Integration guideOpenAI-compatible

Use a model with OpenAI SDK through IteraCompute.

Build with Python and JavaScript.

Get API Key All Integrations

Connect in three steps

1. Create an API key

Create or sign in to your IteraCompute account, then create a key in the Console.

2. Configure the base URL

Set base_url in Python or baseURL in JavaScript, then use Chat Completions.

3. Select the model

Use the exact API Model ID for your chosen model. Check its context and capabilities before enabling agent or vision features.

Choose your model

Model used in the examples

Example configuration

Keep API keys in your server environment or tool credential store. Replace the example key field with your own key where applicable.

OpenAI-compatible API

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.iteracompute.com/v1",
    api_key=os.environ["ITERACOMPUTE_API_KEY"],
)
response = client.chat.completions.create(
    model="qwen/qwen3.8-27b",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=512,
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
text = response.choices[0].message.content
if not text or not text.strip():
    raise RuntimeError("Empty model reply: activation is incomplete.")
print(text)

import OpenAI from "openai";

if (!process.env.ITERACOMPUTE_API_KEY) {
  throw new Error("Set ITERACOMPUTE_API_KEY on the server.");
}

const client = new OpenAI({
  baseURL: "https://api.iteracompute.com/v1",
  apiKey: process.env.ITERACOMPUTE_API_KEY,
});
const response = await client.chat.completions.create({
  model: "qwen/qwen3.8-27b",
  messages: [{ role: "user", content: "Hello!" }],
  max_tokens: 512,
  chat_template_kwargs: { enable_thinking: false },
});
const text = response.choices[0].message.content;
if (!text || !text.trim()) throw new Error("Empty model reply: activation is incomplete.");
console.log(text);

Version and verification

Python SDK 2.14.0 · Python 3.11.4 · October 15, 2026: request serialization and non-empty/empty reply handling checked with a local mock transport. This does not establish a real API call. JavaScript SDK version and end-to-end results are not yet recorded.

Success criterion

Run both SDK snippets. Each must print non-empty content; a missing key or an empty reply must stop the program.

Record the installed version

python -m pip show openai
npm ls openai

Test the configured tool itself after the API check below. An HTTP 200 or a cURL result alone does not verify that tool.

Test the connection

cURL · Chat Completions

# Bash / zsh / WSL; set ITERACOMPUTE_API_KEY in your environment first.
curl --fail-with-body https://api.iteracompute.com/v1/chat/completions \
  -H "Authorization: Bearer $ITERACOMPUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.8-27b","messages":[{"role":"user","content":"Reply with exactly: Hello!"}],"max_tokens":512}'

Check that choices[0].message.content contains visible text; HTTP 200 alone is insufficient. Reasoning may consume the output budget. For free Qwen, use the first free call example to disable thinking, then send a prompt inside your tool.

Selected model capabilities

These are API capabilities of the selected model. Feature availability in your workflow also depends on the tool and its settings; reasoning controls vary by model.

Chat CompletionsSupported
Tool callingSupported
ReasoningSupported
Image inputSupported
StreamingSupported

Troubleshooting

Wrong base URL

Python uses base_url; JavaScript uses baseURL. Pass the IteraCompute key explicitly: the SDK default environment variable is not ITERACOMPUTE_API_KEY.

Wrong endpoint

Call client.chat.completions.create and read choices[0].message.content. A Responses example and response.output_text are a different API; this guide does not establish Qwen Responses support.

HTTP 200, empty text

An empty content field is not a successful text test. The free Qwen examples allow 512 output tokens and disable thinking. This parameter is model-specific.

429 / Request limits

Check account-wide monthly usage and TPM. Honor Retry-After and avoid parallel retries. Free Qwen has no automatic paid overage; other models use their published prices.

401 / 403: check the key and model permission. Free Qwen requires no balance or card. For paid models, also check available balance.

Keep exploring

LiteLLM

Route requests through one interface.

Vercel AI SDK

Build AI experiences in TypeScript.

OpenAI SDK configuration reference →

Start building with OpenAI SDK.

Connect your key, choose a model and send your first request.

Get API Key View Docs