D
DeepSeek V4 Flash 0423OPEN
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.
Prices update automatically — checked daily against provider list prices.
- $0.18 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 66% of the 182 open-weight models tracked here
- 2 of 12 DeepSeek models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for DeepSeek V4 Flash 0423, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning, Max Effort.
For the same budget, DeepSeek V4 Flash 0423 delivers 47 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $1.69 per 1M tokens (median of 12) — this one costs $0.18.
No model tracked here is both cheaper and better on this index.
About this model
DeepSeek V4 Flash 0423 is an open-weight AI model by DeepSeek. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is DeepSeek V4 Flash 0423?
DeepSeek V4 Flash 0423 is an AI language model from DeepSeek. It is open-weight: you can download it and run it on your own hardware, for free. It scores 51.8 on the Artificial Analysis intelligence index.
Is DeepSeek V4 Flash 0423 free?
The weights are free and open — you can self-host DeepSeek V4 Flash 0423 and pay nothing per token. If you prefer a hosted API, list prices are $0.14 per million input tokens and $0.28 per million output tokens.
What is DeepSeek V4 Flash 0423 good at?
Independent benchmarks from Artificial Analysis give it GPQA 90.8%, Humanity's Last Exam 38.6%, Long Context Reasoning 74.3%, SciCode 49.9%, τ-Bench Banking 39.4%, Terminal-Bench 78.7%. It is particularly used for code generation.
How fast is DeepSeek V4 Flash 0423?
It generates about 112.1 tokens per second, with a median 0.97s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host DeepSeek V4 Flash 0423?
Yes. DeepSeek V4 Flash 0423 has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.