Kimi K2 Thinkingmoonshotai/kimi-k2-thinkingChatglobal$0.60 / 1M$2.50 / 1M262.1Ksupported
Moonshotai Kimi K3moonshotai/kimi-k3Chatglobal$3.00 / 1M$15.00 / 1M1.05Msupported
Nousresearch Hermes 2 Pro Llama 3 8Bnousresearch/hermes-2-pro-llama-3-8bChatglobal$0.14 / 1M$0.14 / 1M8.2Kunknown
Nemotron 3 nano 30B A3Bnvidia/nemotron-3-nano-30b-a3bChatglobal$0.05 / 1M$0.20 / 1M262.1Ksupported
gpt-oss-120bopenai/gpt-oss-120bChatglobal$0.05 / 1M$0.25 / 1M131.1Ksupported
gpt-oss-20bopenai/gpt-oss-20bChatglobal$0.04 / 1M$0.15 / 1M131.1Kunknown
Paddlepaddle Paddleocr VLpaddlepaddle/paddleocr-vlChatglobal$0.02 / 1M$0.02 / 1M16.4Kunknown
Qwen Qwen 2 5 72B Instructqwen/qwen-2.5-72b-instructChatglobal$0.38 / 1M$0.40 / 1M32Ksupported
Qwen Qwen Mt Plusqwen/qwen-mt-plusChatglobal$0.25 / 1M$0.75 / 1M16.4Kunknown
Qwen Qwen2 5 7B Instructqwen/qwen2.5-7b-instructChatglobal$0.07 / 1M$0.07 / 1M32Ksupported
Qwen Qwen2 5 VL 72B Instructqwen/qwen2.5-vl-72b-instructChatglobal$0.80 / 1M$0.80 / 1M32.8Kunknown
Qwen Qwen3 235B A22B FP8qwen/qwen3-235b-a22b-fp8Chatglobal$0.20 / 1M$0.80 / 1M41Kunknown
Qwen Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-instruct-2507Chatglobal$0.09 / 1M$0.58 / 1M131.1Ksupported
Qwen Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507Chatglobal$0.30 / 1M$3.00 / 1M131.1Ksupported
Qwen Qwen3 30B A3B FP8qwen/qwen3-30b-a3b-fp8Chatglobal$0.09 / 1M$0.45 / 1M41Ksupported
Qwen Qwen3 32B FP8qwen/qwen3-32b-fp8Chatglobal$0.10 / 1M$0.45 / 1M41Kunknown
Qwen Qwen3 4B FP8qwen/qwen3-4b-fp8Chatglobal$0.03 / 1M$0.03 / 1M128Ksupported
Qwen Qwen3 5 122B A10Bqwen/qwen3.5-122b-a10bChatglobal$0.40 / 1M$3.20 / 1M262.1Ksupported
Qwen Qwen3 5 27Bqwen/qwen3.5-27bChatglobal$0.30 / 1M$2.40 / 1M262.1Ksupported
Qwen Qwen3 5 35B A3Bqwen/qwen3.5-35b-a3bChatglobal$0.25 / 1M$2.00 / 1M262.1Ksupported
Qwen Qwen3 5 397B A17Bqwen/qwen3.5-397b-a17bChatglobal$0.60 / 1M$3.60 / 1M262.1Ksupported
Qwen Qwen3 6 27Bqwen/qwen3.6-27bChatglobal$0.60 / 1M$3.60 / 1M262.1Ksupported
Qwen Qwen3 6 35B A3Bqwen/qwen3.6-35b-a3bChatglobal$0.25 / 1M$1.49 / 1M262.1Ksupported
Qwen Qwen3 7 Maxqwen/qwen3.7-maxChatglobal$1.25 / 1M$3.75 / 1M1Msupported
Qwen Qwen3 8 Maxqwen/qwen3.8-maxChatglobal$2.00 / 1M$6.00 / 1M1Msupported
Qwen Qwen3 8B FP8qwen/qwen3-8b-fp8Chatglobal$0.04 / 1M$0.14 / 1M128Kunknown
Qwen Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instructChatglobal$0.07 / 1M$0.27 / 1M160Ksupported
Qwen Qwen3 Coder 480B A35B Instructqwen/qwen3-coder-480b-a35b-instructChatglobal$0.38 / 1M$1.55 / 1M262.1Ksupported
Qwen Qwen3 Coder Nextqwen/qwen3-coder-nextChatglobal$0.20 / 1M$1.50 / 1M262.1Ksupported
Qwen Qwen3 Embedding 0 6Bqwen/qwen3-embedding-0.6bEmbeddingglobal$0.07 / 1M$0.0000 / 1M32.8Knot_applicable
Qwen Qwen3 Embedding 8Bqwen/qwen3-embedding-8bEmbeddingglobal$0.07 / 1M$0.0000 / 1M32.8Knot_applicable
Qwen Qwen3 Maxqwen/qwen3-maxChatglobal$2.11 / 1M$8.45 / 1M262.1Ksupported
Qwen Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instructChatglobal$0.15 / 1M$1.50 / 1M131.1Ksupported

Showing the first 100 of 135 deployments. Use the API for the complete dataset.

Labs available through Novita

AlibabaBaiduDeepSeekGoogleMetaMiniMaxMistral AIMoonshot AINovitaNVIDIAOpenAIZ.ai