ZCode

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.

Add Inferway in ZCode settings

Configure ZCode from its settings UI: Settings → Model providers → Custom providers → Add provider → Custom endpoint, then fill in the fields below. The block is a reference for checking values on screen; do not hand-edit the files under ~/.zcode.

1. Open Settings → Model providers → Custom providers → Add provider and choose Custom endpoint.
2. Fill in: Name Inferway; API format Chat Completions; Base URL https://api.inferway.ai/v1 — it must end in /v1, ZCode does not add it; API key your Inferway key.
3. Enable the provider, then add a model with the exact ID inferway/mimo-v2.6-flash.
4. In that model's Advanced settings change all four: context window to 393216 (the default is 200000), max output tokens to 131072 (the default is 32000), reasoning levels (low to high) to none then high, and the reasoning parameter mapping to {"reasoning_effort": reasoningLevel}.
5. Press Test model, then switch to this model at the top of the chat box. Restart ZCode after changing the configuration.

名称 / Name: Inferway
API 格式 / API format: Chat Completions
Base URL: https://api.inferway.ai/v1
模型 ID / Model ID: inferway/mimo-v2.6-flash
上下文窗口 / Context window: 393216
最大输出 Token / Max output tokens: 131072
推理等级（从低到高）/ Reasoning levels (low to high): none, high
推理参数映射 / Reasoning parameter mapping: {"reasoning_effort": reasoningLevel}

Required changes and verification scope

The reasoning parameter mapping must be changed: ZCode's default mapping for a custom Chat Completions endpoint is rejected by Inferway, so requests fail until you set it to {"reasoning_effort": reasoningLevel}. With that mapping in place the requests are accepted.

Scope of the 2026-09-25 test: it ran the same agent runtime that ships inside the ZCode app, headless, with an isolated config directory and the configuration above. The clicking through the Settings UI itself was not driven step by step.

Image input was not tested: this guide makes no claim about images, and you do not have to enable anything for them.

ZCode stores the API key in plain text under ~/.zcode (provider_config.json and config.json). Keep ~/.zcode out of sync folders and backup repositories.

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

Verified on 3.14.1 (agent runtime 0.16.9), macOS 26.6.2 arm64, 2026-09-25: basic conversation, and file-read, file-edit and shell-command tool round trips against inferway/mimo-v2.6-flash.

This evidence does not cover images, session resume, or reasoning control. Client-side cost estimates are not billing amounts; use Console → Requests and usage for actual consumption.

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.