Novita AI
Serverless GPU inference for AI models including image generation, language models, and audio processing.
Novita AI
Serverless GPU inference for AI models including image generation, language models, and audio processing.
Authentication
API KeyAdd your Novita AI API key from Organization → Integrations → AI Vendors. Keys are encrypted at rest and scoped to your organization.
Available Models
96 enabled models across 2 categories.
Text94
zai-org/autoglm-phone-9b-multilingualchatModel, languageModel, completionModel
imageInput, vision
baichuan/baichuan-m2-32bchatModel, languageModel, completionModel
deepseek/deepseek-ocr-2chatModel, languageModel, completionModel
imageInput, vision
deepseek/deepseek-ocrchatModel, languageModel, completionModel
imageInput, vision
deepseek/deepseek-prover-v2-671bchatModel, languageModel, completionModel
deepseek/deepseek-r1-0528chatModel, languageModel, completionModel
functionCalling, reasoning
deepseek/deepseek-r1-0528-qwen3-8bchatModel, languageModel, completionModel
reasoning
deepseek/deepseek-r1-distill-llama-70bchatModel, languageModel, completionModel
reasoning
deepseek/deepseek-r1-distill-qwen-14bchatModel, languageModel, completionModel
reasoning
deepseek/deepseek-r1-distill-qwen-32bchatModel, languageModel, completionModel
reasoning
deepseek/deepseek-r1-turbochatModel, languageModel, completionModel
functionCalling, reasoning
deepseek/deepseek-v3-0324chatModel, languageModel, completionModel
functionCalling
deepseek/deepseek-v3.1chatModel, languageModel, completionModel
functionCalling, reasoning
deepseek/deepseek-v3.1-terminuschatModel, languageModel, completionModel
functionCalling, reasoning
deepseek/deepseek-v3.2chatModel, languageModel, completionModel
functionCalling, reasoning
deepseek/deepseek-v3.2-expchatModel, languageModel, completionModel
functionCalling, reasoning
deepseek/deepseek-v3-turbochatModel, languageModel, completionModel
functionCalling
baidu/ernie-4.5-21B-a3bchatModel, languageModel, completionModel
functionCalling
baidu/ernie-4.5-21B-a3b-thinkingchatModel, languageModel, completionModel
reasoning
baidu/ernie-4.5-300b-a47b-paddlechatModel, languageModel, completionModel
baidu/ernie-4.5-vl-28b-a3bchatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
baidu/ernie-4.5-vl-28b-a3b-thinkingchatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
baidu/ernie-4.5-vl-424b-a47bchatModel, languageModel, completionModel
reasoning, imageInput, vision
google/gemma-3-12b-itchatModel, languageModel, completionModel
imageInput, vision
google/gemma-3-27b-itchatModel, languageModel, completionModel
imageInput, vision
google/gemma-4-26b-a4b-itchatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
google/gemma-4-31b-itchatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
zai-org/glm-4.5chatModel, languageModel, completionModel
functionCalling, reasoning
zai-org/glm-4.5-airchatModel, languageModel, completionModel
functionCalling, reasoning
zai-org/glm-4.5vchatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
zai-org/glm-4.6chatModel, languageModel, completionModel
functionCalling, reasoning
zai-org/glm-4.6vchatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
zai-org/glm-4.7chatModel, languageModel, completionModel
functionCalling, reasoning
zai-org/glm-4.7-flashchatModel, languageModel, completionModel
functionCalling, reasoning
zai-org/glm-5chatModel, languageModel, completionModel
functionCalling, reasoning
zai-org/glm-5.1chatModel, languageModel, completionModel
functionCalling, reasoning
nousresearch/hermes-2-pro-llama-3-8bchatModel, languageModel, completionModel
kwaipilot/kat-coder-prochatModel, languageModel, completionModel
functionCalling
moonshotai/kimi-k2-0905chatModel, languageModel, completionModel
functionCalling
moonshotai/kimi-k2.5chatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
moonshotai/kimi-k2.6chatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
moonshotai/kimi-k2-instructchatModel, languageModel, completionModel
functionCalling
moonshotai/kimi-k2-thinkingchatModel, languageModel, completionModel
functionCalling, reasoning
sao10k/l31-70b-euryale-v2.2chatModel, languageModel, completionModel
functionCalling
sao10k/l3-70b-euryale-v2.1chatModel, languageModel, completionModel
functionCalling
