Free Auto in Cline. Three steps.

Follow the fields below, then send your first prompt in Cline.

IteraCompute is a built-in provider in Cline: select it directly and enter your API key. The manual OpenAI Compatible setup below is also available.

30M tokens / monthEligible accounts onlyFree · 128K context

Setup, one step at a time.

Configuration illustrations follow Cline 4.1.23 field names and layout. Enter your key in Cline; these diagrams only show the fields to fill.

The free promotion ends at 00:00 Pacific Time on November 24, 2026. Users with positive net recharge completed before this cutoff retain their existing free tier. Afterward, shared free Auto is limited to these users and users with a currently effective plan. Later recharges do not grant or upgrade free benefits. Plan Auto tokens and monthly shared free benefits are separate allowances.

This guide shows the free Auto settings. For Qwen3.8-Flash, use model ID qwen/qwen3.8-flash and its own context, output limits and paid prices instead.

For MiniMax M3, use model ID minimax/minimax-m3 and its own context, output limits, paid prices and capabilities. Do not copy the free Auto settings. The retained OpenCode and Cline tests cover free Auto only; MiniMax M3 tool workflows have not been verified here. MiniMax M3 model details →

  1. Connect your API

    Choose OpenAI Compatible on the provider setup screen, or open Settings → API Configuration.

    Base URL
    Model ID

    Paste your own API key. Keep /v1 in the URL and use the complete model ID shown here.

    Configure your providerIllustration
    API Provider
    OpenAI Compatible
    Base URL
    https://api.iteracompute.com/v1
    OpenAI Compatible API Key
    ••••••••••••••••••••••••
    Your key, entered locally in Cline.
    Model ID
    Auto
  2. Set the model limits

    Expand MODEL CONFIGURATION and keep the field order shown on the right. These values are for the Free tier.

    • Context includes input plus requested maximum output.
    • Starter / Pro context: 131072 / 262144; maximum output remains 8192.
    • If you use separate Plan/Act models, configure both.
    MODEL CONFIGURATIONIllustration
    Supports Images · Pending
    Context Window Size
    131072
    Max Output Tokens
    8192
    Input Price / 1M tokens
    0
    Output Price / 1M tokens
    0
    Temperature
    0
    Reasoning Effort
    None
    Context: 128K (131072)Input: FreeOutput: Free
    Continue
  3. Send a test prompt

    Continue to the chat, select Act and send the prompt shown here.

    Test prompt

    The actual test returned Hello! without reading files or running commands. A non-empty completed reply is the success criterion.

    ClineIllustration
    COMPLETED

    Hello!

    For this connection test, do not read files or run commands. Complete the task with exactly "Hello!" as your result.

Auto input and output are $0 within the allowance. Cline’s cost display uses the prices you enter. This test verifies connection and completion; assess code edits and shell actions separately.

Version and verification

Tested version
Cline 4.1.23 · VS Code 1.141.0
Result
Text connection passed.

If the reply does not arrive

401 / 403 · Key permissions

Check the key and access to Auto. Free access requires no balance or card.

400 · Context or model settings

Input plus requested max output must fit 131072 on Free. Reduce attached files, history or output budget. Use the exact free model ID; other Qwen models may be paid.

429 · Monthly allowance or concurrency

Check shared account usage, honor Retry-After and avoid parallel retries. Quota exhaustion has no automatic paid overage; wait for the UTC monthly reset or top up to unlock a higher tier.

Empty reply · Test the API separately

Check for a non-empty reply. Try the first free cURL call, which disables thinking for a short visible response through Chat Completions.