| deepinfra/allenai/olmOCR-7B-0725-FP8 | deepinfra | 16,384 | |
| deepinfra/anthropic/claude-3-7-sonnet-latest | deepinfra | 200,000 | - Input
- Input (cached read)
- Output
|
| deepinfra/anthropic/claude-4-opus | deepinfra | 200,000 | |
| deepinfra/anthropic/claude-4-sonnet | deepinfra | 200,000 | |
| deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo | deepinfra | 32,768 | |
| deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B | deepinfra | 131,072 | |
| deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | deepinfra | 131,072 | |
| deepinfra/deepseek-ai/DeepSeek-R1-Turbo | deepinfra | 40,960 | |
| deepinfra/deepseek-ai/DeepSeek-V3.1 | deepinfra | 163,840 | - Input
- Input (cached read)
- Output
|
| deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus | deepinfra | 163,840 | - Input
- Input (cached read)
- Output
|
| deepinfra/google/gemini-2.0-flash-001 | deepinfra | 1,000,000 | |
| deepinfra/google/gemini-2.5-flash | deepinfra | 1,000,000 | |
| deepinfra/google/gemini-2.5-pro | deepinfra | 1,000,000 | |
| deepinfra/meta-llama/Llama-3.2-3B-Instruct | deepinfra | 131,072 | |
| deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo | deepinfra | 131,072 | |
| deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | deepinfra | 1,048,576 | |
| deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct | deepinfra | 327,680 | |
| deepinfra/meta-llama/Llama-Guard-4-12B | deepinfra | 163,840 | |
| deepinfra/meta-llama/Meta-Llama-3-8B-Instruct | deepinfra | 8,192 | |
| deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct | deepinfra | 131,072 | |
| deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | deepinfra | 131,072 | |
| deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct | deepinfra | 131,072 | |
| deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | deepinfra | 131,072 | |
| WizardLM 2 8x22B (Deep Infra) | deepinfra | 65,536 | |
| deepinfra/microsoft/phi-4 | deepinfra | 16,384 | |