Browse all 135 AI models from Novita
Click on any model to view details
Model Name↑ | Provider | Mode | Pricing | Max Input Tokens | Max Output Tokens | Capabilities |
|---|---|---|---|---|---|---|
autoglm-phone-9b-multilingual novita/zai-org/autoglm-phone-9b-multilingual | Chat | Input $0.035000 / 1M tokensOutput $0.138000 / 1M tokens | 65,536 | 65,536 | Vision | |
baichuan-m2-32b novita/baichuan/baichuan-m2-32b | Chat | Input $0.070000 / 1M tokensOutput $0.070000 / 1M tokens | 131k | 131k | ||
bge-m3 novita/baai/bge-m3 | Embedding | Input $0.010000 / 1M tokensOutput $0.010000 / 1M tokens | 8,192 | 96,000 | ||
bge-reranker-v2-m3 novita/baai/bge-reranker-v2-m3 | Rerank | Input $0.010000 / 1M tokensOutput $0.010000 / 1M tokens | 8,000 | 8,000 | ||
deepseek-ocr novita/deepseek/deepseek-ocr | Chat | Input $0.030000 / 1M tokensOutput $0.030000 / 1M tokens | 8,192 | 8,192 | Vision | |
deepseek-prover-v2-671b novita/deepseek/deepseek-prover-v2-671b | Chat | Input $0.700000 / 1M tokensOutput $2.50 / 1M tokens | 160k | 160k | ||
deepseek-r1-0528 novita/deepseek/deepseek-r1-0528 | Chat | Input $0.700000 / 1M tokensOutput $2.50 / 1M tokens | 163k | 32,768 | FunctionsReasoning | |
deepseek-r1-0528-qwen3-8b novita/deepseek/deepseek-r1-0528-qwen3-8b | Chat | Input $0.060000 / 1M tokensOutput $0.090000 / 1M tokens | 128k | 32,000 | Reasoning | |
deepseek-r1-distill-llama-70b novita/deepseek/deepseek-r1-distill-llama-70b | Chat | Input $0.800000 / 1M tokensOutput $0.800000 / 1M tokens | 8,192 | 8,192 | Reasoning | |
deepseek-r1-distill-qwen-14b novita/deepseek/deepseek-r1-distill-qwen-14b | Chat | Input $0.150000 / 1M tokensOutput $0.150000 / 1M tokens | 32,768 | 16,384 | Reasoning | |
deepseek-r1-distill-qwen-32b novita/deepseek/deepseek-r1-distill-qwen-32b | Chat | Input $0.300000 / 1M tokensOutput $0.300000 / 1M tokens | 64,000 | 32,000 | Reasoning | |
deepseek-r1-turbo novita/deepseek/deepseek-r1-turbo | Chat | Input $0.700000 / 1M tokensOutput $2.50 / 1M tokens | 64,000 | 16,000 | FunctionsReasoning | |
deepseek-v3-0324 novita/deepseek/deepseek-v3-0324 | Chat | Input $0.270000 / 1M tokensOutput $1.12 / 1M tokens | 163k | 65,536 | Functions | |
deepseek-v3-turbo novita/deepseek/deepseek-v3-turbo | Chat | Input $0.400000 / 1M tokensOutput $1.30 / 1M tokens | 64,000 | 16,000 | Functions | |
deepseek-v3.1 novita/deepseek/deepseek-v3.1 | Chat | Input $0.270000 / 1M tokensOutput $1.00 / 1M tokens | 131k | 32,768 | FunctionsReasoning | |
deepseek-v3.1-terminus novita/deepseek/deepseek-v3.1-terminus | Chat | Input $0.270000 / 1M tokensOutput $1.00 / 1M tokens | 131k | 32,768 | FunctionsReasoning | |
deepseek-v3.2 novita/deepseek/deepseek-v3.2 | Chat | Input $0.269000 / 1M tokensOutput $0.400000 / 1M tokens | 163k | 65,536 | FunctionsReasoning | |
deepseek-v3.2-exp novita/deepseek/deepseek-v3.2-exp | Chat | Input $0.270000 / 1M tokensOutput $0.410000 / 1M tokens | 163k | 65,536 | FunctionsReasoning | |
deepseek-v4-flash novita/deepseek/deepseek-v4-flash | Chat | Input $0.140000 / 1M tokensOutput $0.280000 / 1M tokens | 1048k | 393k | FunctionsReasoning | |
