DeepSeek

DeepSeek V4 Pro 0423

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

Prices updated . Benchmarks updated .

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

You send / 1M

$0.900

tokens in

It replies / 1M

$1.50

tokens out

Context

1M

tokens it can read at once

Typical request

$0.0019

1,000 words in, 400 out

Benchmarks

BenchmarkScoreKindDateSource
Epoch Capabilities Index149.1Independent2026-04-24Epoch AI
GPQA DiamondHigh effort90.9%Independent2026-08-06Epoch AI
OTIS Mock AIMEMax effort96.7%Independent2026-06-17Epoch AI
SimpleQA VerifiedMax effort47.0%Independent2026-08-27Epoch AI
SWE-bench VerifiedMax effort77.6%Independent2026-06-18Epoch AI
CritPtMax effort12.9%Independent2026-04-24CritPt, republished by Epoch AI
Arena Elo (text)1,451Independent2026-10-28LMArena
Arena Elo (webdev)1,447Independent2026-10-28LMArena

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
Relace · fp4$0.900$1.50100%Read
SiliconFlow · fp8$1.00$1.50100%Read
DeepInfra · fp8$1.04$2.08100%Read
DigitalOcean$1.04$2.09100%Read
DeepInfra · fp8$1.30$2.60100%Read
Novita · fp8$1.60$3.20100%Read
Venice$1.65$3.3099%Read
Azure$1.91$3.83100%Read
DeepInfra · fp8$1.95$3.9099%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: 393K tokens
  • Repeated text is billed at $0.250 per 1M (prompt caching)

Compare with

Appears in

Estimate your monthly cost with DeepSeek V4 Pro 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.