Back to Models
DeepSeek V4 Flash 0731
Available
Compare all DeepSeek models — V4 Pro vs Flash vs V3.2 vs V3.1 vs V3-0324
Description
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.
At a Glance
Key pricing and model details available for this model.
Input price
$0.14
per 1M tokens
Output price
$0.28
per 1M tokens
Context window
1.0M
tokens
Hallucination rate
0%
Token Pricing
Token pricing normalized to per-million-token rates.
Input / 1M tokens
$0.14
Output / 1M tokens
$0.28
Cache Read / 1M tokens
$0.05
Token Pricing Details
Rates are shown per 1M tokens for easier comparison.
| Input / 1M tokens | $0.14 |
| Input unit | 1M tokens |
| Output / 1M tokens | $0.28 |
| Output unit | 1M tokens |
| Cache Read / 1M tokens | $0.05 |
| Cache Read unit | 1M tokens |
Feature Availability
Capabilities explicitly listed in the current payload.
LLM
Available
Yes
Vision
Not listed
No
Function calling
Available
Yes
Reasoning
Available
Yes
Service tiers
Not listed
No
Reasoning Effort Levels
none
low
high
max
Supported Parameters
frequency_penalty
logit_bias
max_completion_tokens
presence_penalty
reasoning_effort
stop
temperature
top_p
tools
tool_choice
Code Samples
Quick start with the Routeway API
import OpenAI from 'openai';
const openai = new OpenAI({
baseURL: "https://api.routeway.ai/v1",
apiKey: "<YOUR_API_KEY>",
});
async function main() {
const completion = await openai.chat.completions.create({
model: "deepseek-v4-flash-0731",
messages: [
{
role: "user",
content: "Explain quantum computing in simple terms"
}
]
});
console.log(completion.choices[0].message);
}
main();