# DeepSeek-V2.5

> DeepSeek's September 2024 model that fused its V2 chat and Coder-V2 models into one open-weight MoE assistant.

- Maker: DeepSeek
- Line: DeepSeek V3
- Canonical page: https://ai-tldr.dev/models/deepseek-v2-5/
- Updated: 2026-06-18

## In short

DeepSeek-V2.5 is an open-weight large language model released by DeepSeek on September 5, 2024. You can use it through DeepSeek, Hugging Face and Ollama.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 128K tokens (advertised; the published Hugging Face config sets max_model_len to 8,192) (max output Not officially published by DeepSeek) | [1] |
| Licence | Open weights — code under MIT License; model weights under the DeepSeek Model License (commercial use permitted). · open weights | [1] |
| Released | 5 September 2024 | [2] |
| Parameters | 236B total / 21B activated per token (Mixture-of-Experts) | [1] |
| Knowledge cutoff | Not officially published by DeepSeek | [1] |

## Sources

1. [DeepSeek-V2.5 model card — Hugging Face](https://huggingface.co/deepseek-ai/DeepSeek-V2.5)
2. [DeepSeek-V2.5 announcement — DeepSeek API Docs](https://api-docs.deepseek.com/news/news0905)

## Overview

DeepSeek-V2.5 is an open-weight large language model released by DeepSeek on September 5, 2024. It merged two earlier DeepSeek models — the general-purpose DeepSeek-V2-Chat (the 0628 checkpoint) and the code-focused DeepSeek-Coder-V2-Instruct (the 0724 checkpoint) — into a single assistant, so one model could handle everyday conversation and programming without users having to switch endpoints.

Under the hood DeepSeek-V2.5 keeps the DeepSeek-V2 architecture: a Mixture-of-Experts transformer with 236 billion total parameters of which about 21 billion are active per token, plus Multi-head Latent Attention (MLA) that compresses the key-value cache for cheaper inference. It is a text-only, non-reasoning model and supports a 128K-token context. The code is released under the MIT License and the weights under the DeepSeek Model License, which permits commercial use.

DeepSeek shipped a revised checkpoint, DeepSeek-V2.5-1210, on December 10, 2024, which improved math (MATH-500 from 74.8 to 82.8) and coding (LiveCodeBench from 29.2 to 34.38) along with file-upload and web-summarization tweaks. Shortly after, DeepSeek-V3 launched (December 26, 2024) and became the served model, making V2.5 a transitional release between the V2 and V3 generations.

## Benchmarks

- HumanEval (Python): 89pass@1 % ([source](https://huggingface.co/deepseek-ai/DeepSeek-V2.5))
- ArenaHard: 76.2win rate % ([source](https://huggingface.co/deepseek-ai/DeepSeek-V2.5))
- MMLU-Pro: 65.83% ([source](https://huggingface.co/deepseek-ai/DeepSeek-V2.5))
- AlpacaEval 2.0: 50.5LC win rate % ([source](https://huggingface.co/deepseek-ai/DeepSeek-V2.5))
- LiveCodeBench (01-09): 41.8% ([source](https://huggingface.co/deepseek-ai/DeepSeek-V2.5))
- MT-Bench: 9.02score (0-10) ([source](https://huggingface.co/deepseek-ai/DeepSeek-V2.5))
- AlignBench: 8.04score (0-10) ([source](https://huggingface.co/deepseek-ai/DeepSeek-V2.5))

## Strengths

- Combined strong general chat and coding in one model, removing the need to choose between a chat and a coder endpoint
- Backward-compatible API: existing deepseek-chat and deepseek-coder calls pointed to the new merged model
- MoE with MLA keeps only ~21B of 236B parameters active per token, making inference relatively cheap for its size
- Improved human-preference alignment and safety over DeepSeek-V2-0628 (overall safety score rose to 82.6% from 74.4%)
- Open weights with commercial-use permission, downloadable from Hugging Face
- Practical developer features carried over: function calling, JSON output, and Fill-in-the-Middle (FIM) code completion

