Loading page…
deepseek-v4-flashDeepSeek · LLM
Modality
text
Reference rate
$0.154–$0.308 / $0.462–$0.924 / 1M tokens
Provider
DeepSeek
Create an EasyAI API key and use deepseek-v4-flash with the supported chat endpoint. Confirm account availability in the console.
deepseek-v4-flash is billed at the rate and billing unit confirmed in your console. This page includes public group offers and estimates for the stated usage scenarios; your account rates can differ.
Yes. One EasyAI key can access the models enabled for your account, including text, image, and video models where available.
Approx. $0.2002–$0.4004
Input / output range across peak and off-peak hours (UTC+8).
Estimated with public group offers, excluding cache savings or additional usage. Your account rates and console records determine actual charges.
from openai import OpenAI
client = OpenAI(
base_url="https://easyairoute.com/v1",
api_key="sk-...",
)
resp = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://easyairoute.com/v1",
apiKey: "sk-...",
});
const resp = await client.chat.completions.create({
model: "deepseek-v4-flash",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);Enterprise volume purchases can qualify for better pricing. Request a quote for your models and scale.