deepseek-v4-flash:cloud

445.5K Downloads Updated 1 month ago

DeepSeek-V4-Flash is the official release of DeepSeek-V4-Flash, built for efficient reasoning across a 1M-token context window, outperforming DeepSeek-V4-Pro (Preview).

tools thinking cloud

Cost /1M tokens

$0.22

input

$0.007

cached

$0.66

output

Context

1M tokens

Size

304B parameters

ollama run deepseek-v4-flash:cloud

curl http://localhost:11434/api/chat \
  -d '{
    "model": "deepseek-v4-flash:cloud",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='deepseek-v4-flash:cloud',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'deepseek-v4-flash:cloud',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Readme

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

DeepSeek-V4-Flash is the official release of DeepSeek-V4-Flash, built for efficient reasoning across a 1M-token context window, outperforming DeepSeek-V4-Pro (Preview).

3 Thinking modes:

No thinking: used for fast, intuitive answers
Thinking: used for careful logical analysis
Max thinking: maximum reasoning effort on the hardest problems

Benchmark	DeepSeek-V4-Flash-0731	DeepSeek-V4-Flash (Preview)	DeepSeek-V4-Pro (Preview)	GLM-5.2	Opus-4.8
Terminal Bench 2.1	82.7	61.8	72.1	81.0	85.0
NL2Repo	54.2	39.4	38.5	48.9	69.7
Cybergym	76.7	38.7	52.7	-	83.1
DeepSWE	54.4	7.3	12.8	46.2	58.0
Toolathlon-Verified	70.3	49.7	55.9	59.9	76.2
Agents’ Last Exam	25.2	15.8	16.5	23.8	25.7
AutomationBench Public	25.1	10.8	12.8	12.9	27.2
DSBench-FullStack †	68.7	37.0	41.8	61.8	71.6
DSBench-Hard †	59.6	25.8	31.1	54.5	71.7

Reference

DeepSeek-V4 technical report

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

**DeepSeek-V4-Flash** is the official release of DeepSeek-V4-Flash, built for efficient reasoning across a 1M-token context window, outperforming DeepSeek-V4-Pro (Preview).

3 Thinking modes:

- No thinking: used for fast, intuitive answers 
- Thinking: used for careful logical analysis 
- Max thinking: maximum reasoning effort on the hardest problems

| Benchmark | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Flash (Preview) | DeepSeek-V4-Pro (Preview) | GLM-5.2 | Opus-4.8 |
| :--- | :---: | :---: | :---: | :---: | :---: |
| Terminal Bench 2.1 | 82.7 | 61.8 | 72.1 | 81.0 | 85.0 |
| NL2Repo | 54.2 | 39.4 | 38.5 | 48.9 | 69.7 |
| Cybergym | 76.7 | 38.7 | 52.7 | - | 83.1 |
| DeepSWE | 54.4 | 7.3 | 12.8 | 46.2 | 58.0 |
| Toolathlon-Verified | 70.3 | 49.7 | 55.9 | 59.9 | 76.2 |
| Agents' Last Exam | 25.2 | 15.8 | 16.5 | 23.8 | 25.7 |
| AutomationBench Public | 25.1 | 10.8 | 12.8 | 12.9 | 27.2 |
| DSBench-FullStack † | 68.7 | 37.0 | 41.8 | 61.8 | 71.6 |
| DSBench-Hard † | 59.6 | 25.8 | 31.1 | 54.5 | 71.7 |

### Reference

[DeepSeek-V4 technical report](https://arxiv.org/abs/2606.19348)

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)