diff --git a/packages/ai/src/protocols/openai-responses.ts b/packages/ai/src/protocols/openai-responses.ts
index 10ca6364fd7..704b5d99375 100644
--- a/packages/ai/src/protocols/openai-responses.ts
+++ b/packages/ai/src/protocols/openai-responses.ts
@@ -134,7 +134,7 @@ const HOSTED_TOOLS = {
     name: "code_interpreter",
     input: (item) => ({ code: item.code, container_id: item.container_id }),
   },
-  computer_use_call: { name: "computer_use", input: (item) => item.action ?? {} },
+  computer_call: { name: "computer_use", input: (item) => item.action ?? {} },
   image_generation_call: { name: "image_generation", input: () => ({}), result: hostedToolResult },
   mcp_call: {
     name: "mcp",
diff --git a/packages/ai/src/protocols/utils/open-responses-options.ts b/packages/ai/src/protocols/utils/open-responses-options.ts
index 89b72b1fdbd..ff00d74dbf1 100644
--- a/packages/ai/src/protocols/utils/open-responses-options.ts
+++ b/packages/ai/src/protocols/utils/open-responses-options.ts
@@ -28,7 +28,11 @@ export const ResponseIncludables = [
 export type ResponseIncludable = (typeof ResponseIncludables)[number] | (string & {})
 
 export const ServiceTiers = ["auto", "default", "flex", "priority"] as const
-export type ServiceTier = (typeof ServiceTiers)[number]
+export type ServiceTier = (typeof ServiceTiers)[number] | (string & {})
+export const ServiceTier = Schema.declare<ServiceTier>(
+  (value): value is ServiceTier => typeof value === "string",
+  { title: "ServiceTier" },
+)
 
 export const Truncations = ["auto", "disabled"] as const
 export type Truncation = (typeof Truncations)[number]
@@ -38,7 +42,7 @@ export const ResponseIncludableSchema = Schema.declare<ResponseIncludable>(
   (value): value is ResponseIncludable => typeof value === "string",
   { title: "ResponseIncludable" },
 )
-export const ServiceTierSchema = Schema.Literals(ServiceTiers)
+export const ServiceTierSchema = ServiceTier
 export const TruncationSchema = Schema.Literals(Truncations)
 
 export const AllowedTools = Schema.Struct({
diff --git a/packages/ai/src/protocols/utils/openai-options.ts b/packages/ai/src/protocols/utils/openai-options.ts
index bb47053093c..f3e56be4a06 100644
--- a/packages/ai/src/protocols/utils/openai-options.ts
+++ b/packages/ai/src/protocols/utils/openai-options.ts
@@ -9,8 +9,8 @@ export type OpenAITextVerbosity = OpenResponsesOptions.TextVerbosity
 // in lockstep with `openai-node/src/resources/responses/responses.ts`.
 export const OpenAIResponseIncludables = OpenResponsesOptions.ResponseIncludables
 export type OpenAIResponseIncludable = OpenResponsesOptions.ResponseIncludable
-export const OpenAIServiceTiers = OpenResponsesOptions.ServiceTiers
-export type OpenAIServiceTier = OpenResponsesOptions.ServiceTier
+export const OpenAIServiceTiers = [...OpenResponsesOptions.ServiceTiers, "scale"] as const
+export type OpenAIServiceTier = (typeof OpenAIServiceTiers)[number] | (string & {})
 
 export const OpenAIReasoningEffort = OpenResponsesOptions.ReasoningEffort
 export const OpenAITextVerbosity = OpenResponsesOptions.TextVerbosity
diff --git a/packages/ai/src/providers/openai-options.ts b/packages/ai/src/providers/openai-options.ts
index ca85642ef3a..5adaf555a1f 100644
--- a/packages/ai/src/providers/openai-options.ts
+++ b/packages/ai/src/providers/openai-options.ts
@@ -1,9 +1,13 @@
 import { mergeProviderOptions, type ProviderOptions } from "../schema/index.js"
-import type { OpenResponsesOptionsInput } from "./open-responses-options.js"
+import type { OpenAIServiceTier } from "../protocols/utils/openai-options.js"
+import type { Options } from "../protocols/utils/open-responses-options.js"
 
 export type { OpenAIResponseIncludable, OpenAIServiceTier } from "../protocols/utils/openai-options.js"
 
-export type OpenAIOptionsInput = OpenResponsesOptionsInput
+export type OpenAIOptionsInput = Omit<Options, "serviceTier"> & {
+  readonly serviceTier?: OpenAIServiceTier
+  readonly [key: string]: unknown
+}
 
 export type OpenAIProviderOptionsInput = OpenAIOptionsInput
 
diff --git a/packages/ai/test/provider-options/google-vertex-chat.types.ts b/packages/ai/test/provider-options/google-vertex-chat.types.ts
index 2e748e65377..5b6e9840c4d 100644
--- a/packages/ai/test/provider-options/google-vertex-chat.types.ts
+++ b/packages/ai/test/provider-options/google-vertex-chat.types.ts
@@ -4,10 +4,4 @@ import { GoogleVertexChat } from "../../src/providers.js"
 const model = GoogleVertexChat.configure({ accessToken: "test", project: "project" }).model("gemini")
 
