From 9c585bb58ba98826cd5f7bf596cb65f411d378a4 Mon Sep 17 00:00:00 2001 From: xinxin <45682184+andyWang1688@users.noreply.github.com> Date: Wed, 11 Mar 2026 23:35:16 +0800 Subject: [PATCH] docs(providers): clarify npm choice for chat vs responses APIs (#16974) Co-authored-by: wangxinxin --- packages/web/src/content/docs/providers.mdx | 4 ++-- packages/web/src/content/docs/zh-cn/providers.mdx | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/packages/web/src/content/docs/providers.mdx b/packages/web/src/content/docs/providers.mdx index 34e362649..7f9932051 100644 --- a/packages/web/src/content/docs/providers.mdx +++ b/packages/web/src/content/docs/providers.mdx @@ -1890,7 +1890,7 @@ You can use any OpenAI-compatible provider with opencode. Most modern AI provide ``` Here are the configuration options: - - **npm**: AI SDK package to use, `@ai-sdk/openai-compatible` for OpenAI-compatible providers + - **npm**: AI SDK package to use, `@ai-sdk/openai-compatible` for OpenAI-compatible providers (for `/v1/chat/completions`). If your provider/model uses `/v1/responses`, use `@ai-sdk/openai`. - **name**: Display name in UI. - **models**: Available models. - **options.baseURL**: API endpoint URL. @@ -1957,5 +1957,5 @@ If you are having trouble with configuring a provider, check the following: 2. For custom providers, check the opencode config and: - Make sure the provider ID used in the `/connect` command matches the ID in your opencode config. - - The right npm package is used for the provider. For example, use `@ai-sdk/cerebras` for Cerebras. And for all other OpenAI-compatible providers, use `@ai-sdk/openai-compatible`. + - The right npm package is used for the provider. For example, use `@ai-sdk/cerebras` for Cerebras. And for all other OpenAI-compatible providers, use `@ai-sdk/openai-compatible` (for `/v1/chat/completions`); if a model uses `/v1/responses`, use `@ai-sdk/openai`. For mixed setups under one provider, you can override per model via `provider.npm`. - Check correct API endpoint is used in the `options.baseURL` field. diff --git a/packages/web/src/content/docs/zh-cn/providers.mdx b/packages/web/src/content/docs/zh-cn/providers.mdx index 9c1616876..571b73024 100644 --- a/packages/web/src/content/docs/zh-cn/providers.mdx +++ b/packages/web/src/content/docs/zh-cn/providers.mdx @@ -1845,7 +1845,7 @@ Vercel AI Gateway 允许你通过统一端点访问来自 OpenAI、Anthropic、G ``` 以下是配置选项说明： - - **npm**：要使用的 AI SDK 包，对于 OpenAI 兼容的提供商使用 `@ai-sdk/openai-compatible` + - **npm**：要使用的 AI SDK 包，对于 OpenAI 兼容的提供商使用 `@ai-sdk/openai-compatible`（适用于 `/v1/chat/completions`）。如果你的提供商/模型走 `/v1/responses`，请使用 `@ai-sdk/openai`。 - **name**：在 UI 中显示的名称。 - **models**：可用模型。 - **options.baseURL**：API 端点 URL。 @@ -1911,5 +1911,5 @@ Vercel AI Gateway 允许你通过统一端点访问来自 OpenAI、Anthropic、G 2. 对于自定义提供商，请检查 OpenCode 配置并确认： - `/connect` 命令中使用的提供商 ID 与 OpenCode 配置中的 ID 一致。 - - 使用了正确的 npm 包。例如，Cerebras 应使用 `@ai-sdk/cerebras`。对于其他所有 OpenAI 兼容的提供商，使用 `@ai-sdk/openai-compatible`。 + - 使用了正确的 npm 包。例如，Cerebras 应使用 `@ai-sdk/cerebras`。对于其他所有 OpenAI 兼容的提供商，使用 `@ai-sdk/openai-compatible`（`/v1/chat/completions`）；如果模型走 `/v1/responses`，请使用 `@ai-sdk/openai`。同一 provider 混用时，可在模型下设置 `provider.npm` 覆盖默认值。 - `options.baseURL` 字段中的 API 端点地址正确。