# DeepSeek V4 Flash 0423

> DeepSeek V4 Flash 0423 is an open-weight language model from DeepSeek, released on 23 Apr 2026. It accepts text and generates text, with a 1M-token context window and up to 384K output tokens per response.

Source page: https://www.aimodel.directory/models/deepseek-v4-flash-0423
Last verified: 4 Oct 2026

## Specifications

- **Developer:** DeepSeek
- **Release date:** 23 Apr 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/ofox/models/deepseek/deepseek-v4-flash-0423.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/ofox/models/deepseek/deepseek-v4-flash-0423.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/ofox/models/deepseek/deepseek-v4-flash-0423.toml)
- **Context window:** 1M (1,000,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/ofox/models/deepseek/deepseek-v4-flash-0423.toml)
- **Max output:** 384K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/ofox/models/deepseek/deepseek-v4-flash-0423.toml)
- **Knowledge cutoff:** May 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/ofox/models/deepseek/deepseek-v4-flash-0423.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/ofox/models/deepseek/deepseek-v4-flash-0423.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/ofox/models/deepseek/deepseek-v4-flash-0423.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/ofox/models/deepseek/deepseek-v4-flash-0423.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/ofox/models/deepseek/deepseek-v4-flash-0423.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/ofox/models/deepseek/deepseek-v4-flash-0423.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|

## FAQ

### What is the context window of DeepSeek V4 Flash 0423?

DeepSeek V4 Flash 0423 has a context window of 1,000,000 tokens (1M) and can generate up to 384,000 tokens in a single response, according to models.dev.

### Is DeepSeek V4 Flash 0423 open source?

DeepSeek V4 Flash 0423 is an open-weight model. Check the license terms before commercial use.

### When was DeepSeek V4 Flash 0423 released?

DeepSeek released DeepSeek V4 Flash 0423 on 23 Apr 2026, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "DeepSeek V4 Flash 0423", https://www.aimodel.directory/models/deepseek-v4-flash-0423