deepseek-v4-flash-0731 novita/deepseek/deepseek-v4-flash-0731 | Chat | Input $0.440000 / 1M tokensOutput $1.32 / 1M tokens | 1048k | 393k | FunctionsReasoning | |
deepseek-v4-flash-vision-exp novita/deepseek/deepseek-v4-flash-vision-exp | Chat | Input $0.440000 / 1M tokensOutput $1.32 / 1M tokens | 1048k | 393k | FunctionsVisionReasoning | |
deepseek-v4-pro novita/deepseek/deepseek-v4-pro | Chat | Input $1.60 / 1M tokensOutput $3.20 / 1M tokens | 1048k | 393k | FunctionsReasoning | |
deepseek-v4-pro-0813 novita/deepseek/deepseek-v4-pro-0813 | Chat | Input $1.32 / 1M tokensOutput $3.96 / 1M tokens | 1048k | 393k | FunctionsReasoning | |
ernie-4.5-21B-a3b novita/baidu/ernie-4.5-21B-a3b | Chat | Input $0.070000 / 1M tokensOutput $0.280000 / 1M tokens | 120k | 8,000 | Functions | |
ernie-4.5-21B-a3b-thinking novita/baidu/ernie-4.5-21B-a3b-thinking | Chat | Input $0.070000 / 1M tokensOutput $0.280000 / 1M tokens | 131k | 65,536 | Reasoning | |
ernie-4.5-300b-a47b-paddle novita/baidu/ernie-4.5-300b-a47b-paddle | Chat | Input $0.280000 / 1M tokensOutput $1.10 / 1M tokens | 123k | 12,000 | ||
ernie-4.5-vl-28b-a3b novita/baidu/ernie-4.5-vl-28b-a3b | Chat | Input $0.140000 / 1M tokensOutput $0.560000 / 1M tokens | 30,000 | 8,000 | FunctionsVisionReasoning | |
ernie-4.5-vl-28b-a3b-thinking novita/baidu/ernie-4.5-vl-28b-a3b-thinking | Chat | Input $0.390000 / 1M tokensOutput $0.390000 / 1M tokens | 131k | 65,536 | FunctionsVisionReasoning | |
ernie-4.5-vl-424b-a47b novita/baidu/ernie-4.5-vl-424b-a47b | Chat | Input $0.420000 / 1M tokensOutput $1.25 / 1M tokens | 123k | 16,000 | VisionReasoning | |
gemma-3-12b-it novita/google/gemma-3-12b-it | Chat | Input $0.050000 / 1M tokensOutput $0.100000 / 1M tokens | 131k | 8,192 | Vision | |
gemma-3-27b-it novita/google/gemma-3-27b-it | Chat | Input $0.119000 / 1M tokensOutput $0.200000 / 1M tokens | 98,304 | 16,384 | Vision | |
glm-4.5 novita/zai-org/glm-4.5 | Chat | Input $0.600000 / 1M tokensOutput $2.20 / 1M tokens | 131k | 98,304 | FunctionsReasoning | |
glm-4.5-air novita/zai-org/glm-4.5-air | Chat | Input $0.130000 / 1M tokensOutput $0.850000 / 1M tokens | 131k | 98,304 | FunctionsReasoning | |
glm-4.5v novita/zai-org/glm-4.5v | Chat | Input $0.600000 / 1M tokensOutput $1.80 / 1M tokens | 65,536 | 16,384 | FunctionsVisionReasoning | |
glm-4.6 novita/zai-org/glm-4.6 | Chat | Input $0.550000 / 1M tokensOutput $2.20 / 1M tokens | 204k | 131k | FunctionsReasoning | |
glm-4.6v novita/zai-org/glm-4.6v | Chat | Input $0.300000 / 1M tokensOutput $0.900000 / 1M tokens | 131k | 32,768 | FunctionsVisionReasoning | |
glm-4.7 novita/zai-org/glm-4.7 | Chat | Input $0.600000 / 1M tokensOutput $2.20 / 1M tokens | 204k | 131k | FunctionsReasoning | |
glm-5.2 novita/zai-org/glm-5.2 | Chat | Input $1.40 / 1M tokensOutput $4.40 / 1M tokens | 1048k | 131k | FunctionsReasoning | |
glm-5.3 novita/zai-org/glm-5.3 | Chat | Input $1.40 / 1M tokensOutput $4.40 / 1M tokens | 1048k | 131k | FunctionsReasoning | |
