diff --git a/packages/ai/.changes/fast-mode-api-key.md b/packages/ai/.changes/fast-mode-api-key.md
new file mode 100644
index 000000000..8be2fd217
--- /dev/null
+++ b/packages/ai/.changes/fast-mode-api-key.md
@@ -0,0 +1 @@
+- Added Fast mode (service_tier `priority`) support for OpenAI API-key models GPT-5.4/GPT-5.5/GPT-5.6, and corrected the GPT-5.6 fast-pricing multiplier from 2.5x to 2x per OpenAI's pricing table ([#1595](https://github.com/PrimeIntellect-ai/prime-agent/discussions/1595)).
diff --git a/packages/ai/src/models.ts b/packages/ai/src/models.ts
index fc1910ce7..892fd608f 100644
--- a/packages/ai/src/models.ts
+++ b/packages/ai/src/models.ts
@@ -36,10 +36,12 @@ export function getModels<TProvider extends KnownProvider>(
 }
 
 export function supportsFastMode<TApi extends Api>(model: Model<TApi>): boolean {
+	const eligibleId =
+		model.id === "gpt-5.4" || model.id === "gpt-5.5" || model.id === "gpt-5.6" || model.id.startsWith("gpt-5.6-");
 	return (
-		model.provider === "openai-codex" &&
-		model.api === "openai-codex-responses" &&
-		(model.id === "gpt-5.4" || model.id === "gpt-5.5" || model.id === "gpt-5.6" || model.id.startsWith("gpt-5.6-"))
+		eligibleId &&
+		((model.provider === "openai-codex" && model.api === "openai-codex-responses") ||
+			(model.provider === "openai" && model.api === "openai-responses"))
 	);
 }
 
diff --git a/packages/ai/src/providers/openai-codex-responses.ts b/packages/ai/src/providers/openai-codex-responses.ts
index 01f0d7782..cf9f113a8 100644
--- a/packages/ai/src/providers/openai-codex-responses.ts
+++ b/packages/ai/src/providers/openai-codex-responses.ts
@@ -366,6 +366,7 @@ function buildRequestBody(
 	return body;
 }
 
+// Multipliers per https://developers.openai.com/api/docs/pricing (retrieved 2026-08-21)
 function getServiceTierCostMultiplier(
 	model: Pick<Model<"openai-codex-responses">, "id">,
 	serviceTier: ResponseCreateParamsStreaming["service_tier"] | undefined,
@@ -374,7 +375,7 @@ function getServiceTierCostMultiplier(
 		case "flex":
 			return 0.5;
 		case "priority":
-			return model.id.startsWith("gpt-5.5") || model.id.startsWith("gpt-5.6") ? 2.5 : 2;
+			return model.id.startsWith("gpt-5.5") ? 2.5 : 2;
 		default:
 			return 1;
 	}
diff --git a/packages/ai/src/providers/openai-responses.ts b/packages/ai/src/providers/openai-responses.ts
index e0a4f7228..0370d63fc 100644
--- a/packages/ai/src/providers/openai-responses.ts
+++ b/packages/ai/src/providers/openai-responses.ts
@@ -265,6 +265,7 @@ function buildParams(model: Model<"openai-responses">, context: Context, options
 	return params;
 }
 
+// Multipliers per https://developers.openai.com/api/docs/pricing (retrieved 2026-08-21)
 function getServiceTierCostMultiplier(
 	model: Pick<Model<"openai-responses">, "id">,
 	serviceTier: ResponseCreateParamsStreaming["service_tier"] | undefined,
diff --git a/packages/ai/test/fast-mode.test.ts b/packages/ai/test/fast-mode.test.ts
index 3f2185ec0..7c3203001 100644
--- a/packages/ai/test/fast-mode.test.ts
+++ b/packages/ai/test/fast-mode.test.ts
@@ -23,10 +23,17 @@ describe("Fast mode", () => {
 		expect(supportsFastMode(model("openai-codex", id, "openai-codex-responses"))).toBe(true);
 	});
 
-	it("rejects unsupported models and API-key providers", () => {
+	it("rejects unsupported models and non-OpenAI gateways", () => {
 		expect(supportsFastMode(model("openai-codex", "gpt-5.3-codex", "openai-codex-responses"))).toBe(false);
 		expect(supportsFastMode(model("openai-codex", "gpt-5.4-mini", "openai-codex-responses"))).toBe(false);
-		expect(supportsFastMode(model("openai", "gpt-5.5", "openai-responses"))).toBe(false);
+		expect(supportsFastMode(model("openai", "gpt-5.1", "openai-responses"))).toBe(false);
+		expect(supportsFastMode(model("github-copilot", "gpt-5.5", "openai-responses"))).toBe(false);
+	});
+
+	it("admits API-key models and forwards priority", () => {
+		const testModel = model("openai", "gpt-5.5", "openai-responses");
+		expect(supportsFastMode(testModel)).toBe(true);
+		expect(buildBaseOptions(testModel, { serviceTier: "priority" }).serviceTier).toBe("priority");
 	});
 
