Text

DeepSeek V4 Flash API

Use DeepSeek V4 Flash for text and code through FishToken's OpenAI-compatible chat completions endpoint.

Create your account Quickstart

At a glance

Type: Text and code (chat completions)
Model ID: deepseek-v4-flash
Endpoint: POST https://fishtoken.ai/v1/chat/completions
SDK: OpenAI SDK for Python or Node.js: set base_url and the API key
Billing: Pay as you go from your prepaid balance. Current price: fishtoken.ai/pricing

What it can do

Write and rewrite text: captions, product descriptions, email drafts.
Answer questions in a chat flow, with a system prompt that sets tone and limits.
Write and explain code.
Draft prompts for the video models on this site.

Where it fits in Southeast Asia

Customer service chatbots, with a human agent for anything the bot is unsure about.
Product listing copy for online shops.
Social captions and ad text variations.
Test quality in Bahasa Indonesia, Filipino or Vietnamese before you put output in front of customers.

Example request

Set your key as an environment variable first: export FISHTOKEN_API_KEY=...

Python (OpenAI SDK)

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://fishtoken.ai/v1",
    api_key=os.environ["FISHTOKEN_API_KEY"],
)

resp = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[
        {"role": "user", "content": "Write a two-line caption for a handmade batik tote bag."}
    ],
)
print(resp.choices[0].message.content)

Python: streaming support assistant

from openai import OpenAI
import os

client = OpenAI(base_url="https://fishtoken.ai/v1", api_key=os.environ["FISHTOKEN_API_KEY"])

# A simple support assistant with streaming output
stream = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[
        {"role": "system", "content": "You answer questions for an online shop. Be short and polite. "
                                      "If you are not sure, say a human agent will follow up."},
        {"role": "user", "content": "Can I change my delivery address after ordering?"},
    ],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Node.js and curl versions are in the quickstart.

Before you publish

Content filtering depends on the upstream model service. You are responsible for what you generate and publish: no sexual content, no graphic violence, and no real person's likeness or voice without their consent. Label AI-generated content where the platform you publish on or local law requires it.

Read the full content rules