DeepSeek V4 Flash

DeepSeekMCP Tool CallReasoning

deepseek/deepseek-v4-flashOpen Weights

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

Benchmark Pricing$0.15 / 1M in$0.60 / 1M out$0.00 cache read

Context: 1,000,000 tokens•Max Output: 384,000 tokens•Knowledge: 2025-05•Released: 2026-04-24

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 V4 Flash 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

SWE-Bench Verifiedresolved

MMLU-ProEM

86.2

SimpleQA-Verifiedpass@1

34.1

Chinese SimpleQApass@1

78.9

GPQA Diamondpass@1

88.1

Humanity's Last Exampass@1

34.8

LiveCodeBenchpass@1

91.6

Codeforcesrating

3052

HMMTpass@1

94.8

IMOAnswerBenchpass@1

88.4

MathArena Apexpass@1

MathArena Apex Shortlistpass@1

85.7

MRCRMMR

78.7

CorpusQAaccuracy

60.5

Terminal-Benchaccuracy

56.9

SWE-Bench Proresolved

52.6

SWE-Bench Multilingualresolved

73.3

BrowseComppass@1

73.2

Humanity's Last Exampass@1

45.1

MCP Atlaspass@1

GDPval-AAElo

1395

Toolathlonpass@1

47.8

API CALL INVOCATION EXAMPLE

// Example: Calling DeepSeek V4 Flash 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-v4-flash",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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