DeepSeek R1 0528 Qwen3 8B

DeepSeekReasoning

deepseek/deepseek-r1-0528-qwen3-8bOpen Weights

DeepSeek R1 0528 distilled into Qwen3 8B for mathematics, coding, and reasoning

Benchmark Pricing$0.06 / 1M in$0.09 / 1M out

Context: 131,072 tokens•Max Output: 32,000 tokens•Released: 2025-05-29

TECHNICAL SPECIFICATIONS

Context Window131,072131.1K tokens

Max Output32,00032K tokens

LicenseMITSelf-hostable

Input Modalities

Text

Function / Tool CallingNot Supported

Structured OutputsPrompt Based

MODEL CONTEXT PROTOCOL (MCP) READINESS

⚠ DeepSeek R1 0528 Qwen3 8B does not natively advertise tool-calling capabilities. When connecting to MCP servers, function calling must be handled via structured prompt injection.

MCP Context Window Recommendations

With a context capacity of 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling DeepSeek R1 0528 Qwen3 8B via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.DEEPSEEK_API_KEY,
});

const response = await client.chat.completions.create({
  model: "deepseek/deepseek-r1-0528-qwen3-8b",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);