NovitaAI

103 个模型
名称 输入模态 输出模态 上下文 输出限制 能力 知识截止
GLM-5.1 text text 204,800 131,072 🧠 🔧 📋 -
GLM-5 text text 202,800 131,072 🧠 🔧 📋 -
GLM-4.7-Flash text text 200,000 128,000 🧠 🔧 📋 2025-04
GLM-4.7 text text 204,800 131,072 🧠 🔧 📋 -
GLM 4.6V text, video, image text 131,072 32,768 🧠 🔧 📋 2025-04
GLM 4.6 text text 204,800 131,072 🧠 🔧 📋 -
GLM 4.5V text, video, image text 65,536 16,384 🧠 🔧 📋 2025-04
GLM 4.5 Air text text 131,072 98,304 🧠 🔧 2025-04
GLM-4.5 text text 131,072 98,304 🧠 🔧 -
AutoGLM-Phone-9B-Multilingual text, image text 65,536 65,536 -
XiaomiMiMo/MiMo-V2-Flash text text 262,144 32,000 🧠 🔧 📋 2024-12
L31 70B Euryale V2.2 text text 8,192 8,192 🔧 -
L31 70B Euryale V2.2 text text 8,192 8,192 🔧 -
L3 8B Stheno V3.2 text text 8,192 32,000 🔧 -
L3 8B Stheno V3.2 text text 8,192 32,000 🔧 -
Sao10k L3 8B Lunaris text text 8,192 8,192 📋 -
Sao10k L3 8B Lunaris text text 8,192 8,192 📋 -
L3 70B Euryale V2.1 text text 8,192 8,192 🔧 -
L3 70B Euryale V2.1 text text 8,192 8,192 🔧 -
Qwen3.5-397B-A17B text, image, video text 262,144 64,000 🧠 🔧 📋 -
Qwen3.5-35B-A3B text, image, video text 262,144 65,536 🧠 🔧 📋 -
Qwen3.5-27B text, image, video text 262,144 65,536 🧠 🔧 📋 -
Qwen3.5-122B-A10B text, image, video text 262,144 65,536 🧠 🔧 📋 -
qwen/qwen3-vl-8b-instruct text, image, video text 131,072 32,768 🔧 📋 -
qwen/qwen3-vl-30b-a3b-thinking text, image, video text 131,072 32,768 🔧 📋 -
qwen/qwen3-vl-30b-a3b-instruct text, video, image text 131,072 32,768 🔧 📋 -
Qwen3 VL 235B A22B Thinking text, image, video text 131,072 32,768 🧠 -
Qwen3 VL 235B A22B Instruct text, image, video text 131,072 32,768 🔧 📋 -
Qwen3 Omni 30B A3B Thinking text, audio, video, image text 65,536 16,384 🧠 🔧 📋 -
Qwen3 Omni 30B A3B Instruct text, video, audio, image text, audio 65,536 16,384 🔧 📋 2024-04
Qwen3 Next 80B A3B Thinking text text 131,072 32,768 🧠 🔧 📋 -
Qwen3 Next 80B A3B Instruct text text 131,072 32,768 🔧 📋 -
Qwen3 Max text text 262,144 65,536 🔧 📋 2025-04
Qwen3 Coder Next text text 262,144 65,536 🔧 📋 -
Qwen3 Coder 480B A35B Instruct text text 262,144 65,536 🔧 📋 2025-04
Qwen3 Coder 30b A3B Instruct text text 160,000 32,768 🔧 📋 -
Qwen3 8B text text 128,000 20,000 🧠 -
Qwen3 4B text text 128,000 20,000 🧠 -
Qwen3 32B text text 40,960 20,000 🧠 -
Qwen3 30B A3B text text 40,960 20,000 🧠 -
Qwen3 235B A22b Thinking 2507 text text 131,072 32,768 🧠 🔧 2025-04
Qwen3 235B A22B Instruct 2507 text text 131,072 16,384 🔧 📋 2025-04
Qwen3 235B A22B text text 40,960 20,000 🧠 -
Qwen2.5 VL 72B Instruct text, image, video text 32,768 32,768 -
Qwen2.5 7B Instruct text text 32,000 32,000 🔧 📋 -
Qwen MT Plus text text 16,384 8,192 -
Qwen 2.5 72B Instruct text text 32,000 8,192 🔧 📋 2024-04
PaddleOCR-VL text, image text 16,384 16,384 -
OpenAI: GPT OSS 20B text, image text 131,072 32,768 🧠 📋 -
