| DeepSeek-R1 (Deep Infra) | deepinfra | 163,840 | - Input
- Input (cached read)
- Output
|
| Llama 3.1 Nemotron 70B Instruct (Deep Infra) | deepinfra | 131,072 | |
| Nemotron 3 Nano 30B A3B (Deep Infra) | deepinfra | 262,144 | - Input
- Input (cached read)
- Output
|
| Muse Glimmer 30B (Deep Infra) | deepinfra | 131,072 | - Input
- Input (cached read)
- Output
|
| Gemma 3 4B IT (Deep Infra) | deepinfra | 131,072 | |
| Gemma 3 27B IT (Deep Infra) | deepinfra | 131,072 | |
| Gemma 3 12B IT (Deep Infra) | deepinfra | 131,072 | |
| GLM-4.7-Flash (Deep Infra) | deepinfra | 202,752 | - Input
- Input (cached read)
- Output
|
| Inkling Small (Deep Infra) | deepinfra | 524,288 | - Input
- Input (cached read)
- Output
|
| Inkling (Deep Infra) | deepinfra | 524,288 | - Input
- Input (cached read)
- Output
|
| Llama-Guard-3-8B (Deep Infra) | deepinfra | 131,072 | |
| Llama-3.3-70B-Instruct (Deep Infra) | deepinfra | 131,072 | |
| Llama-3.2-11B-Vision-Instruct (Deep Infra) | deepinfra | 131,072 | |
| GPT OSS 20B (Deep Infra) | deepinfra | 131,072 | |
| GPT OSS 120B (Deep Infra) | deepinfra | 131,072 | |
| Kimi K2.5 (Deep Infra) | deepinfra | 262,144 | - Input
- Input (cached read)
- Output
|
| Hy3 (Deep Infra) | deepinfra | 262,144 | - Input
- Input (cached read)
- Output
|
| deepinfra/Gryphe/MythoMax-L2-13b | deepinfra | 4,096 | |
| deepinfra/NousResearch/Hermes-3-Llama-3.1-405B | deepinfra | 131,072 | |
| deepinfra/NousResearch/Hermes-3-Llama-3.1-70B | deepinfra | 131,072 | |
| deepinfra/Qwen/QwQ-32B | deepinfra | 131,072 | |
| deepinfra/Qwen/Qwen2.5-72B-Instruct | deepinfra | 32,768 | |
| deepinfra/Qwen/Qwen2.5-7B-Instruct | deepinfra | 32,768 | |
| deepinfra/Qwen/Qwen2.5-VL-32B-Instruct | deepinfra | 128,000 | |
| deepinfra/Qwen/Qwen3-14B | deepinfra | 40,960 | |