Connect this model to your app through OMA’s OpenAI-compatible API.
Compare this model’s providers. Each provider has its own API ID, pricing, limits and availability.
Pay for the tokens you use. Chat and API usage draw from your account credits.
Provider route prices, context, output limits, input modalities and privacy verified against the Venice model catalog. OMA applies its listed markup. Provider catalog checked 2026-10-25.
deepseek-v4-flash-0731Use this ID in the model field of your chat completion request.
Set OMA_API_KEY to your API key. API requests use your account credits.
curl https://www.oma-ai.com/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OMA_API_KEY" \
-d '{
"model": "deepseek-v4-flash-0731",
"messages": [{ "role": "user", "content": "Hello!" }],
"max_tokens": 150
}'import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["OMA_API_KEY"],
base_url="https://www.oma-ai.com/api/v1",
)
response = client.chat.completions.create(
model="deepseek-v4-flash-0731",
messages=[{"role": "user", "content": "Hello!"}],
max_tokens=150,
)
print(response.choices[0].message.content)import { OpenAI } from "openai";
const client = new OpenAI({
apiKey: process.env.OMA_API_KEY,
baseURL: API_V1_BASE,
});
const response = await client.chat.completions.create({
model: "deepseek-v4-flash-0731",
messages: [{ role: "user", content: "Hello!" }],
max_tokens: 150,
});
console.log(response.choices[0].message.content);