| novita/zai-org/glm-4.5 | novita | 131,072 | - Input
- Input (cached read)
- Output
|
| novita/qwen/qwen3-235b-a22b-thinking-2507 | novita | 131,072 | |
| novita/meta-llama/llama-3.1-8b-instruct | novita | 16,384 | |
| novita/google/gemma-3-12b-it | novita | 131,072 | |
| novita/zai-org/glm-4.5v | novita | 65,536 | - Input
- Input (cached read)
- Output
|
| novita/openai/gpt-oss-20b | novita | 131,072 | |
| novita/qwen/qwen3-235b-a22b-instruct-2507 | novita | 131,072 | |
| novita/deepseek/deepseek-r1-distill-qwen-14b | novita | 32,768 | |
| novita/meta-llama/llama-3.3-70b-instruct | novita | 12,288 | |
| novita/qwen/qwen-2.5-72b-instruct | novita | 32,000 | |
| novita/mistralai/mistral-nemo | novita | 60,288 | |
| novita/minimaxai/minimax-m1-80k | novita | 1,000,000 | |
| novita/deepseek/deepseek-r1-0528 | novita | 64,000 | - Input
- Input (cached read)
- Output
|
| novita/deepseek/deepseek-r1-distill-qwen-32b | novita | 64,000 | |
| novita/meta-llama/llama-3-8b-instruct | novita | 8,192 | |
| novita/microsoft/wizardlm-2-8x22b | novita | 65,535 | |
| novita/deepseek/deepseek-r1-0528-qwen3-8b | novita | 128,000 | |
| novita/deepseek/deepseek-r1-distill-llama-70b | novita | 8,192 | |
| novita/meta-llama/llama-3-70b-instruct | novita | 8,192 | |
| novita/qwen/qwen3-235b-a22b-fp8 | novita | 40,960 | |
| novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | novita | 1,048,576 | |
| novita/meta-llama/llama-4-scout-17b-16e-instruct | novita | 131,072 | |
| novita/nousresearch/hermes-2-pro-llama-3-8b | novita | 8,192 | |
| novita/qwen/qwen2.5-vl-72b-instruct | novita | 32,768 | |
| novita/sao10k/l3-70b-euryale-v2.1 | novita | 8,192 | |