Generic SDKs (Python / Node.js)
To call 6090ti from your own code, use the official OpenAI or Anthropic SDK and change only the endpoint and key. The same key works with both SDKs; pick by the model you call:
| Model | SDK | Base URL |
|---|---|---|
| Claude models | Anthropic SDK | https://api.6090ti.com |
| GPT and other models | OpenAI SDK | https://api.6090ti.com/v1 |
Before you start
- You have an account, a topped-up balance and an API key created in the console.
- Request
/v1/modelswith this key and choose a model from the returned list. The pricing page shows display prices only. The model is shown below as<model>. - Keep the key in the environment variable
P6090TI_API_KEY, not in your code.
# macOS / Linux
export P6090TI_API_KEY="<your key>"
# Windows (reopen the terminal afterwards)
setx P6090TI_API_KEY "<your key>"
Python
Install:
pip install openai anthropic
OpenAI SDK (GPT and other models)
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.6090ti.com/v1",
api_key=os.environ["P6090TI_API_KEY"],
)
resp = client.chat.completions.create(
model="<model>",
messages=[{"role": "user", "content": "Introduce yourself in one sentence"}],
)
print(resp.choices[0].message.content)
Streaming (show output as it is generated):
stream = client.chat.completions.create(
model="<model>",
messages=[{"role": "user", "content": "Write a four-line poem"}],
stream=True,
)
for chunk in stream:
if chunk.choices and chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)
The OpenAI SDK can also use the Responses API:
resp = client.responses.create(model="<model>", input="Reply with OK only")
print(resp.output_text)
Anthropic SDK (Claude models)
import os
import anthropic
client = anthropic.Anthropic(
base_url="https://api.6090ti.com",
api_key=os.environ["P6090TI_API_KEY"],
)
msg = client.messages.create(
model="<model>",
max_tokens=512,
messages=[{"role": "user", "content": "Introduce yourself in one sentence"}],
)
print(msg.content[0].text)
Streaming:
with client.messages.stream(
model="<model>",
max_tokens=512,
messages=[{"role": "user", "content": "Write a four-line poem"}],
) as stream:
for text in stream.text_stream:
print(text, end="", flush=True)
Node.js
Install:
npm install openai @anthropic-ai/sdk
OpenAI SDK (GPT and other models)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.6090ti.com/v1",
apiKey: process.env.P6090TI_API_KEY,
});
const resp = await client.chat.completions.create({
model: "<model>",
messages: [{ role: "user", content: "Introduce yourself in one sentence" }],
});
console.log(resp.choices[0].message.content);
Anthropic SDK (Claude models)
import Anthropic from "@anthropic-ai/sdk";
const client = new Anthropic({
baseURL: "https://api.6090ti.com",
apiKey: process.env.P6090TI_API_KEY,
});
const msg = await client.messages.create({
model: "<model>",
max_tokens: 512,
messages: [{ role: "user", content: "Introduce yourself in one sentence" }],
});
console.log(msg.content[0].text);
These Node.js examples use ES modules. Save the file as .mjs, or set "type": "module" in package.json.
List available models
Request the model list with your key. It returns the models enabled for that key:
curl https://api.6090ti.com/v1/models \
-H "Authorization: Bearer <your key>"
Common errors
- 401: the key is wrong, or the environment variable was not read.
- 403 insufficient balance: top up and retry.
- 404 model not available: the model name is wrong, or the model is not enabled for your key.
- SDK does not match the model: use the Anthropic SDK and
https://api.6090ti.comfor Claude models, and the OpenAI SDK andhttps://api.6090ti.com/v1for other models. - 429: too many requests or a busy upstream. Retry later; add backoff retries in your code.
See the API reference for full parameters and errors.