gpt-oss-120b novita/openai/gpt-oss-120b | Chat | Input $0.050000 / 1M tokensOutput $0.250000 / 1M tokens | 131k | 32,768 | FunctionsReasoning | |
gpt-oss-20b novita/openai/gpt-oss-20b | Chat | Input $0.040000 / 1M tokensOutput $0.150000 / 1M tokens | 131k | 32,768 | Reasoning | |
hermes-2-pro-llama-3-8b novita/nousresearch/hermes-2-pro-llama-3-8b | Chat | Input $0.140000 / 1M tokensOutput $0.140000 / 1M tokens | 8,192 | 8,192 | ||
hy3 novita/tencent/hy3 | Chat | Input $0.140000 / 1M tokensOutput $0.580000 / 1M tokens | 262k | 262k | FunctionsReasoning | |
kat-coder-pro novita/kwaipilot/kat-coder-pro | Chat | Input $0.300000 / 1M tokensOutput $1.20 / 1M tokens | 256k | 128k | Functions | |
kimi-k2-0905 novita/moonshotai/kimi-k2-0905 | Chat | Input $0.600000 / 1M tokensOutput $2.50 / 1M tokens | 262k | 100k | Functions | |
kimi-k2-instruct novita/moonshotai/kimi-k2-instruct | Chat | Input $0.570000 / 1M tokensOutput $2.30 / 1M tokens | 131k | 100k | Functions | |
kimi-k2-thinking novita/moonshotai/kimi-k2-thinking | Chat | Input $0.600000 / 1M tokensOutput $2.50 / 1M tokens | 262k | 100k | FunctionsReasoning | |
kimi-k2.7-code novita/moonshotai/kimi-k2.7-code | Chat | Input $0.950000 / 1M tokensOutput $4.00 / 1M tokens | 262k | 262k | FunctionsVisionReasoning | |
kimi-k3 novita/moonshotai/kimi-k3 | Chat | Input $3.00 / 1M tokensOutput $15.00 / 1M tokens | 1048k | 1048k | FunctionsVisionReasoning | |
l3-70b-euryale-v2.1 novita/sao10k/l3-70b-euryale-v2.1 | Chat | Input $1.48 / 1M tokensOutput $1.48 / 1M tokens | 8,192 | 8,192 | Functions | |
l3-8b-lunaris novita/sao10k/l3-8b-lunaris | Chat | Input $0.050000 / 1M tokensOutput $0.050000 / 1M tokens | 8,192 | 8,192 | ||
L3-8B-Stheno-v3.2 novita/Sao10K/L3-8B-Stheno-v3.2 | Chat | Input $0.050000 / 1M tokensOutput $0.050000 / 1M tokens | 8,192 | 32,000 | Functions | |
l31-70b-euryale-v2.2 novita/sao10k/l31-70b-euryale-v2.2 | Chat | Input $1.48 / 1M tokensOutput $1.48 / 1M tokens | 8,192 | 8,192 | Functions | |
ling-3.0-flash novita/inclusionai/ling-3.0-flash | Chat | Input $0.060000 / 1M tokensOutput $0.180000 / 1M tokens | 262k | 32,768 | FunctionsReasoning | |
ling-3.0-flash-fast novita/inclusionai/ling-3.0-flash-fast | Chat | Input $0.060000 / 1M tokensOutput $0.180000 / 1M tokens | 262k | 32,768 | FunctionsReasoning | |
llama-3-70b-instruct novita/meta-llama/llama-3-70b-instruct | Chat | Input $0.510000 / 1M tokensOutput $0.740000 / 1M tokens | 8,192 | 8,000 | ||
llama-3-8b-instruct novita/meta-llama/llama-3-8b-instruct | Chat | Input $0.040000 / 1M tokensOutput $0.040000 / 1M tokens | 8,192 | 8,192 | ||
llama-3.1-8b-instruct novita/meta-llama/llama-3.1-8b-instruct | Chat | Input $0.020000 / 1M tokensOutput $0.050000 / 1M tokens | 16,384 | 16,384 | ||
llama-3.2-3b-instruct novita/meta-llama/llama-3.2-3b-instruct | Chat | Input $0.030000 / 1M tokensOutput $0.050000 / 1M tokens | 32,768 | 32,000 | Functions | |
llama-3.3-70b-instruct novita/meta-llama/llama-3.3-70b-instruct | Chat | Input $0.135000 / 1M tokensOutput $0.400000 / 1M tokens | 12,288 | 12,288 | Functions | |
