1. Create an API key
Create or sign in to your IteraCompute account, then create a key in the Console.
Connect models to chains and agents.
Create or sign in to your IteraCompute account, then create a key in the Console.
Configure ChatOpenAI with base_url. Use the Chat Completions path rather than Responses API.
Use the exact API Model ID for your chosen model. Check its context and capabilities before enabling agent or vision features.
Keep API keys in your server environment or tool credential store. Replace the example key field with your own key where applicable.
import os
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
model="Auto",
base_url="https://api.iteracompute.com/v1",
api_key=os.environ["ITERACOMPUTE_API_KEY"],
use_responses_api=False,
stream_usage=False,
max_tokens=512,
)
print(llm.invoke("Hello!").content)# 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":"Auto","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 Auto, use the first free call example to disable thinking, then send a prompt inside your tool.
Capabilities describe the IteraCompute API. Feature availability in your workflow also depends on the tool and its settings; reasoning controls vary by model.
Import ChatOpenAI from langchain_openai. Keep base_url ending in /v1 and use_responses_api=False for this Chat Completions recipe.
This compatible-endpoint example sets stream_usage=False. Do not assume every OpenAI-specific streaming option is accepted by the selected model.
A text invoke only tests text generation. Bind tools separately, inspect the returned tool calls and execute a bounded test tool before claiming agent support.
Check account-wide monthly usage and concurrency. Honor Retry-After and avoid parallel retries. Free Auto has no automatic paid overage; other models use their published prices.
401 / 403: check the key and model permission. Free Auto requires no balance or card. For paid models, also check available balance.
Connect your key, choose a model and send your first request.