## Best for

- General-purpose chat assistants that also need solid coding help
- Code generation, completion, and Fill-in-the-Middle tasks in developer tools
- Self-hosted or on-prem deployments where open weights and commercial licensing matter
- Function-calling and structured-JSON workflows
- A reproducible historical baseline for studying the DeepSeek V2-to-V3 transition

## How to access

- [DeepSeek](https://api-docs.deepseek.com/news/news0905) — model id `deepseek-chat`
- [Hugging Face](https://huggingface.co/deepseek-ai/DeepSeek-V2.5) — model id `deepseek-ai/DeepSeek-V2.5`
- [Ollama](https://ollama.com/library/deepseek-v2.5) — model id `deepseek-v2.5`

## DeepSeek V3 versions

- [DeepSeek-V3.2](https://ai-tldr.dev/models/deepseek-v3-2/) (1 December 2025)
- [DeepSeek-V3.2-Speciale](https://ai-tldr.dev/models/deepseek-v3-2-speciale/) (1 December 2025)
- [DeepSeek-V3.2-Exp](https://ai-tldr.dev/models/deepseek-v3-2-exp/) (29 September 2025)
- [DeepSeek-V3.1-Terminus](https://ai-tldr.dev/models/deepseek-v3-1-terminus/) (22 September 2025)
- [DeepSeek-V3.1](https://ai-tldr.dev/models/deepseek-v3-1/) (21 August 2025)
- [DeepSeek-V3-0324](https://ai-tldr.dev/models/deepseek-v3-0324/) (24 March 2025)
- [DeepSeek-V3](https://ai-tldr.dev/models/deepseek-v3/) (26 December 2024)
- DeepSeek-V2.5 (5 September 2024) — this page
- [DeepSeek-V2](https://ai-tldr.dev/models/deepseek-v2/) (May 2024)

## FAQ

### What is DeepSeek-V2.5?

DeepSeek-V2.5 is an open-weight large language model released on September 5, 2024 that merged DeepSeek-V2-Chat (the 0628 checkpoint) and DeepSeek-Coder-V2-Instruct (the 0724 checkpoint) into a single model good at both general chat and coding. It is a 236B-total / 21B-active Mixture-of-Experts model with 128K context.

### Is DeepSeek-V2.5 still the current model?

No. DeepSeek-V2.5 was revised as DeepSeek-V2.5-1210 on December 10, 2024, then superseded by DeepSeek-V3 (released December 26, 2024) and later versions. The open weights remain available on Hugging Face, but it is no longer DeepSeek's served model.

### What license does DeepSeek-V2.5 use, and can I use it commercially?

The code is released under the MIT License and the model weights under the DeepSeek Model License, which permits commercial use including deployment, fine-tuning, and building products on top of the model.

### How does DeepSeek-V2.5 perform on benchmarks?

DeepSeek's model card reports HumanEval (Python) 89, ArenaHard 76.2, MMLU-Pro 65.83, AlpacaEval 2.0 50.5, LiveCodeBench (01-09) 41.8, plus MT-Bench 9.02 and AlignBench 8.04 on their 0-10 scales — improving on both source models on most tests.

## Links

- [DeepSeek-V2.5 announcement — DeepSeek API Docs](https://api-docs.deepseek.com/news/news0905)
- [DeepSeek-V2.5 model card — Hugging Face](https://huggingface.co/deepseek-ai/DeepSeek-V2.5)
- [DeepSeek API change log (V2.5 & V2.5-1210)](https://api-docs.deepseek.com/updates)
- [DeepSeek-V2 paper (architecture: MLA + DeepSeekMoE)](https://arxiv.org/abs/2405.04434)
- [DeepSeek-V2.5 on Ollama](https://ollama.com/library/deepseek-v2.5)
- [DeepSeek-V2.5 — Artificial Analysis](https://artificialanalysis.ai/models/deepseek-v2-5)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/deepseek-v2-5/