Pi

Before you start

Install the named client using its official instructions. Pi here means the pi-mono coding agent; Hermes means Nous Research's Hermes Agent.

Once your Inferway account is activated, get an API key from Console → API keys. Use a dedicated key for this client and review its model access and spending limits. Both live and test prefixes use the same inference and billing path; test is an environment label, not a free or simulated inference mode.

Use an Inferway key for Inferway's endpoint. An OpenRouter key belongs to OpenRouter and cannot authenticate to this address.

Keep the key in the client's credential store or your local environment. Do not paste it into a prompt, screenshot, or committed configuration. These examples use bash/zsh on macOS or Linux.

Make the key available to this terminal

The prompt below hides your input and keeps the key out of shell history. Start the client from this same terminal; a separately opened app may not inherit this variable.

printf 'Inferway API key: '
IFS= read -r -s INFERWAY_API_KEY
printf '\n'
export INFERWAY_API_KEY

Confirm the endpoint and model

Use the full model ID inferway/mimo-v2.6-flash. The Base URL ends in /v1 once; do not append /chat/completions to a Base URL setting. Check that the response below contains the model ID.

curl --fail-with-body --silent --show-error --max-time 30 \
  'https://api.inferway.ai/v1/models' \
  -H "Authorization: Bearer $INFERWAY_API_KEY"

Add the custom provider

Merge this provider into ~/.pi/agent/models.json. Preserve other providers if the file already exists. Pi's openai-completions adapter uses Chat Completions; it does not mean the legacy /completions route.

The dollar sign in $INFERWAY_API_KEY is required for Pi's environment interpolation. Check for an older inferway credential in Pi's auth.json if it keeps using a different key. The text-only example leaves reasoning and images disabled; enable them only after checking the model and client behavior.

The config shows the catalog context window and maxTokens; the accepted live probes used a 1024-token output limit for bounded verification. Raising the limit in daily use was not covered by that verification.

{
  "providers": {
    "inferway": {
      "baseUrl": "https://api.inferway.ai/v1",
      "api": "openai-completions",
      "apiKey": "$INFERWAY_API_KEY",
      "models": [
        {
          "id": "inferway/mimo-v2.6-flash",
          "name": "Inferway",
          "reasoning": false,
          "input": [
            "text"
          ],
          "contextWindow": 262144,
          "maxTokens": 131072,
          "compat": {
            "supportsDeveloperRole": false,
            "supportsReasoningEffort": false,
            "maxTokensField": "max_tokens"
          }
        }
      ]
    }
  }
}

Select Inferway

Start Pi with the explicit provider and model below, or use /model in Pi and select the Inferway entry. /model reloads the model configuration. If the model is missing, check that INFERWAY_API_KEY is available.

pi --provider inferway --model 'inferway/mimo-v2.6-flash'

Free accounts and long tasks

Registered free accounts: 8 requests/second burst, 90 requests/minute, 300 requests/hour and 1,000 requests/day, with 2 concurrent requests. No per-request input or output token cap, and no per-minute or daily token quota.

Hourly and daily request counts are rolling windows, not a reset at a fixed time. API keys on the same account share these request counts.

Each request is still bounded by the model's own context length and maximum output. Use streaming for outputs above 4,096 tokens.

Pi streams model responses. For noninteractive runs, redirect stdin from /dev/null. If a task reports a request-size limit, compact the conversation; waiting does not change that limit.

pi --provider inferway --model 'inferway/mimo-v2.6-flash' -p 'Review this project and run its tests' </dev/null

Confirm the connection

1. Start a fresh conversation with the configured provider and model. Ask: "Reply with exactly: connected". Confirm that text arrives without an API error.
2. Open Console → Requests to see the request status and token usage.
3. For coding tasks, ask the client to read a non-sensitive file. Review any proposed edits before applying them.

Cost and usage

Actual consumption is recorded by Inferway: open Console → Requests to see each request's status and token usage, and Console → Usage for totals. Numbers a client shows locally are its own estimates, not billing amounts; rely on the Console.

Verification status

There is no verification record for this model in this client: the recipe below is a configuration reference, not a tested integration for that model.

If a request fails

Authentication: check that an API key is present, active, and allowed to use the model. Reopen the client from the terminal containing the variable. Never print the full key when debugging.

Wrong endpoint or model: check for a duplicate /v1, use the exact published model ID, and confirm the client is using Chat Completions. A request to /responses or /completions cannot be repaired by changing the key.

Limits or timeout: check wallet balance and key limits, respect Retry-After, and reduce the prompt or output budget. Keep streaming enabled for long outputs. Avoid repeated agent retries while diagnosing.

When contacting support, share the client version, model ID, timestamp, and request ID if available. Redact credentials and source code.