DeepSeek V4 Flash

ChatInput: TextReleased Apr 24, 2026

Built by DeepSeek · China · deepseek.com

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...

How to use

model: "deepseek/deepseek-v4-flash"

Cap quality here and save

Hard questions go to this model, easy ones drop to something cheaper. Set a savings target (0–0.8) and the router tunes itself until realized savings converge on it.

{
  "model": "celon/auto",
  "celon": {
    "anchor": "deepseek/deepseek-v4-flash",
    "savings_target": 0.4
  }
}

Naming a model directly gets you that model — savings controls don't apply.

Context

Max output

—

Input $/1M

$0.09

Output $/1M

$0.18

Features

Tool callingJSON

Serving providers

DeepInfraNovitaW&B Inference

Providers

Price, latency, and uptime per provider serving this model. Celon routes each request to the fastest and cheapest of them. Click a row for regions and data policies.

Loading provider metrics…

Performance

Benchmark quality scores, and measured speed per provider.

Quality

SciCodeScientific code generation

44.9%

At each model's best reasoning effort. Benchmarks it wasn't run on are omitted.

Speed

Loading provider metrics…