llama-4-maverick-17b-128e-instruct-fp8 novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | Chat | Input $0.270000 / 1M tokensOutput $0.850000 / 1M tokens | 1048k | 8,192 | Vision | |
llama-4-scout-17b-16e-instruct novita/meta-llama/llama-4-scout-17b-16e-instruct | Chat | Input $0.180000 / 1M tokensOutput $0.590000 / 1M tokens | 131k | 131k | Vision | |
macaron-v1-venti novita/mindai/macaron-v1-venti | Chat | Input $0.825000 / 1M tokensOutput $2.48 / 1M tokens | 1048k | 131k | FunctionsReasoning | |
mimo-v2-flash novita/xiaomimimo/mimo-v2-flash | Chat | Input $0.100000 / 1M tokensOutput $0.300000 / 1M tokens | 262k | 32,000 | FunctionsReasoning | |
minimax-m1-80k novita/minimaxai/minimax-m1-80k | Chat | Input $0.550000 / 1M tokensOutput $2.20 / 1M tokens | 1000k | 40,000 | FunctionsReasoning | |
minimax-m2 novita/minimax/minimax-m2 | Chat | Input $0.300000 / 1M tokensOutput $1.20 / 1M tokens | 204k | 131k | FunctionsReasoning | |
minimax-m2.1 novita/minimax/minimax-m2.1 | Chat | Input $0.300000 / 1M tokensOutput $1.20 / 1M tokens | 204k | 131k | Functions | |
minimax-m3 novita/minimax/minimax-m3 | Chat | Input $0.300000 / 1M tokensOutput $1.20 / 1M tokens | 1000k | 131k | FunctionsVisionReasoning | |
mistral-nemo novita/mistralai/mistral-nemo | Chat | Input $0.040000 / 1M tokensOutput $0.170000 / 1M tokens | 60,288 | 16,000 | ||
mythomax-l2-13b novita/gryphe/mythomax-l2-13b | Chat | Input $0.090000 / 1M tokensOutput $0.090000 / 1M tokens | 4,096 | 3,200 | ||
paddleocr-vl novita/paddlepaddle/paddleocr-vl | Chat | Input $0.020000 / 1M tokensOutput $0.020000 / 1M tokens | 16,384 | 16,384 | Vision | |
qwen-2.5-72b-instruct novita/qwen/qwen-2.5-72b-instruct | Chat | Input $0.380000 / 1M tokensOutput $0.400000 / 1M tokens | 32,000 | 8,192 | Functions | |
qwen-mt-plus novita/qwen/qwen-mt-plus | Chat | Input $0.250000 / 1M tokensOutput $0.750000 / 1M tokens | 16,384 | 8,192 | ||
qwen2.5-7b-instruct novita/qwen/qwen2.5-7b-instruct | Chat | Input $0.070000 / 1M tokensOutput $0.070000 / 1M tokens | 32,000 | 8,192 | Functions | |
qwen2.5-vl-72b-instruct novita/qwen/qwen2.5-vl-72b-instruct | Chat | Input $0.800000 / 1M tokensOutput $0.800000 / 1M tokens | 32,768 | 32,768 | Vision | |
qwen3-235b-a22b-fp8 novita/qwen/qwen3-235b-a22b-fp8 | Chat | Input $0.200000 / 1M tokensOutput $0.800000 / 1M tokens | 40,960 | 20,000 | Reasoning | |
qwen3-235b-a22b-instruct-2507 novita/qwen/qwen3-235b-a22b-instruct-2507 | Chat | Input $0.090000 / 1M tokensOutput $0.580000 / 1M tokens | 131k | 16,384 | Functions | |
qwen3-235b-a22b-thinking-2507 novita/qwen/qwen3-235b-a22b-thinking-2507 | Chat | Input $0.300000 / 1M tokensOutput $3.00 / 1M tokens | 131k | 32,768 | FunctionsReasoning | |
qwen3-30b-a3b-fp8 novita/qwen/qwen3-30b-a3b-fp8 | Chat | Input $0.090000 / 1M tokensOutput $0.450000 / 1M tokens | 40,960 | 20,000 | FunctionsReasoning | |
qwen3-32b-fp8 novita/qwen/qwen3-32b-fp8 | Chat | Input $0.100000 / 1M tokensOutput $0.450000 / 1M tokens | 40,960 | 20,000 | Reasoning | |
