DeepSeek V4 Flash 0423

by DeepSeek

Zero data retention−41%
deepseek/deepseek-v4-flash
Input
$0.13/1M tokens
Output
$0.25/1M tokens
Context
1Mtokens
Max output
944Ktokens
Knows to
-
Released
24 Apr 2026

About

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.

Pricing

Input$0.13 from $0.07per 1M prompt tokens
Output$0.25 from $0.23per 1M generated tokens, reasoning included
Cached input$0.03per 1M tokens read back from the prompt cache

41% off right now. The provider is running a promotion, and the developer API bills what the provider actually charged for your call plus our flat markup, so it reaches your bill with nothing to claim. The “from” figure is the cheapest endpoint serving the model; which one answers is the provider’s routing decision, so treat it as a floor. Promotions can end at any time.

What a request costs

Typical requestEachPer 1,000
Short chat reply1,500 in · 400 out$0.0003$0.293
Question over a long document40,000 in · 800 out$0.0053$5.30
Agent tool step20,000 in · 1,200 out$0.0029$2.85

At the developer-API rate, before any provider promotion or prompt-cache saving. In the app, the model picker shows what a message costs on your plan before you send it.

Benchmarks

Coding56.2#70 of 162
Agentic22.2#64 of 132

Head-to-head rankings

  1. #47SVGModel arenaElo 115248% wins
  2. #573DModel arenaElo 118649% wins
  3. #58Game devModel arenaElo 119750% wins
  4. #61ASCII artModel arenaElo 110743% wins
  5. #62CodeModel arenaElo 120449% wins
  6. #63WebsitesModel arenaElo 120649% wins
  7. #77UI componentsModel arenaElo 115945% wins
  8. #93Data vizModel arenaElo 112741% wins

Scores from Artificial Analysis; bars are scaled to the best model on our list. Rankings from Design Arena head-to-head votes. Published by OpenRouter alongside its catalogue.

Call it from code

OpenAI-compatible: point any OpenAI SDK at https://api.privateer.pro/v1 and set model. Keys are created in the app under Settings.

cURL
curl https://api.privateer.pro/v1/chat/completions \
  -H "Authorization: Bearer $PRIVATEER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash",
    "messages": [{ "role": "user", "content": "Hello" }],
    "reasoning": { "effort": "xhigh" }
  }'
Python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.privateer.pro/v1",
    api_key=os.environ["PRIVATEER_API_KEY"],
)
reply = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)
JavaScript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.privateer.pro/v1",
  apiKey: process.env.PRIVATEER_API_KEY,
});
const reply = await client.chat.completions.create({
  model: "deepseek/deepseek-v4-flash",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);

Parameters this model accepts

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p

API reference → · How API billing works →

Prices are USD at the developer-API rate, as of 5 Nov 2026, rebuilt daily from the providers’ live catalogues. ← All models