sao10k/L3-8B-Stheno-v3.2chatModel, languageModel, completionModel
functionCalling
inclusionai/ling-2.6-1tchatModel, languageModel, completionModel
functionCalling
meta-llama/llama-3.1-8b-instructchatModel, languageModel, completionModel
meta-llama/llama-3.2-3b-instructchatModel, languageModel, completionModel
meta-llama/llama-3.3-70b-instructchatModel, languageModel, completionModel
functionCalling
meta-llama/llama-3-70b-instructchatModel, languageModel, completionModel
meta-llama/llama-3-8b-instructchatModel, languageModel, completionModel
meta-llama/llama-4-maverick-17b-128e-instruct-fp8chatModel, languageModel, completionModel
imageInput, vision
meta-llama/llama-4-scout-17b-16e-instructchatModel, languageModel, completionModel
imageInput, vision
minimaxai/minimax-m1-80kchatModel, languageModel, completionModel
functionCalling, reasoning
minimax/minimax-m2chatModel, languageModel, completionModel
functionCalling, reasoning
minimax/minimax-m2.1chatModel, languageModel, completionModel
functionCalling
minimax/minimax-m2.5chatModel, languageModel, completionModel
functionCalling, reasoning
minimax/minimax-m2.5-highspeedchatModel, languageModel, completionModel
functionCalling, reasoning
minimax/minimax-m2.7chatModel, languageModel, completionModel
functionCalling, reasoning
mistralai/mistral-nemochatModel, languageModel, completionModel
gryphe/mythomax-l2-13bchatModel, languageModel, completionModel
openai/gpt-oss-120bchatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
openai/gpt-oss-20bchatModel, languageModel, completionModel
reasoning, imageInput, vision
paddlepaddle/paddleocr-vlchatModel, languageModel, completionModel
imageInput, vision
qwen/qwen-2.5-72b-instructchatModel, languageModel, completionModel
functionCalling
qwen/qwen2.5-7b-instructchatModel, languageModel, completionModel
functionCalling
qwen/qwen2.5-vl-72b-instructchatModel, languageModel, completionModel
imageInput, vision
qwen/qwen3-235b-a22b-fp8chatModel, languageModel, completionModel
reasoning
qwen/qwen3-235b-a22b-instruct-2507chatModel, languageModel, completionModel
functionCalling
qwen/qwen3-235b-a22b-thinking-2507chatModel, languageModel, completionModel
functionCalling, reasoning
qwen/qwen3-30b-a3b-fp8chatModel, languageModel, completionModel
reasoning
qwen/qwen3-32b-fp8chatModel, languageModel, completionModel
reasoning
qwen/qwen3-4b-fp8chatModel, languageModel, completionModel
reasoning
qwen/qwen3.5-122b-a10bchatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
qwen/qwen3.5-27bchatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
qwen/qwen3.5-35b-a3bchatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
qwen/qwen3.5-397b-a17bchatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
qwen/qwen3-8b-fp8chatModel, languageModel, completionModel
reasoning
qwen/qwen3-coder-30b-a3b-instructchatModel, languageModel, completionModel
functionCalling
qwen/qwen3-coder-480b-a35b-instructchatModel, languageModel, completionModel
functionCalling
qwen/qwen3-coder-nextchatModel, languageModel, completionModel
functionCalling
qwen/qwen3-maxchatModel, languageModel, completionModel
functionCalling
qwen/qwen3-next-80b-a3b-instructchatModel, languageModel, completionModel
functionCalling
qwen/qwen3-next-80b-a3b-thinkingchatModel, languageModel, completionModel
functionCalling, reasoning
qwen/qwen3-vl-235b-a22b-instructchatModel, languageModel, completionModel
functionCalling, imageInput, vision
qwen/qwen3-vl-235b-a22b-thinkingchatModel, languageModel, completionModel
reasoning, imageInput, vision
qwen/qwen-mt-pluschatModel, languageModel, completionModel
qwen/qwen3-vl-30b-a3b-instructchatModel, languageModel, completionModel
functionCalling, imageInput, vision
qwen/qwen3-vl-30b-a3b-thinkingchatModel, languageModel, completionModel
functionCalling, imageInput, vision
qwen/qwen3-vl-8b-instructchatModel, languageModel, completionModel
functionCalling, imageInput, vision
sao10k/l3-8b-lunarischatModel, languageModel, completionModel
microsoft/wizardlm-2-8x22bchatModel, languageModel, completionModel
xiaomimimo/mimo-v2-flashchatModel, languageModel, completionModel
functionCalling, reasoning
Sound2
qwen/qwen3-omni-30b-a3b-instructspeech
functionCalling, imageInput, vision
qwen/qwen3-omni-30b-a3b-thinkingtranscription
functionCalling, reasoning, imageInput, vision