Quickstart

Sign up

Create a free account at nexotao.com. Just an email and a password.

Top up your balance

Top up your Rupiah balance from Rp 10,000 via QRIS or crypto (USDT / USDC). The balance never expires and is billed per token as you use it — no subscription. Top up Rp 150,000+ for a +6% balance bonus, Rp 500,000+ for +15%.

Create an API key

In the dashboard, open API Keys and create a new key. It looks like sk-nexo-....

First request

Easiest path: the OpenAI endpoint (/v1/chat/completions) — it works for every model, including Claude. Not sure which to pick? See Endpoints & Formats.

from openai import OpenAI
 
client = OpenAI(base_url="https://api.nexotao.com/v1", api_key="sk-nexo-...")
 
resp = client.chat.completions.create(
    model="claude-opus-4-8",  # or gpt-5.6-terra, DeepSeek-V4-Pro, etc.
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

curl https://api.nexotao.com/v1/messages \
  -H "x-api-key: sk-nexo-..." \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "max_tokens": 256,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import OpenAI from "openai"
 
const client = new OpenAI({ baseURL: "https://api.nexotao.com/v1", apiKey: "sk-nexo-..." })
 
const resp = await client.chat.completions.create({
  model: "gpt-5.6-terra",
  messages: [{ role: "user", content: "Hello" }],
})
console.log(resp.choices[0].message.content)

Every response includes an X-Cost-Rp header (the actual cost in Rupiah) and X-Request-Id. See Billing & Pricing for details.

Switch models by changing one string

Same call, cheaper or stronger — just change the model:

• DeepSeek-V4-Flash — ultra-cheap workhorse for high-volume work: classification, extraction, short chat. Not for agentic/coding or large context (~20k TPM capacity — heavy requests can hit 429 server at capacity).
• claude-opus-4-8 — frontier reasoning for coding/agentic & large context.
• claude-opus-5 — the newest Opus, a 1M-token context, with the same rate for input and output (see Models & Pricing). Capacity is still limited, so heavy agentic workloads are safer on Opus 4.8.
• gpt-5.6-luna, gpt-5.6-terra, gpt-5.6-sol — the GPT-5.6 family from efficient to balanced to the top tier, with Sol at Rp 7,000 input/output.

Browse every model and today’s price at nexotao.com/harga.