DeepSeek-R1-Turbo-DI

Bot Information

Creator: @deepinfra

Description: Top open-source reasoning LLM rivaling OpenAI's o1 model; delivers top-tier performance across math, code, and reasoning tasks at a fraction of the cost. Turbo model is quantized to achieve higher speeds. All data you provide this bot will not be used in training, and is sent only to DeepInfra, a US-based company.

Supports 32k tokens of input context and 8k tokens of output context. Quantization: FP4 (turbo).

Extra: Powered by a server managed by @deepinfra. Learn more

Architecture

Input Modalities: text

Output Modalities: text

Modality: text->text

Pricing

| Type | Cost |

|------|------|

| Total Cost | 500 points/message |

| Initial Points Cost | 500 points |

Last Checked: 2025-08-05 23:18:58.847977

Technical Details

Model ID: DeepSeek-R1-Turbo-DI

Object Type: model

Created: 1741250889407

Owned By: poe

Root: DeepSeek-R1-Turbo-DI