| novita/qwen/qwen2.5-7b-instruct | novita | 32,000 | |
| novita/meta-llama/llama-3.2-3b-instruct | novita | 32,768 | |
| novita/sao10k/l31-70b-euryale-v2.2 | novita | 8,192 | |
| novita/qwen/qwen3-embedding-0.6b | novita | 32,768 | |
| novita/qwen/qwen3-embedding-8b | novita | 32,768 | |
| novita/baai/bge-m3 | novita | 8,192 | |
| novita/qwen/qwen3-reranker-8b | novita | 32,768 | |
| novita/baai/bge-reranker-v2-m3 | novita | 8,000 | |
| novita/zai-org/glm-5.3 | novita | 1,048,576 | - Input
- Input (cached read)
- Output
|
| novita/deepseek/deepseek-v4-pro-0813 | novita | 1,048,576 | - Input
- Input (cached read)
- Output
|
| novita/moonshotai/kimi-k3 | novita | 1,048,576 | - Input
- Input (cached read)
- Output
|
| novita/tencent/hy3 | novita | 262,144 | - Input
- Input (cached read)
- Output
|
| novita/zai-org/glm-5.2 | novita | 1,048,576 | - Input
- Input (cached read)
- Output
|
| novita/moonshotai/kimi-k2.7-code | novita | 262,144 | - Input
- Input (cached read)
- Output
|
| novita/deepseek/deepseek-v4-flash-vision-exp | novita | 1,048,576 | - Input
- Input (cached read)
- Output
|
| novita/deepseek/deepseek-v4-flash-0731 | novita | 1,048,576 | - Input
- Input (cached read)
- Output
|
| novita/mindai/macaron-v1-venti | novita | 1,048,576 | - Input
- Input (cached read)
- Output
|
| novita/minimax/minimax-m3 | novita | 1,000,000 | - Input
- Input (cached read)
- Output
|
| novita/inclusionai/ling-3.0-flash-fast | novita | 262,144 | - Input
- Input (cached read)
- Output
|
| novita/qwen/qwen3.8-max | novita | 1,000,000 | - Input
- Input (cached read)
- Output
|
| novita/inclusionai/ling-3.0-flash | novita | 262,144 | - Input
- Input (cached read)
- Output
|
| novita/mindai/macaron-v1-tall | novita | 262,144 | - Input
- Input (cached read)
- Output
|
| novita/stepfun/step-3.7-flash | novita | 262,144 | - Input
- Input (cached read)
- Output
|
| novita/nvidia/nemotron-3-nano-30b-a3b | novita | 262,144 | |
| novita/baidu/cobuddy | novita | 131,072 | - Input
- Input (cached read)
- Output
|