DeepSeek

Use DeepSeek with Blazen — construct the DeepseekProvider and call complete().

DeepSeek is an OpenAI-compatible LLM provider. Construct it like any other Blazen provider — build a list of ChatMessages, call complete() (or stream()), and read back a typed ModelResponse.

At a glance

Provider id	deepseek
Base URL	https://api.deepseek.com
Default model	deepseek-chat
API key env var	DEEPSEEK_API_KEY
Auth	Authorization: Bearer <key>

Set DEEPSEEK_API_KEY in the environment and Blazen reads it automatically, or pass the key explicitly when you construct the provider.

Capabilities

Capability	Supported
Streaming	Yes
Tool calling	Yes
Structured output	Yes
Vision	No
Model listing	No
Embeddings	No

Usage

Construct the provider and call complete(). The default model is deepseek-chat; override it with with_model / model when you need a different one.

use blazen_llm::{Model, ModelRequest, ChatMessage};
use blazen_provider_deepseek::DeepseekProvider;

// Reads DEEPSEEK_API_KEY from the environment, or pass the key to `new`.
let model = DeepseekProvider::new(std::env::var("DEEPSEEK_API_KEY")?);

let resp = model
    .complete(ModelRequest::new(vec![ChatMessage::user("Hello")]))
    .await?;
println!("{}", resp.content.unwrap_or_default());

from blazen import DeepseekProvider, ProviderOptions, ChatMessage

# Omit the api_key to read DEEPSEEK_API_KEY from the environment.
model = DeepseekProvider(options=ProviderOptions(api_key="..."))

resp = await model.complete([ChatMessage.user("Hello")])
print(resp.content)

import { DeepseekProvider, ChatMessage } from "blazen";

// Omit apiKey to read DEEPSEEK_API_KEY from the environment.
const model = DeepseekProvider.create({ apiKey: "..." });

const resp = await model.complete([ChatMessage.user("Hello")]);
console.log(resp.content);

Streaming

async for chunk in model.stream([ChatMessage.user("Count to five")]):
    print(chunk.delta, end="")

await model.stream([ChatMessage.user("Count to five")], (chunk) => {
  if (chunk.delta) process.stdout.write(chunk.delta);
});

See also

• Models & Providers — the canonical provider + ModelManager guide