DeepSeek V3.2

DeepSeekMCP Tool CallReasoning
deepseek/deepseek-v3.2Open Weights

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use

Benchmark Pricing$0.50 / 1M in$1.50 / 1M out$0.15 cache read
Context: 128,000 tokens•Max Output: 64,000 tokens•Knowledge: 2024-07•Released: 2025-12-01

TECHNICAL SPECIFICATIONS

Context Window128,000128K tokens
Max Output64,00064K tokens
LicenseMIT LicenseSelf-hostable
Input Modalities
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ DeepSeek V3.2 natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 128,000 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling DeepSeek V3.2 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-v3.2",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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

PRICING BY PROVIDER

15 providers
Cortecsdeepseek-v3.2
$0.50 / $1.50$0.15 cache
NanoGPTTEE/deepseek-v3.2
$0.50 / $1.00$0.25 cache
TokenGodeepseek/deepseek-v3.2
$0.22 / $0.33$0.06 cache
Meganovadeepseek-ai/DeepSeek-V3.2
$0.26 / $0.38$0.13 cache
302.AIdeepseek-v3.2
$0.29 / $0.43
Vivgriddeepseek-v3.2
$0.28 / $0.42$0.03 cache
LLM Gatewaynovita/deepseek-v3.2
$0.27 / $0.40$0.13 cache
Poenovita/deepseek-v3.2
$0.26 / $0.38$0.13 cache
Friendlideepseek-ai/DeepSeek-V3.2
$0.50 / $1.50$0.25 cache
Venice AIdeepseek-v3.2
$0.33 / $0.48$0.16 cache
Abacusdeepseek-ai/DeepSeek-V3.2
$0.27 / $0.40
Vercel AI Gatewaydeepseek/deepseek-v3.2
$0.62 / $1.85
NEAR AI Clouddeepseek/deepseek-v3.2
$1.10 / $1.10$0.55 cache
Meliousdeepseek-v3.2
$0.35 / $0.58$0.09 cache
Ofoxdeepseek/deepseek-v3.2
$0.29 / $0.43$0.06 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.15 / 1M tokens, saving up to 70% on repetitive MCP tool definitions and system instructions.

MODEL RESOURCES

View DeepSeek HubHugging Face Weights

More Models by DeepSeek

Alternative and family models from the same lab

View all DeepSeek models →
DeepSeek V4.1 Flash 1017
deepseek/deepseek-v4.1-flash-1017•DeepSeek
1M ctx

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

384K out maxVisionHumanity's Last Exam: 42.6 (unit not reported)
In: $0.15 • Out: $0.60
DeepSeek
DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-0813•DeepSeek
1M ctx

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

384K out maxHumanity's Last Exam: 42.7 score
In: $2.00 • Out: $4.00
DeepSeek
DeepSeek V4 Pro 0423
deepseek/deepseek-v4-pro-0423•DeepSeek
1M ctx

DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes

384K out max
In: $1.32 • Out: $3.96
DeepSeek