# DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 costs $0.126 per 1M input tokens and $0.252 per 1M output tokens on LLM API, with a 1M-token context window.

Model ID: `deepseek-v4-flash-0731` · DeepSeek · Text generation · Released July 31, 2026
Updated: 2026-11-09
Canonical: https://llmapi.ai/models/deepseek-v4-flash-0731/

- Input: $0.126 (list $0.14) per 1M tokens
- Output: $0.252 (list $0.28) per 1M tokens
- Cache read: $0.0154 (list $0.022) per 1M tokens
- Context: 1M tokens
- Max output: 384K tokens

## Pricing

Lowest price among 3 providers, after discounts.

| Price | Amount | Per |
| --- | --- | --- |
| Input | $0.126 (list $0.14) | per 1M tokens |
| Output | $0.252 (list $0.28) | per 1M tokens |
| Cache read | $0.0154 (list $0.022) | per 1M tokens |

**Volume pricing.** At higher monthly volume, DeepSeek V4 Flash 0731 may cost less. Book a call and sales will quote a price for your usage. [Book a call with sales](https://meetings.hubspot.com/julia-andriienko/llmapi) or [Create an account first](https://app.llmapi.ai/signup).

## Providers

Prices after each provider’s discount; the lowest in bold.

| Provider | Input / 1M | Output / 1M | Cache read / 1M | Context | Max output |
| --- | --- | --- | --- | --- | --- |
| [Alibaba Cloud](https://llmapi.ai/providers/alibaba-cloud/) (−30%) | $0.154 | $0.462 | **$0.0154** | 1M | 384K |
| [Novita AI](https://llmapi.ai/providers/novita/) | $0.44 | $1.32 | $0.028 | 1M | 384K |
| [CanopyWave](https://llmapi.ai/providers/canopywave/) (−10%) | **$0.126** | **$0.252** | $0.0252 | 1M | 384K |

## Features

- Tools: Yes
- Parallel tool calls: No
- Image input: No
- Reasoning: Yes (Levels: high, max · default max)
- Prompt caching: Yes
- Structured outputs: Yes
- JSON mode: Yes
- Streaming: Yes
- Web search: Yes

## Call DeepSeek V4 Flash 0731

### Chat Completions (`POST /v1/chat/completions`)

Set LLMAPI_KEY to your LLM API key.

```python
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

response = client.chat.completions.create(
    model="deepseek-v4-flash-0731",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
```

Docs: [Chat Completions docs](https://docs.llmapi.ai/api/v1/chat/completions)

## More from DeepSeek

- [DeepSeek V4.1 Flash 1017](https://llmapi.ai/models/deepseek-v4-1-flash-1017/): $0.15 / $0.6 per 1M input / output
- [DeepSeek V4 Pro](https://llmapi.ai/models/deepseek-deepseek-v4-pro/): $0.66 / $1.98 per 1M input / output
- [DeepSeek V4.1 Flash](https://llmapi.ai/models/deepseek-deepseek-v4-1-flash/): $0.15 / $0.6 per 1M input / output

Prices synced 2026-11-09.

Next step: [Get API key](https://app.llmapi.ai/signup)