qwen3-4b-fp8 novita/qwen/qwen3-4b-fp8 | Chat | Input $0.030000 / 1M tokensOutput $0.030000 / 1M tokens | 128k | 8,192 | FunctionsReasoning | |
qwen3-8b-fp8 novita/qwen/qwen3-8b-fp8 | Chat | Input $0.035000 / 1M tokensOutput $0.138000 / 1M tokens | 128k | 20,000 | Reasoning | |
qwen3-coder-30b-a3b-instruct novita/qwen/qwen3-coder-30b-a3b-instruct | Chat | Input $0.070000 / 1M tokensOutput $0.270000 / 1M tokens | 160k | 32,768 | Functions | |
qwen3-coder-480b-a35b-instruct novita/qwen/qwen3-coder-480b-a35b-instruct | Chat | Input $0.300000 / 1M tokensOutput $1.30 / 1M tokens | 262k | 65,536 | Functions | |
qwen3-embedding-0.6b novita/qwen/qwen3-embedding-0.6b | Embedding | Input $0.070000 / 1M tokensOutput $0.0000000000 / 1M tokens | 32,768 | 32,768 | ||
qwen3-embedding-8b novita/qwen/qwen3-embedding-8b | Embedding | Input $0.070000 / 1M tokensOutput $0.0000000000 / 1M tokens | 32,768 | 4,096 | ||
qwen3-max novita/qwen/qwen3-max | Chat | Input $2.11 / 1M tokensOutput $8.45 / 1M tokens | 262k | 65,536 | Functions | |
qwen3-next-80b-a3b-instruct novita/qwen/qwen3-next-80b-a3b-instruct | Chat | Input $0.150000 / 1M tokensOutput $1.50 / 1M tokens | 131k | 32,768 | FunctionsReasoning | |
qwen3-next-80b-a3b-thinking novita/qwen/qwen3-next-80b-a3b-thinking | Chat | Input $0.150000 / 1M tokensOutput $1.50 / 1M tokens | 131k | 32,768 | FunctionsReasoning | |
qwen3-omni-30b-a3b-instruct novita/qwen/qwen3-omni-30b-a3b-instruct | Chat | Input $0.250000 / 1M tokensOutput $0.970000 / 1M tokens | 65,536 | 16,384 | FunctionsVisionAudio InAudio Out | |
qwen3-omni-30b-a3b-thinking novita/qwen/qwen3-omni-30b-a3b-thinking | Chat | Input $0.250000 / 1M tokensOutput $0.970000 / 1M tokens | 65,536 | 16,384 | FunctionsVisionReasoningAudio In | |
qwen3-reranker-8b novita/qwen/qwen3-reranker-8b | Rerank | Input $0.050000 / 1M tokensOutput $0.050000 / 1M tokens | 32,768 | 4,096 | ||
qwen3-vl-235b-a22b-instruct novita/qwen/qwen3-vl-235b-a22b-instruct | Chat | Input $0.300000 / 1M tokensOutput $1.50 / 1M tokens | 131k | 32,768 | FunctionsVision | |
qwen3-vl-235b-a22b-thinking novita/qwen/qwen3-vl-235b-a22b-thinking | Chat | Input $0.980000 / 1M tokensOutput $3.95 / 1M tokens | 131k | 32,768 | FunctionsVisionReasoning | |
qwen3-vl-30b-a3b-instruct novita/qwen/qwen3-vl-30b-a3b-instruct | Chat | Input $0.200000 / 1M tokensOutput $0.700000 / 1M tokens | 131k | 32,768 | FunctionsVision | |
qwen3-vl-30b-a3b-thinking novita/qwen/qwen3-vl-30b-a3b-thinking | Chat | Input $0.200000 / 1M tokensOutput $1.00 / 1M tokens | 131k | 32,768 | FunctionsVision | |
qwen3-vl-8b-instruct novita/qwen/qwen3-vl-8b-instruct | Chat | Input $0.080000 / 1M tokensOutput $0.500000 / 1M tokens | 131k | 32,768 | FunctionsVision | |
qwen3.8-max novita/qwen/qwen3.8-max | Chat | Input $2.00 / 1M tokensOutput $6.00 / 1M tokens | 1000k | 131k | FunctionsVisionReasoning | |
r1v4-lite novita/skywork/r1v4-lite | Chat | Input $0.200000 / 1M tokensOutput $0.600000 / 1M tokens | 262k | 65,536 | Vision | |
wizardlm-2-8x22b novita/microsoft/wizardlm-2-8x22b | Chat | Input $0.620000 / 1M tokensOutput $0.620000 / 1M tokens | 65,535 | 8,000 |