DeepSeek

DeepSeek provides endpoints for large language models. See their library of models here. We recommend experimenting to find the best-suited model for your use-case. Here are some general recommendations:

deepseek-v4-flash (default): fast V4 model, 1M context. Hybrid thinking + non-thinking.
deepseek-v4-pro: flagship V4 model, 1M context. Hybrid thinking + non-thinking.

DeepSeek does not have rate limits. See their docs for information about how to deal with slower responses during high traffic.

Installation

uv pip install -U openai agno

Authentication

Set your DEEPSEEK_API_KEY environment variable. Get your key from here.

export DEEPSEEK_API_KEY=***

setx DEEPSEEK_API_KEY ***

Example

Use DeepSeek with your Agent:

from agno.agent import Agent
from agno.models.deepseek import DeepSeek

agent = Agent(model=DeepSeek(id="deepseek-v4-flash"), markdown=True)

# Print the response in the terminal
agent.print_response("Share a 2 sentence horror story.")

View more examples here.

Parameters

Parameter	Type	Default	Description
`id`	`str`	`"deepseek-v4-flash"`	The id of the DeepSeek model to use
`name`	`str`	`"DeepSeek"`	The name of the model
`provider`	`str`	`"DeepSeek"`	The provider of the model
`api_key`	`Optional[str]`	`None`	The API key for DeepSeek (defaults to `DEEPSEEK_API_KEY` env var)
`base_url`	`str`	`"https://api.deepseek.com"`	The base URL for the DeepSeek API
`use_thinking`	`Optional[bool]`	`None`	Control thinking mode. See Thinking mode.

DeepSeek extends the OpenAI-compatible interface and supports most parameters from the OpenAI model. Note: DeepSeek supports JSON mode but not native json_schema structured outputs, so supports_native_structured_outputs is set to False. Use use_json_mode=True for structured output.

Available Models

Model id	Notes
`deepseek-v4-flash`	Fast V4 model (default), 1M context. Hybrid thinking + non-thinking.
`deepseek-v4-pro`	Flagship V4 model, 1M context. Hybrid thinking + non-thinking.

The legacy ids deepseek-chat and deepseek-reasoner still work and route server-side to the V4 models (deepseek-chat to non-thinking, deepseek-reasoner to thinking), but you should migrate to deepseek-v4-flash / deepseek-v4-pro.

Thinking mode

V4 models run with thinking enabled by default, so you get reasoning_content out of the box. Control it with the use_thinking flag:

Value	Behavior
`None` (default)	V4 models think by default; legacy `deepseek-chat` does not.
`True`	Force thinking on. The model returns `reasoning_content`.
`False`	Force thinking off for a faster, cheaper response.

For agent scenarios, DeepSeek recommends reasoning_effort="max". The API default is "high". While thinking is active, temperature, top_p, presence_penalty and frequency_penalty are ignored by the API.

from agno.agent import Agent
from agno.models.deepseek import DeepSeek

agent = Agent(
    model=DeepSeek(id="deepseek-v4-pro", reasoning_effort="max"),
    markdown=True,
)

Get Started

Basics

Advanced

Production

Providers

Other

Additional Resources

Installation

Authentication

Example

Parameters

Available Models

Thinking mode

​Installation

​Authentication

​Example

​Parameters

​Available Models

​Thinking mode

Installation

Authentication

Example

Parameters

Available Models

Thinking mode