diff --git a/packages/llm/AGENTS.md b/packages/llm/AGENTS.md
index cf8ceffbf4..c2713273e3 100644
--- a/packages/llm/AGENTS.md
+++ b/packages/llm/AGENTS.md
@@ -109,7 +109,7 @@ Do not blanket re-record an entire test file when adding one cassette. `RECORD=t
 
 - [x] Add a generic OpenAI-compatible Chat adapter for non-OpenAI providers that expose `/chat/completions`; use `../ai/packages/openai-compatible` as the behavior reference.
 - [ ] Keep OpenAI Responses as a separate first-class protocol for providers that actually implement `/responses`; do not treat generic OpenAI-compatible providers as Responses-capable by default.
-- [ ] Cover OpenAI-compatible provider families that can share the generic adapter first: DeepSeek, TogetherAI, Cerebras, Baseten, Fireworks, DeepInfra, and similar providers.
+- [x] Cover OpenAI-compatible provider families that can share the generic adapter first: DeepSeek, TogetherAI, Cerebras, Baseten, Fireworks, DeepInfra, and similar providers.
 - [ ] Decide which providers need thin dedicated wrappers over OpenAI-compatible Chat because they have custom parsing/options: Mistral, Groq, xAI, Perplexity, and Cohere.
 - [ ] Add Bedrock Converse support or a clear compatibility layer before moving Amazon Bedrock traffic onto `packages/llm`.
 - [ ] Decide Vertex shape after Bedrock/OpenAI-compatible are stable: Vertex Gemini as Gemini target/http patch vs adapter, and Vertex Anthropic as Anthropic target/http patch vs adapter.
diff --git a/packages/llm/src/provider/openai-compatible-chat.ts b/packages/llm/src/provider/openai-compatible-chat.ts
index ecaefc0f7e..f4700cdd66 100644
--- a/packages/llm/src/provider/openai-compatible-chat.ts
+++ b/packages/llm/src/provider/openai-compatible-chat.ts
@@ -15,6 +15,24 @@ export type OpenAICompatibleChatModelInput = Omit<ModelInput, "protocol" | "head
   readonly queryParams?: Record<string, string>
 }
 
+export type ProviderFamilyModelInput = Omit<OpenAICompatibleChatModelInput, "provider" | "baseURL"> & {
+  readonly baseURL?: string
+}
+
+interface ProviderFamily {
+  readonly provider: string
+  readonly baseURL: string
+}
+
+const families = {
+  baseten: { provider: "baseten", baseURL: "https://inference.baseten.co/v1" },
+  cerebras: { provider: "cerebras", baseURL: "https://api.cerebras.ai/v1" },
+  deepinfra: { provider: "deepinfra", baseURL: "https://api.deepinfra.com/v1/openai" },
+  deepseek: { provider: "deepseek", baseURL: "https://api.deepseek.com/v1" },
+  fireworks: { provider: "fireworks", baseURL: "https://api.fireworks.ai/inference/v1" },
+  togetherai: { provider: "togetherai", baseURL: "https://api.together.xyz/v1" },
+} as const satisfies Record<string, ProviderFamily>
+
 const invalid = (message: string) => new InvalidRequestError({ message })
 
 const isStringRecord = (value: unknown): value is Record<string, string> =>
@@ -77,6 +95,26 @@ export const model = (input: OpenAICompatibleChatModelInput) => {
   })
 }
 
+const familyModel = (family: ProviderFamily, input: ProviderFamilyModelInput) =>
+  model({
+    ...input,
+    provider: family.provider,
+    baseURL: input.baseURL ?? family.baseURL,
+    native: { ...input.native, openaiCompatibleProvider: family.provider },
+  })
+
+export const baseten = (input: ProviderFamilyModelInput) => familyModel(families.baseten, input)
+
+export const cerebras = (input: ProviderFamilyModelInput) => familyModel(families.cerebras, input)
+
+export const deepinfra = (input: ProviderFamilyModelInput) => familyModel(families.deepinfra, input)
+
+export const deepseek = (input: ProviderFamilyModelInput) => familyModel(families.deepseek, input)
+
+export const fireworks = (input: ProviderFamilyModelInput) => familyModel(families.fireworks, input)
+
+export const togetherai = (input: ProviderFamilyModelInput) => familyModel(families.togetherai, input)
+
 export const includeUsage = adapter.patch("include-usage", {
   reason: "request final usage chunk from OpenAI-compatible Chat streaming responses",
   apply: (target) => ({
diff --git a/packages/llm/test/provider/openai-compatible-chat.test.ts b/packages/llm/test/provider/openai-compatible-chat.test.ts
index 56b220d00c..37c813f943 100644
--- a/packages/llm/test/provider/openai-compatible-chat.test.ts
+++ b/packages/llm/test/provider/openai-compatible-chat.test.ts
@@ -41,6 +41,15 @@ const usageChunk = (usage: object) => ({
   usage,
 })
 
+const providerFamilies = [
+  ["baseten", OpenAICompatibleChat.baseten, "https://inference.baseten.co/v1"],
+  ["cerebras", OpenAICompatibleChat.cerebras, "https://api.cerebras.ai/v1"],
+  ["deepinfra", OpenAICompatibleChat.deepinfra, "https://api.deepinfra.com/v1/openai"],
+  ["deepseek", OpenAICompatibleChat.deepseek, "https://api.deepseek.com/v1"],
+  ["fireworks", OpenAICompatibleChat.fireworks, "https://api.fireworks.ai/inference/v1"],
+  ["togetherai", OpenAICompatibleChat.togetherai, "https://api.together.xyz/v1"],
+] as const
+
 describe("OpenAI-compatible Chat adapter", () => {
   it.effect("prepares generic Chat target", () =>
     Effect.gen(function* () {
@@ -76,6 +85,45 @@ describe("OpenAI-compatible Chat adapter", () => {
     }),
   )
 
+  it.effect("provides model helpers for compatible provider families", () =>
+    Effect.gen(function* () {
+      expect(
+        providerFamilies.map(([provider, makeModel, baseURL]) => {
+          const model = makeModel({ id: `${provider}-model`, apiKey: "test-key" })
+          return {
+            id: model.id,
+            provider: model.provider,
+            protocol: model.protocol,
+            baseURL: model.baseURL,
+            headers: model.headers,
+            native: model.native,
+          }
+        }),
+      ).toEqual(
+        providerFamilies.map(([provider, _, baseURL]) => ({
+          id: `${provider}-model`,
+          provider,
+          protocol: "openai-compatible-chat",
+          baseURL,
+          headers: { authorization: "Bearer test-key" },
+          native: { openaiCompatibleProvider: provider },
+        })),
+      )
+
+      const custom = OpenAICompatibleChat.deepseek({
+        id: "deepseek-chat",
+        apiKey: "test-key",
+        baseURL: "https://custom.deepseek.test/v1",
+      })
+      expect(custom).toMatchObject({
+        provider: "deepseek",
+        protocol: "openai-compatible-chat",
+        baseURL: "https://custom.deepseek.test/v1",
+        native: { openaiCompatibleProvider: "deepseek" },
+      })
+    }),
+  )
+
   it.effect("posts to the configured compatible endpoint and parses text usage", () =>
     Effect.gen(function* () {
       const response = yield* client({