DeepSeek V3.1

DeepSeekMCP Tool CallReasoning
deepseek/deepseek-chat-v3.1Open Weights

DeepSeek chat model for instruction following, coding, and analysis

Benchmark Pricing$0.20 / 1M in$0.70 / 1M out$0.10 cache read
Context: 163,840 tokens•Max Output: 32,768 tokens•Knowledge: 2025-03-31•Released: 2025-08-21

TECHNICAL SPECIFICATIONS

Context Window163,840163.8K tokens
Max Output32,76832.8K tokens
LicenseOpen SourceSelf-hostable
Input Modalities
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ DeepSeek V3.1 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 163,840 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling DeepSeek V3.1 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-chat-v3.1",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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

PRICING BY PROVIDER

13 providers
NanoGPTdeepseek-ai/DeepSeek-V3.1
$0.20 / $0.70$0.10 cache
Meganovadeepseek-ai/DeepSeek-V3.1
$0.19 / $0.79
submodeldeepseek-ai/DeepSeek-V3.1
$0.20 / $0.80
CoreWeavedeepseek-ai/DeepSeek-V3.1
$0.55 / $1.65$0.55 cache
Basetendeepseek-ai/DeepSeek-V3.1
$0.50 / $1.50
Abacusdeepseek/deepseek-v3.1
$0.55 / $1.66
Merge Gatewaydeepseek/deepseek-v3.1
$0.56 / $1.68$0.13 cache
Together AIdeepseek-ai/DeepSeek-V3-1
$0.60 / $1.70
Kilo Gatewaydeepseek/deepseek-chat-v3.1
$0.25 / $0.95$0.13 cache
Vertexdeepseek-ai/deepseek-v3.1-maas
$0.60 / $1.70$0.06 cache
Alibaba (China)deepseek-v3-1
$0.57 / $1.72
Jiekou.AIdeepseek/deepseek-v3.1
$0.27 / $1.00
OpenRouterdeepseek/deepseek-chat-v3.1
$0.25 / $0.95$0.13 cache

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

Prompt Caching Active

This model supports prompt caching at $0.10 / 1M tokens, saving up to 50% 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