← all models

DeepSeek V4 Flash 0423

deepseek

openrouter
Parameters 284B openrouter api · from the description
Context 1M 1048576 tokens
Input $0.09 OpenRouter
Output $0.18 OpenRouter
Cache read $0.02 OpenRouter

Accepts

text

Capabilities

frequency_penalty include_reasoning logit_bias logprobs max_completion_tokens max_tokens min_p presence_penalty reasoning reasoning_effort repetition_penalty response_format seed stop structured_outputs temperature tool_choice tools top_a top_k top_logprobs top_p

Description

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...

The OpenRouter API truncates descriptions — read the full text at the source

Also known as

Every id and name this model has been seen under — for matching it against another catalogue.

openrouter deepseek/deepseek-v4-flash huggingface deepseek-ai/DeepSeek-V4-Flash version slug deepseek/deepseek-v4-flash-20260423 name DeepSeek: DeepSeek V4 Flash 0423 display name DeepSeek V4 Flash 0423

Identifiers

Vendor
deepseek
OpenRouter
deepseek/deepseek-v4-flash
Hugging Face
deepseek-ai/DeepSeek-V4-Flash
Version slug
deepseek/deepseek-v4-flash-20260423
Released
2026-04-24T03:17:46.000Z
First seen
59 d ago
Last crawled
16 min ago