 LLM.request({ model, prompt: "Hello", providerOptions: { serviceTier: "priority" } })
-
-LLM.request({
-  model,
-  prompt: "Hello",
-  // @ts-expect-error Vertex OpenAI-compatible service tiers use the OpenAI union.
-  providerOptions: { serviceTier: "premium" },
-})
+LLM.request({ model, prompt: "Hello", providerOptions: { serviceTier: "future-tier" } })
diff --git a/packages/ai/test/provider-options/openai.types.ts b/packages/ai/test/provider-options/openai.types.ts
index 6419070b355..e2746750f48 100644
--- a/packages/ai/test/provider-options/openai.types.ts
+++ b/packages/ai/test/provider-options/openai.types.ts
@@ -8,6 +8,8 @@ LLM.request({ model: selected, prompt: "Hello", providerOptions: { reasoningEffo
 LLM.request({ model: selected, prompt: "Hello", providerOptions: { reasoningEffort: "experimental" } })
 LLM.request({ model: selected, prompt: "Hello", providerOptions: { textVerbosity: "low" } })
 LLM.request({ model: selected, prompt: "Hello", providerOptions: { textVerbosity: "verbose" } })
+LLM.request({ model: selected, prompt: "Hello", providerOptions: { serviceTier: "scale" } })
+LLM.request({ model: selected, prompt: "Hello", providerOptions: { serviceTier: "future-tier" } })
 LLM.request({ model: chat, prompt: "Hello", providerOptions: { reasoningEffort: "max" } })
 LLM.request({ model: chat, prompt: "Hello", providerOptions: { reasoningEffort: "experimental" } })
 
diff --git a/packages/ai/test/provider/openai-compatible-responses.test.ts b/packages/ai/test/provider/openai-compatible-responses.test.ts
index e1968d6272b..ad46fbc516d 100644
--- a/packages/ai/test/provider/openai-compatible-responses.test.ts
+++ b/packages/ai/test/provider/openai-compatible-responses.test.ts
@@ -189,6 +189,7 @@ describe("Open Responses-compatible route", () => {
           streamOptions: { includeObfuscation: false },
           topLogprobs: 3,
           truncation: "auto",
+          serviceTier: "provider-tier",
           allowedTools: { toolNames: ["lookup"] },
           maxToolCalls: 2,
           parallelToolCalls: false,
@@ -213,6 +214,7 @@ describe("Open Responses-compatible route", () => {
         presence_penalty: 0.2,
         frequency_penalty: -0.1,
         truncation: "auto",
+        service_tier: "provider-tier",
         tool_choice: {
           type: "allowed_tools",
           mode: "auto",
diff --git a/packages/ai/test/provider/openai-responses.test.ts b/packages/ai/test/provider/openai-responses.test.ts
index 15489673fa5..0a0f40af04d 100644
--- a/packages/ai/test/provider/openai-responses.test.ts
+++ b/packages/ai/test/provider/openai-responses.test.ts
@@ -188,13 +188,13 @@ describe("OpenAI Responses route", () => {
     }),
   )
 
-  it.effect("omits unsupported semantic service tiers", () =>
+  it.effect("passes through provider-defined service tiers", () =>
     Effect.gen(function* () {
       const prepared = yield* compileRequest(
-        LLMRequest.update(request, { providerOptions: { serviceTier: "unsupported" } }),
+        LLMRequest.update(request, { providerOptions: { serviceTier: "scale" } }),
       )
 
-      expect(prepared.body).not.toHaveProperty("service_tier")
+      expect(prepared.body.service_tier).toBe("scale")
     }),
   )
 
@@ -2652,6 +2652,47 @@ describe("OpenAI Responses route", () => {
     }),
   )
 
+  it.effect("decodes computer_call as provider-executed tool-call + tool-result", () =>
+    Effect.gen(function* () {
+      const item = {
+        type: "computer_call",
+        id: "computer_1",
+        call_id: "call_1",
+        status: "completed",
+        action: { type: "click", x: 100, y: 200 },
+      }
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { type: "response.output_item.done", item },
+              { type: "response.completed", response: { usage: { input_tokens: 5, output_tokens: 1 } } },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.events.filter((event) => event.type === "tool-call" || event.type === "tool-result")).toEqual([
+        {
+          type: "tool-call",
+          id: "computer_1",
+          name: "computer_use",
+          input: { type: "click", x: 100, y: 200 },
+          providerExecuted: true,
+          providerMetadata: { openai: { itemId: "computer_1" } },
+        },
+        {
+          type: "tool-result",
+          id: "computer_1",
+          name: "computer_use",
+          result: { type: "json", value: item },
+          providerExecuted: true,
+          providerMetadata: { openai: { itemId: "computer_1" } },
+        },
+      ])
+    }),
+  )
+
   it.effect("decodes image generation output as image content", () =>
     Effect.gen(function* () {
       const item = {