From 31125260510b93812fa44adc5fcf6ad2ff5b84c9 Mon Sep 17 00:00:00 2001
From: Markus Ylisiurunen <markus.ylisiurunen@gmail.com>
Date: Wed, 21 Jan 2026 20:31:02 +0200
Subject: [PATCH] remove service tier from `azure-openai-responses`; add link
 to changelog entry

---
 packages/ai/CHANGELOG.md                      |  2 +-
 .../src/providers/azure-openai-responses.ts   | 29 -------------------
 2 files changed, 1 insertion(+), 30 deletions(-)

diff --git a/packages/ai/CHANGELOG.md b/packages/ai/CHANGELOG.md
index 4035338b..0a72f9b9 100644
--- a/packages/ai/CHANGELOG.md
+++ b/packages/ai/CHANGELOG.md
@@ -13,7 +13,7 @@
 - Added `headers` option to `StreamOptions` for custom HTTP headers in API requests. Supported by all providers except Amazon Bedrock (which uses AWS SDK auth). Headers are merged with provider defaults and `model.headers`, with `options.headers` taking precedence.
 - Added `originator` option to `loginOpenAICodex()` for custom OAuth client identification
 - Browser compatibility for pi-ai: replaced top-level Node.js imports with dynamic imports for browser environments ([#873](https://github.com/badlogic/pi-mono/issues/873))
-- Added `azure-openai-responses` provider support for Azure OpenAI Responses API.
+- Added `azure-openai-responses` provider support for Azure OpenAI Responses API. ([#890](https://github.com/badlogic/pi-mono/pull/890) by [@markusylisiurunen](https://github.com/markusylisiurunen))
 
 ### Fixed
 
diff --git a/packages/ai/src/providers/azure-openai-responses.ts b/packages/ai/src/providers/azure-openai-responses.ts
index c6d89a4e..cd25a3e1 100644
--- a/packages/ai/src/providers/azure-openai-responses.ts
+++ b/packages/ai/src/providers/azure-openai-responses.ts
@@ -25,7 +25,6 @@ import type {
 	ThinkingContent,
 	Tool,
 	ToolCall,
-	Usage,
 } from "../types.js";
 import { AssistantMessageEventStream } from "../utils/event-stream.js";
 import { parseStreamingJson } from "../utils/json-parse.js";
@@ -52,7 +51,6 @@ const DEFAULT_AZURE_API_VERSION = "2025-04-01-preview";
 export interface AzureOpenAIResponsesOptions extends StreamOptions {
 	reasoningEffort?: "minimal" | "low" | "medium" | "high" | "xhigh";
 	reasoningSummary?: "auto" | "detailed" | "concise" | null;
-	serviceTier?: ResponseCreateParamsStreaming["service_tier"];
 	azureApiVersion?: string;
 	azureEndpoint?: string;
 	azureResourceName?: string;
@@ -292,7 +290,6 @@ export const streamAzureOpenAIResponses: StreamFunction<"azure-openai-responses"
 						};
 					}
 					calculateCost(model, output.usage);
-					applyServiceTierPricing(output.usage, response?.service_tier ?? options?.serviceTier);
 					// Map status to stop reason
 					output.stopReason = mapStopReason(response?.status);
 					if (output.content.some((b) => b.type === "toolCall") && output.stopReason === "stop") {
@@ -424,10 +421,6 @@ function buildParams(
 		params.temperature = options?.temperature;
 	}
 
-	if (options?.serviceTier !== undefined) {
-		params.service_tier = options.serviceTier;
-	}
-
 	if (context.tools) {
 		params.tools = convertTools(context.tools);
 	}
@@ -616,28 +609,6 @@ function convertTools(tools: Tool[]): OpenAITool[] {
 	}));
 }
 
-function getServiceTierCostMultiplier(serviceTier: ResponseCreateParamsStreaming["service_tier"] | undefined): number {
-	switch (serviceTier) {
-		case "flex":
-			return 0.5;
-		case "priority":
-			return 2;
-		default:
-			return 1;
-	}
-}
-
-function applyServiceTierPricing(usage: Usage, serviceTier: ResponseCreateParamsStreaming["service_tier"] | undefined) {
-	const multiplier = getServiceTierCostMultiplier(serviceTier);
-	if (multiplier === 1) return;
-
-	usage.cost.input *= multiplier;
-	usage.cost.output *= multiplier;
-	usage.cost.cacheRead *= multiplier;
-	usage.cost.cacheWrite *= multiplier;
-	usage.cost.total = usage.cost.input + usage.cost.output + usage.cost.cacheRead + usage.cost.cacheWrite;
-}
-
 function mapStopReason(status: OpenAI.Responses.ResponseStatus | undefined): StopReason {
 	if (!status) return "stop";
 	switch (status) {