# DeepSeek V4 Flash

> DeepSeek V4 Flash is an open-weight language model from DeepSeek, released on 24 Apr 2026. It accepts text and generates text, with a 1M-token context window and up to 16K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.09 per million input tokens and $0.18 per million output tokens (DeepInfra), across 7 providers we track.

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

## Specifications

- **Developer:** DeepSeek
- **Release date:** 24 Apr 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/deepseek-ai/DeepSeek-V4-Flash.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/deepseek-ai/DeepSeek-V4-Flash.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash)
- **License:** mit (source: Hugging Face, https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash)
- **Parameters:** 291B (source: Hugging Face, https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash)
- **Context window:** 1M (1,048,576 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/deepseek-ai/DeepSeek-V4-Flash.toml)
- **Max output:** 16K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/deepseek-ai/DeepSeek-V4-Flash.toml)
- **Knowledge cutoff:** May 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/deepseek-ai/DeepSeek-V4-Flash.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/deepseek-ai/DeepSeek-V4-Flash.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/deepseek-ai/DeepSeek-V4-Flash.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/deepseek-ai/DeepSeek-V4-Flash.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/deepseek-ai/DeepSeek-V4-Flash.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/deepseek-ai/DeepSeek-V4-Flash.toml)
- **Hugging Face:** deepseek-ai/DeepSeek-V4-Flash (source: Hugging Face, https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| OpenRouter | $0.02 | $1.28 | $0.02 | 1M |
| DeepInfra | $0.09 | $0.18 | $0.02 | 1M |
| SiliconFlow | $0.13 | $0.28 | $0.03 | 1M |
| Vercel AI Gateway | $0.13 | $0.26 | $0.03 | 1M |
| Novita AI | $0.14 | $0.28 | $0.03 | 1M |
| Hugging Face Inference Providers | $0.14 | $0.28 | – | 1M |
| Azure AI Foundry | $0.19 | $0.51 | – | 1M |

## FAQ

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

DeepSeek V4 Flash has a context window of 1,048,576 tokens (1M) and can generate up to 16,384 tokens in a single response, according to models.dev.

### How much does the DeepSeek V4 Flash API cost?

DeepSeek V4 Flash is listed from $0.09 per million input tokens and $0.18 per million output tokens (DeepInfra). Prices last verified 4 Oct 2026.

### Is DeepSeek V4 Flash open source?

DeepSeek V4 Flash is an open-weight model: its weights are published on Hugging Face as deepseek-ai/DeepSeek-V4-Flash under the mit license. Check the license terms before commercial use.

### When was DeepSeek V4 Flash released?

DeepSeek released DeepSeek V4 Flash on 24 Apr 2026, according to models.dev.

### Which providers offer DeepSeek V4 Flash?

We track DeepSeek V4 Flash on 7 providers: OpenRouter, DeepInfra, SiliconFlow, Vercel AI Gateway, Novita AI, Hugging Face Inference Providers, Azure AI Foundry.

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