Introduction

DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. Compared to the previous version, this upgrade brings improvements in multiple aspects:

• Hybrid thinking mode: One model supports both thinking mode and non-thinking mode by changing the chat template.
• Smarter tool calling: Through post-training optimization, the model's performance in tool usage and agent tasks has significantly improved.
• Higher thinking efficiency: DeepSeek-V3.1-Think achieves comparable answer quality to DeepSeek-R1-0528, while responding more quickly.

DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.

Model Downloads

Chat Template

The details of our chat template is described in tokenizer_config.json and assets/chat_template.jinja. Here is a brief description.

Non-Thinking

With the given prefix, DeepSeek V3.1 generates responses to queries in non-thinking mode. Unlike DeepSeek V3, it introduces an additional token </think>.

By concatenating the context and the prefix, we obtain the correct prompt for the query.

Thinking

The prefix of thinking mode is similar to DeepSeek-R1.

The multi-turn template is the same with non-thinking multi-turn chat template. It means the thinking token in the last turn will be dropped but the <think> is retained in every turn of context.

ToolCall

Toolcall is supported in non-thinking mode. The format is:

where the tool_description is:

## Tools
You have access to the following tools:

### {tool_name1}
Description: {description}
Parameters: {json.dumps(parameters)}

IMPORTANT: ALWAYS adhere to this exact format for tool use:
<｜tool_calls_begin｜><｜tool_call_begin｜>tool_call_name<｜tool_sep｜>tool_call_arguments<｜tool_call_end｜>[{additional_tool_calls}]<｜tool_calls_end｜>

Where:
- `tool_call_name` must be an exact match to one of the available tools
- `tool_call_arguments` must be valid JSON that strictly follows the tool's Parameters Schema
- For multiple tool calls, chain them directly without separators or spaces

Code-Agent: We support various code agent frameworks. Please refer to the above toolcall format to create your own code agents. An example is shown in assets/code_agent_trajectory.html.

Search-Agent: We design a specific format for searching toolcall in thinking mode, to support search agent. For complex questions that require accessing external or up-to-date information, DeepSeek-V3.1 can leverage a user-provided search tool through a multi-turn tool-calling process. Please refer to the assets/search_tool_trajectory.html and assets/search_python_tool_trajectory.html for the detailed template.

Evaluation

• Search agents are evaluated with our internal search framework, which uses a commercial search API + webpage filter + 128K context window. Search agent results of R1-0528 are evaluated with a pre-defined workflow.
• SWE-bench is evaluated with our internal code agent framework.
• HLE is evaluated with the text-only subset.

Usage Example

import transformers

tokenizer = transformers.AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V3.1")

messages = [
    {"role": "system", "content": "You are a helpful assistant"},
    {"role": "user", "content": "Who are you?"},
    {"role": "assistant", "content": "<think>Hmm</think>I am DeepSeek"},
    {"role": "user", "content": "1+1=?"}
]

tokenizer.apply_chat_template(messages, tokenize=False, thinking=True, add_generation_prompt=True)
# '<｜begin_of_sentence｜>You are a helpful assistant<｜User｜>Who are you?<｜Assistant｜><think>Hmm</think>I am DeepSeek<｜end_of_sentence｜><｜User｜>1+1=?<｜Assistant｜><think>'

tokenizer.apply_chat_template(messages, tokenize=False, thinking=False, add_generation_prompt=True)
# '<｜begin_of_sentence｜>You are a helpful assistant<｜User｜>Who are you?<｜Assistant｜></think>I am DeepSeek<｜end_of_sentence｜><｜User｜>1+1=?<｜Assistant｜></think>'