Bestony AI Provider for StepFun

Adds StepFun (阶跃星辰) as a provider for the WordPress AI Client.

• The model list is fetched live from GET /v1/models, so newly released models appear on their own.

• Text generation and chat history with the Step chat models, including tool calling, structured

output (JSON schema) and stop sequences.

• Vision: step-3.7-flash and the step-1v-* / *-vision families accept images, so features like

Alt Text Generation work.

• Image generation with the step-image-* / step-2x-* text-to-image models, returning either an

inline image or a URL.

• Reasoning output is surfaced as thought parts rather than mixed into the answer text.

• A Settings → Bestony AI Provider for StepFun page to pick which StepFun host to talk to, including the

Step Plan endpoints.

Settings

Settings → Bestony AI Provider for StepFun picks which StepFun host the provider talks to. Four hosts are

offered:

• Stepfun.com — https://api.stepfun.com/v1 (default)

• StepPlan at Stepfun.com — https://api.stepfun.com/step_plan/v1

• Stepfun.ai — https://api.stepfun.ai/v1

• Step Plan at Stepfun.ai — https://api.stepfun.ai/step_plan/v1

The chosen host is used for the model list and for every generation request. It is stored per site, so

each site on a multisite network configures its own. There is also a Setup Step Plan link in the

plugin’s row on the Plugins screen that jumps straight to this page.

Only these four hosts can be selected: a value that is not one of them (written to the database

directly, for example) falls back to the default. Setting STEPFUN_BASE_URL overrides the choice.

The page is available in English, Simplified Chinese ( zh_CN ) and Traditional Chinese ( zh_TW ).

Configuration

The API key is read, in order of precedence, from:

• The STEPFUN_API_KEY environment variable

• The STEPFUN_API_KEY PHP constant

• The connectors_ai_stepfun_api_key option (Settings → Connectors)

All optional settings are environment variables or PHP constants:

• STEPFUN_DEFAULT_MODEL — chat model to prefer in pickers and feature filters.

7-flash.

• STEPFUN_IMAGE_MODEL — image model to prefer in the image generation feature.

Default: step-image-edit-2.

• STEPFUN_BASE_URL — API base URL. Overrides the value chosen on Settings → Bestony AI Provider for StepFun

(see below).

• STEPFUN_MODEL_INPUT_MODALITIES — comma-separated list of modalities your models accept. Include

g. text,image ) to declare vision for every chat model, for deployments ahead of

the built-in list.

• STEPFUN_STRUCTURED_OUTPUT — how JSON response requests are shaped. One of:

• json_schema (default) — sends the JSON schema, wrapped the way StepFun documents it.

• json_object — asks only for valid JSON, without the schema. Fallback for a model that rejects

schemas.

• none — sends no response_format at all.

• STEPFUN_SIZE_LANDSCAPE / STEPFUN_SIZE_PORTRAIT / STEPFUN_SIZE_SQUARE — override the size

value sent for each orientation. Defaults: 1360x768 / 768x1360 / 1024x1024. See the FAQ.

• STEPFUN_REQUEST_TIMEOUT — request timeout in seconds. Default: 120.

• STEPFUN_CONNECT_TIMEOUT — connection timeout in seconds. Default: 10.

Because the plugin has no database-backed settings of its own, changing an environment variable after

the AI Client has cached its model list does not invalidate that cache. If a new value does not take

effect immediately, clear the cache — in WP-CLI:

wp cache flush wp transient delete --all

To influence which models the AI plugin picks, use the standard filters in your own plugin or theme —

this plugin already puts its preferred models first:

5-flash' ) ); return $models; } );<h3>External services</h3>

This plugin connects to the StepFun API, an external service operated by 上海阶跃星辰智能科技有限公司

(StepFun). It is required so the WordPress AI Client can send requests to StepFun models from your

site. StepFun is a paid service: requests are billed to your StepFun account, and an account with API

access is required.

com/v1

by default, or whichever host is chosen on Settings → Bestony AI Provider for StepFun:

• GET /models — called when the AI Client refreshes its list of available models, and when it checks

whether your credentials work. No user content is sent; only your API key, so StepFun can return the

models available to your account.

• POST /chat/completions — called whenever any plugin or theme on your site uses the WordPress AI

Client to generate text or to analyze an image. The request carries your API key and the prompt:

messages, system instruction, tool definitions, and any other parameters the calling code supplied

(conversation history, a JSON schema for structured output, or images attached to the prompt).

• POST /images/generations — called when something on your site asks the AI Client to generate an

image. The request carries your API key and the image prompt.

No request is made until something on your site asks the AI Client for a generation, or the AI Client

refreshes its model list. Your API key is stored on your own site and is only ever sent to the host

configured above.

This service is provided by StepFun:

• Platform and documentation: https://platform.stepfun.com/

• Terms of Service: https://platform.stepfun.com/docs/zh/agreement/userservice

• Privacy Policy: https://platform.stepfun.com/docs/zh/agreement/userprivacy

• International platform: https://platform.stepfun.ai/