Docs

Getting started

Create your key on the Keys page. Only published model names are accepted. Any other name returns 400.

Setup

# If Claude Code is not installed
npm install -g @anthropic-ai/claude-code

export ANTHROPIC_BASE_URL="https://api.wiozen.com"
export ANTHROPIC_AUTH_TOKEN="sk-gw-..."
export ANTHROPIC_MODEL="wiozen-anthropic"
claude

// OpenAI API Key
sk-gw-...

// Override OpenAI Base URL
https://api.wiozen.com/v1

// Add to the model list and select it
wiozen-anthropic

from openai import OpenAI

client = OpenAI(base_url="https://api.wiozen.com/v1", api_key="sk-gw-...")

response = client.chat.completions.create(
    model="wiozen-anthropic",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=16000,
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.wiozen.com/v1", apiKey: "sk-gw-..." });

const res = await client.chat.completions.create({
  model: "wiozen-anthropic",
  messages: [{ role: "user", content: "Hello!" }],
  max_tokens: 16000,
});
console.log(res.choices[0].message.content);

curl https://api.wiozen.com/v1/messages \
  -H "x-api-key: $API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "wiozen-anthropic",
    "max_tokens": 4096,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

curl https://api.wiozen.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "wiozen-anthropic",
    "max_tokens": 4096,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Key Tool

Connects Claude Desktop and Claude Code without writing environment variables: open the tool, enter your sk-gw-… key, and click Apply.

Endpoints

Image generation

/v1/images/generations generates images from text. If you pass a reference image in the image field, generation starts from that image: editing, changing the background, or showing the same product in a different scene. The image comes back as base64 in data[0].b64_json in the response.

curl https://api.wiozen.com/v1/images/generations \
  -H "Authorization: Bearer $API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "prompt": "A red apple on a white table, studio photo"
  }'

import base64, requests

ref = base64.b64encode(open("urun.png", "rb").read()).decode()

r = requests.post(
    "https://api.wiozen.com/v1/images/generations",
    headers={"Authorization": "Bearer sk-gw-..."},
    json={
        "model": "gemini-3.1-flash-image",
        "prompt": "Keep the same product, make the background light blue",
        "image": "data:image/png;base64," + ref,
    },
)
open("sonuc.jpg", "wb").write(base64.b64decode(r.json()["data"][0]["b64_json"]))

The reference image must be a data URI or plain base64; URLs are not accepted. One reference image is used per request.

Response format

{
  "id": "msg_01XyZ987654321",
  "type": "message",
  "role": "assistant",
  "content": [{ "type": "text", "text": "Hello!" }],
  "model": "wiozen-anthropic",
  "stop_reason": "end_turn",
  "usage": { "input_tokens": 14, "output_tokens": 11 }
}

event: message_start
data: {"type":"message_start","message":{"id":"msg_01X...","role":"assistant"}}

event: content_block_delta
data: {"type":"content_block_delta","delta":{"type":"text_delta","text":"Hello"}}

event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"output_tokens":11}}

data: [DONE]

Parameters

Billing

• Dollar balance. The amount you add becomes your balance and does not expire; each request deducts the price of the tokens it uses. Current prices are on the Models page.
• Four separate prices. Input, cached input read, cached input write, and output are priced separately. A cache read costs one tenth of the input price; in long-context agent use, this makes up most of the cost.
• Reservation. When a request starts, its estimated cost is held from your balance, then adjusted to the actual cost when the response ends. Setting max_tokens higher than you need increases this held amount.
• Failed requests are not charged. /v1/messages/count_tokens is free too.
• Key limit. You can set a spend cap on a key; when it is reached, only that key stops.
• You can see the request breakdown on the Usage page.

Errors