Model Library
DeepSeekReleased December 10, 2024DeepSeek-V2.5 (Dec)
DeepSeek · Released December 10, 2024
Intelligence score
7
At a glance
- Intelligence
- 7
- Speed
- —
- Latency
- —
- Input price
- Not published
- Output price
- Not published
- Context window
- 130Ktokens
- Parameters
- 236billions
Summary
Comparison summary
DeepSeek-V2.5 (Dec '24) scores 7 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 17).
Specifications
Technical specifications
| Model name | DeepSeek-V2.5 (Dec) |
|---|---|
| Provider | DeepSeek |
| Release date | December 10, 2024 |
| Intelligence score | 7 |
| Speed | — |
| Latency (TTFT) | — |
| Input price | Not published |
| Output price | Not published |
| Context window | 130,000 tokens |
| Parameters | 236B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | DEEPSEEK LICENSE AGREEMENT |
| API availability | — |
| Source | Model Intelligence legacy profile: deepseek-v2-5 |
FAQ · 16
Frequently asked questions
DeepSeek-V2.5 (Dec '24) was released on December 10, 2024.
DeepSeek-V2.5 (Dec '24) was created by DeepSeek.
DeepSeek-V2.5 (Dec '24) scores 7 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 17).
No, DeepSeek-V2.5 (Dec '24) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
DeepSeek-V2.5 (Dec '24) supports text only input.
DeepSeek-V2.5 (Dec '24) supports text only output.
No, DeepSeek-V2.5 (Dec '24) does not support image input. It can only process text.
No, DeepSeek-V2.5 (Dec '24) is not multimodal. It only supports text only input.
DeepSeek-V2.5 (Dec '24) has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, DeepSeek-V2.5 (Dec '24) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
DeepSeek-V2.5 (Dec '24) has 236 billion parameters (21 billion active).
DeepSeek-V2.5 (Dec '24) is a Mixture of Experts (MoE) model with 236 billion total parameters, but only 21 billion active parameters are used during inference.
DeepSeek-V2.5 (Dec '24) is released under the DEEPSEEK LICENSE AGREEMENT license. This license allows commercial use.
DeepSeek-V2.5 (Dec '24) achieves a score of 7 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
DeepSeek-V2.5 (Dec '24) is an open weights model that can be self-hosted.
DeepSeek-V2.5 (Dec '24) is an open weights model that can be downloaded and self-hosted.