DeepSeek Reasoner

DeepSeekMCP Tool CallReasoning
deepseek/deepseek-reasonerOpen Weights

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

Benchmark Pricing$0.56 / 1M in$1.68 / 1M out$0.07 cache read
Context: 1,000,000 tokens•Max Output: 384,000 tokens•Knowledge: 2025-09•Released: 2025-12-01

TECHNICAL SPECIFICATIONS

Context Window1,000,0001M tokens
Max Output384,000384K tokens
LicenseOpen SourceSelf-hostable
Input Modalities
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ DeepSeek Reasoner 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 1,000,000 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.

STANDARDIZED BENCHMARKS & EVALS

Aider Polyglotpercent correct
74.2

API CALL INVOCATION EXAMPLE

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

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

PRICING BY PROVIDER

2 providers
Heliconedeepseek-reasoner
$0.56 / $1.68$0.07 cache
OrcaRouterdeepseek/deepseek-reasoner
$0.24 / $0.73$0.01 cache

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

Prompt Caching Active

This model supports prompt caching at $0.07 / 1M tokens, saving up to 88% on repetitive MCP tool definitions and system instructions.