DeepSeek V4 Flash is the smaller model in the DeepSeek V4 family, next to the larger DeepSeek V4 Pro. Both have open weights and the same feature set, and Flash is the lower-cost option for work where price and request volume matter. In Jantaris it has a 1,000,000-token context window and up to 384,000 output tokens. It supports streaming, tool calls (tools) and JSON mode. It thinks before answering by default, and thinking tokens are billed as output, so set max_tokens on simple tasks.
Best for
- Coding agents that read a large chunk of the codebase before each change
- Bulk classification, data extraction and summaries of long documents
- Customer support chat on a tight budget
- Tests and prototypes where you run thousands of requests
How to call it
The OpenAI SDK works with the Jantaris base URL:
from openai import OpenAI
client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role": "user", "content": "Refactor this module to remove the global state."}],
)
print(resp.choices[0].message.content)FAQ
How much does DeepSeek V4 Flash cost?
$0.135 / $0.27 per 1M tokens in Jantaris. It has the lowest output rate in the chat catalog, which makes it a good fit for agents and bulk jobs.
Do I need a DeepSeek account to use it?
No. You call it with your Jantaris key and pay from the same balance you use for every other model, in USD with no subscription. Jantaris does not use your prompts or outputs to train models.
DeepSeek V4 Flash or DeepSeek V4 Pro?
Flash costs several times less on both input and output, and both share the same context window and output limit. Start with Flash and keep DeepSeek V4 Pro for tasks where your own data shows a clear quality gain from the larger model.
How to call DeepSeek V4 Flash via API
from openai import OpenAI
client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role": "user", "content": "Write a haiku about Baltic amber."}],
)
print(resp.choices[0].message.content)curl https://jantaris.com/v1/chat/completions \
-H "Authorization: Bearer $JANTARIS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek-v4-flash", "messages": [{"role": "user", "content": "Write a haiku about Baltic amber."}]}'import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://jantaris.com/v1", apiKey: process.env.JANTARIS_API_KEY });
const resp = await client.chat.completions.create({
model: "deepseek-v4-flash",
messages: [{ role: "user", content: "Write a haiku about Baltic amber." }],
});
console.log(resp.choices[0].message.content);