DeepSeek: DeepSeek V4 Flash 0731
The DeepSeek V4 Flash 0731 is an AI model designed for handling text input and supporting reasoning capabilities. It operates within a context length of 1310720 tokens and has a maximum completion token limit of 943718. The model also supports the use of tools, but its structured output capabilities are undefined. This model may be worth considering by those who prioritize reasoning over other features, given its support for this capability. Its pricing structure is based on input ($0.05/M tokens) and output ($0.1/M tokens), which may appeal to users with specific needs and budget constraints. However, it's essential to note that there are currently no independent benchmarks or coverage available to verify the model's performance.
- Model ID
- deepseek/deepseek-v4-flash-0731
- Vendor
- deepseek
- Released
- July 2026
- Tokenizer
- DeepSeek
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 943,718 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.04/M input and $0.64/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.05 |
| A month of a busy support chatbot | 5M in / 2M out | $1.48 |
Price & spec history
Tracked daily by PicksByModel since 2026-08-01.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-09-22 | $0.04 | $0.64 | 1,310,720 |
| 2026-09-21 | $0.04 | $0.16 | 1,310,720 |
| 2026-09-20 | $0.04 | $0.08 | 1,310,720 |
| 2026-09-19 | $0.07 | $0.18 | 1,310,720 |
| 2026-09-14 | $0.06 | $0.12 | 1,310,720 |
| 2026-09-13 | $0.04 | $0.08 | 1,310,720 |
| 2026-09-09 | $0.07 | $0.18 | 1,310,720 |
| 2026-09-07 | $0.14 | $0.28 | 1,310,720 |
| 2026-09-01 | $0.07 | $0.18 | 1,310,720 |
| 2026-08-29 | $0.04 | $0.09 | 1,310,720 |
| 2026-08-26 | $0.06 | $0.12 | 1,310,720 |
| 2026-08-24 | $0.14 | $0.28 | 1,310,720 |
| 2026-08-22 | $0.08 | $0.18 | 1,310,720 |
| 2026-08-18 | $0.14 | $0.28 | 1,310,720 |
| 2026-08-14 | $0.14 | $0.28 | 1,048,576 |
| 2026-08-11 | $0.08 | $0.18 | 1,048,576 |
| 2026-08-02 | $0.09 | $0.18 | 1,048,576 |
| 2026-08-01 | $0.14 | $0.28 | 1,048,576 |
Similar models
DeepSeek: DeepSeek V4 Flash 0423
DeepSeek: DeepSeek V4.1 Flash
DeepSeek: DeepSeek V4.1 Flash (batch)
DeepSeek: DeepSeek V4 Flash Vision Exp
DeepSeek: DeepSeek V4 Pro 0813
DeepSeek: DeepSeek V4 Pro 0423
Quick answers
- How much does DeepSeek: DeepSeek V4 Flash 0731 cost?
- $0.04 per million input tokens and $0.64 per million output tokens.
- What is DeepSeek: DeepSeek V4 Flash 0731's context window?
- 1,310,720 tokens, roughly 1,966 pages of text in a single request.
- Does DeepSeek: DeepSeek V4 Flash 0731 support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can DeepSeek: DeepSeek V4 Flash 0731 process images?
- No, it is text-only on the input side.