Skip to content

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Rust

Support /fast with OpenAI API-key authentication (#1609)

Sebastian Müller848081edb1f9
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 0000000000..8be2fd2178
--- /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 fc1910ce7a..892fd608fb 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 01f0d77825..cf9f113a86 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 e0a4f72284..0370d63fcc 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 3f2185ec0c..7c32030016 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 f2e6926a24..e05b9d9831 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 0000000000..771b537bf1
--- /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 2e73dda72b..5b7f74cdef 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 2fd0ae6b0d..380b075540 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 4511723670..29d20c82fd 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",