1. Create an API key
Create or sign in to your IteraCompute account, then create a key in the Console.
Use open models in your IDE.
Create or sign in to your IteraCompute account, then create a key in the Console.
Use provider: openai with apiBase and useResponsesApi: false. These chat, edit and apply roles use Chat Completions.
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.
name: IteraCompute
version: 1.0.0
schema: v1
models:
- name: Auto
provider: openai
model: Auto
apiBase: https://api.iteracompute.com/v1
apiKey: ${{ secrets.ITERACOMPUTE_API_KEY }}
useResponsesApi: false
roles: [chat, edit, apply]
capabilities: [tool_use]
defaultCompletionOptions:
contextLength: 131072# 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.
Merge the example into ~/.continue/config.yaml and check the YAML indentation. Store the key in ~/.continue/.env with the same name used by the secrets expression.
Use provider: openai, apiBase ending in /v1 and useResponsesApi: false. These chat, edit and apply roles are not an autocomplete configuration.
Check the selected role and tool_use capability. Test a small edit, review its diff and run its test; a chat reply alone does not verify editing.
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.