OpenAI GPT OSS 120B text, image text 131,072 32,768 🧠 🔧 📋 -
Hermes 2 Pro Llama 3 8B text text 8,192 8,192 📋 -
Kimi K2.6 text, image, video text 262,144 262,144 🧠 🔧 📋 2025-01
Kimi K2.5 text, image, video text 262,144 262,144 🧠 🔧 📋 2025-01
Kimi K2 Thinking text text 262,144 262,144 🧠 🔧 📋 -
Kimi K2 Instruct text text 131,072 131,072 🔧 📋 -
Kimi K2 0905 text text 262,144 262,144 🔧 📋 2024-10
Mistral Nemo text text 60,288 16,000 📋 -
MiniMax M1 text text 1,000,000 40,000 🧠 🔧 -
MiniMax M2.7 text text 204,800 131,072 🧠 🔧 📋 -
MiniMax M2.5 Highspeed text text 204,800 131,100 🧠 🔧 📋 -
MiniMax M2.5 text text 204,800 131,100 🧠 🔧 📋 -
Minimax M2.1 text text 204,800 131,072 🔧 📋 -
MiniMax-M2 text text 204,800 131,072 🧠 🔧 -
Wizardlm 2 8x22B text text 65,535 8,000 -
Llama 4 Scout Instruct text, image text 131,072 131,072 -
Llama 4 Maverick Instruct text, image text 1,048,576 8,192 -
Llama 3.3 70B Instruct text text 131,072 120,000 🔧 2023-12
Llama 3.2 3B Instruct text text 32,768 32,000 -
Llama 3.1 8B Instruct text text 16,384 16,384 -
Llama 3 8B Instruct text text 8,192 8,192 -
Llama3 70B Instruct text text 8,192 8,000 📋 -
Kat Coder Pro text text 256,000 128,000 🔧 📋 -
Ling-2.6-flash text text 262,144 32,768 🔧 📋 -
Ling-2.6-1T text text 262,144 32,768 🔧 📋 -
Mythomax L2 13B text text 4,096 3,200 -
Gemma 4 31B text, image text 262,144 131,072 🧠 🔧 📋 -
Gemma 4 26B A4B text, image text 262,144 131,072 🧠 🔧 📋 -
Gemma 3 27B text, image text 98,304 16,384 -
Gemma 3 12B text, image text 131,072 8,192 -
DeepSeek V4 Pro text text 1,048,576 393,216 🧠 🔧 📋 2025-05
DeepSeek V4 Flash text text 1,048,576 393,216 🧠 🔧 📋 2025-05
Deepseek V3.2 Exp text text 163,840 65,536 🧠 🔧 📋 -
Deepseek V3.2 text text 163,840 65,536 🧠 🔧 📋 -
Deepseek V3.1 Terminus text text 131,072 32,768 🧠 🔧 📋 -
DeepSeek V3.1 text text 131,072 32,768 🧠 🔧 📋 -
DeepSeek V3 (Turbo) text text 64,000 16,000 🔧 -
DeepSeek V3 0324 text text 163,840 163,840 🔧 📋 2024-07
DeepSeek R1 (Turbo) text text 64,000 16,000 🧠 🔧 -
DeepSeek R1 Distill Qwen 32B text text 64,000 32,000 -
DeepSeek R1 Distill Qwen 14B text text 32,768 16,384 -
DeepSeek R1 Distill LLama 70B text text 8,192 8,192 🧠 📋 -
DeepSeek R1 0528 Qwen3 8B text text 128,000 32,000 🧠 -
DeepSeek R1 0528 text text 163,840 32,768 🧠 🔧 📋 2024-07
Deepseek Prover V2 671B text text 160,000 160,000 -
deepseek/deepseek-ocr-2 text, image text 8,192 8,192 -
DeepSeek-OCR text, image text 8,192 8,192 📋 -
ERNIE 4.5 VL 424B A47B text, image text 123,000 16,000 🧠 -
ERNIE-4.5-VL-28B-A3B-Thinking text, image, video text 131,072 65,536 🧠 🔧 📋 -
ERNIE 4.5 VL 28B A3B text, image text 30,000 8,000 🧠 🔧 -
ERNIE 4.5 300B A47B text text 123,000 12,000 📋 -
ERNIE-4.5-21B-A3B-Thinking text text 131,072 65,536 🧠 2025-03
ERNIE 4.5 21B A3B text text 120,000 8,000 🔧 2025-03
baichuan-m2-32b text text 131,072 131,072 2024-12