DeepSeek

DeepSeek V4 Flash 0423

Launched 2026-04-24 · Knowledge up to 2025-05 · Listed on OpenRouter 2026-04-24

Prices updated . Benchmarks updated .

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. It is designed for fast inference and...

You send / 1M

$0.090

tokens in

It replies / 1M

$0.180

tokens out

Context

1M

tokens it can read at once

Typical request

$0.0002

1,000 words in, 400 out

Benchmarks

BenchmarkScoreKindDateSource
Epoch Capabilities Index146.2Independent2026-04-24Epoch AI
CritPtMax effort7.1%Independent2026-04-24CritPt, republished by Epoch AI
Arena Elo (text)1,432Independent2026-10-28LMArena
Arena Elo (webdev)High effort1,582Independent2026-10-28LMArena

Rankings on this site use the Epoch Capabilities Index, an independent composite. Lab-reported rows are the lab's own figures and are kept separate.

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

ProviderYou send / 1MIt replies / 1MUptimePrivacy policy
DeepInfra · fp8$0.072$0.14498%Read
Wafer · mxfp4$0.120$0.170100%Read
DeepInfra · fp8$0.090$0.180100%Read
Venice$0.097$0.193100%Read
Fireworks$0.105$0.21096%Read
DeepInfra · fp8$0.135$0.270100%Read
Parasail · fp8$0.140$0.280100%Read
SiliconFlow · fp8$0.130$0.28099%Read
Relace · fp4$0.050$0.450100%Read
Mancer 2 · fp8$0.150$0.50099%Read
Azure$0.210$0.560100%Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: text
  • Writes: text
  • Weights: Open weights
  • Reasoning: Yes
  • Tool calling: Yes
  • Longest reply: 384K tokens
  • Repeated text is billed at $0.018 per 1M (prompt caching)

Compare with

Appears in

Estimate your monthly cost with DeepSeek V4 Flash 0423

Sources and licenses

  • OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
  • Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
  • models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
  • Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
  • LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
  • Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
  • What a score measures: the benchmark guide.