DeepSeek-R1

DeepSeekMCP Tool CallReasoning
deepseek/deepseek-r1Open Weights

Classic open reasoning model for transparent math, coding, and deliberate problem solving

Benchmark Pricing$0.70 / 1M in$2.50 / 1M out$0.35 cache read
Context: 128,000 tokens•Max Output: 32,768 tokens•Knowledge: 2024-07•Released: 2025-01-20

TECHNICAL SPECIFICATIONS

Context Window128,000128K 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-R1 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.

STANDARDIZED BENCHMARKS & EVALS

Aider Polyglotpercent correct
56.9
Artificial Analysis Coding Indexindex
15.9
SciCodepercent correct
35.7
Terminal-Bench Hardsuccess rate
6.1

API CALL INVOCATION EXAMPLE

// Example: Calling DeepSeek-R1 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",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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

PRICING BY PROVIDER

15 providers
Novita AIdeepseek/deepseek-r1-0528
$0.70 / $2.50$0.35 cache
D.Run (China)public/deepseek-r1
$0.55 / $2.20
Vercel AI Gatewaydeepseek/deepseek-r1
$1.35 / $5.40
Eden AItensorx/deepseek/deepseek-r1-0528
$0.66 / $2.60$0.17 cache
Meliousdeepseek-r1-0528
$0.70 / $2.78$0.19 cache
Merge Gatewaydeepseek/deepseek-r1-0528
$1.35 / $5.40$0.94 cache
Azure Cognitive Servicesdeepseek-r1
$1.35 / $5.40
Hugging Facedeepseek-ai/DeepSeek-R1
$0.70 / $2.50
FastRouterdeepseek-ai/deepseek-r1-distill-llama-70b
$0.03 / $0.14
Together AIdeepseek-ai/DeepSeek-R1
$3.00 / $7.00
Amazon Bedrockdeepseek.r1-v1:0
$1.35 / $5.40
Kilo Gatewaydeepseek/deepseek-r1-0528
$0.50 / $2.15$0.35 cache
Alibaba (China)deepseek-r1-distill-qwen-14b
$0.14 / $0.43
Cloudflare Workers AI@cf/deepseek-ai/deepseek-r1-distill-qwen-32b
$0.50 / $4.88
iFlowdeepseek-r1
$0.00 / $0.00

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

Prompt Caching Active

This model supports prompt caching at $0.35 / 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