 	it("forwards priority through simple stream options", () => {
diff --git a/packages/ai/test/openai-codex-stream.test.ts b/packages/ai/test/openai-codex-stream.test.ts
index f2e6926a2..e05b9d983 100644
--- a/packages/ai/test/openai-codex-stream.test.ts
+++ b/packages/ai/test/openai-codex-stream.test.ts
@@ -567,7 +567,7 @@ describe("openai-codex streaming", () => {
 		["gpt-5.4", "priority", 2],
 		["gpt-5.5", "flex", 0.5],
 		["gpt-5.5", "priority", 2.5],
-		["gpt-5.6-sol", "priority", 2.5],
+		["gpt-5.6-sol", "priority", 2],
 	] as const)(
 		"uses the client-sent %s service tier for %s when Codex echoes default",
 		async (modelId, serviceTier, multiplier) => {
diff --git a/packages/coding-agent/.changes/fast-mode-api-key.md b/packages/coding-agent/.changes/fast-mode-api-key.md
new file mode 100644
index 000000000..771b537bf
--- /dev/null
+++ b/packages/coding-agent/.changes/fast-mode-api-key.md
@@ -0,0 +1 @@
+- Enabled `/fast` with OpenAI API-key authentication for GPT-5.4/GPT-5.5/GPT-5.6 and updated the unavailable message ([#1595](https://github.com/PrimeIntellect-ai/prime-agent/discussions/1595)).
diff --git a/packages/coding-agent/src/modes/interactive/interactive-mode.ts b/packages/coding-agent/src/modes/interactive/interactive-mode.ts
index 2e73dda72..5b7f74cde 100644
--- a/packages/coding-agent/src/modes/interactive/interactive-mode.ts
+++ b/packages/coding-agent/src/modes/interactive/interactive-mode.ts
@@ -7854,7 +7854,8 @@ export class InteractiveMode {
 	}
 
 	private handleFastCommand(): void {
-		const unavailableMessage = "Fast mode requires GPT-5.4, GPT-5.5, or GPT-5.6 with ChatGPT authentication";
+		const unavailableMessage =
+			"Fast mode requires GPT-5.4, GPT-5.5, or GPT-5.6 with ChatGPT or OpenAI API key authentication";
 		if (!this.currentModelSupportsFastMode()) {
 			this.showStatus(unavailableMessage);
 			return;
diff --git a/packages/coding-agent/test/interactive-mode-effort-command.test.ts b/packages/coding-agent/test/interactive-mode-effort-command.test.ts
index 2fd0ae6b0..380b07554 100644
--- a/packages/coding-agent/test/interactive-mode-effort-command.test.ts
+++ b/packages/coding-agent/test/interactive-mode-effort-command.test.ts
@@ -403,7 +403,7 @@ describe("InteractiveMode /effort", () => {
 
 			expect(context.agentConnection.setServiceTier).not.toHaveBeenCalled();
 			expect(context.showStatus).toHaveBeenCalledWith(
-				"Fast mode requires GPT-5.4, GPT-5.5, or GPT-5.6 with ChatGPT authentication",
+				"Fast mode requires GPT-5.4, GPT-5.5, or GPT-5.6 with ChatGPT or OpenAI API key authentication",
 			);
 		});
 
diff --git a/packages/coding-agent/test/suite/regressions/4620-fast-mode-settings.test.ts b/packages/coding-agent/test/suite/regressions/4620-fast-mode-settings.test.ts
index 451172367..29d20c82f 100644
--- a/packages/coding-agent/test/suite/regressions/4620-fast-mode-settings.test.ts
+++ b/packages/coding-agent/test/suite/regressions/4620-fast-mode-settings.test.ts
@@ -79,6 +79,20 @@ describe("ENG-4620 fast mode settings", () => {
 		expect(harness.session.serviceTier).toBe("priority");
 	});
 
+	it("admits fast mode with OpenAI API-key models and clamps unsupported ones", async () => {
+		harness = await createHarness({
+			api: "openai-responses",
+			provider: "openai",
+			models: [{ id: "gpt-5.5" }, { id: "gpt-4-turbo" }],
+		});
+
+		harness.session.setServiceTier("priority");
+		expect(harness.session.serviceTier).toBe("priority");
+
+		await harness.session.setModel(harness.getModel("gpt-4-turbo")!);
+		expect(harness.session.serviceTier).toBe("default");
+	});
+
 	it("returns the effective service tier when cycling models", async () => {
 		harness = await createHarness({
 			api: "openai-codex-responses",