diff --git a/src/lib/inference/nvidia-featured-models.test.ts b/src/lib/inference/nvidia-featured-models.test.ts index 9370a47e60c..83ff9dc26cb 100644 --- a/src/lib/inference/nvidia-featured-models.test.ts +++ b/src/lib/inference/nvidia-featured-models.test.ts @@ -315,6 +315,34 @@ describe("NVIDIA featured model catalog", () => { ); }); + it("filters the retired DeepSeek V4 Pro entry the featured feed still lists (#9611)", () => { + const options = getNvidiaFeaturedModelPromptOptions(null, { + runCurlProbeImpl: () => ({ + ok: true, + httpStatus: 200, + curlStatus: 0, + body: JSON.stringify({ + "featured-models": [ + { model: "nvidia/nemotron-3-ultra-550b-a55b", "model-name": "Nemotron 3 Ultra 550B" }, + { model: "nemotron-3-super-120b-a12b", "model-name": "Nemotron 3 Super 120B" }, + { model: "z-ai/glm-5.2", "model-name": "GLM 5.2" }, + { model: "minimaxai/minimax-m3", "model-name": "Minimax M3" }, + { model: "deepseek-ai/deepseek-v4-pro", "model-name": "DeepSeek V4 Pro" }, + ], + }), + stderr: "", + message: "", + }), + }); + + expect(options.cloudModelOptions.map((option) => option.id)).toEqual([ + "nvidia/nemotron-3-ultra-550b-a55b", + "nvidia/nemotron-3-super-120b-a12b", + "z-ai/glm-5.2", + "minimaxai/minimax-m3", + ]); + }); + it("reuses one featured catalog lookup but recomputes defaults across onboarding retries", () => { let probeCount = 0; const loadOptions = createNvidiaFeaturedModelPromptOptionsLoader({ diff --git a/src/lib/inference/nvidia-featured-models.ts b/src/lib/inference/nvidia-featured-models.ts index 580ef43ece8..76a0d9945e7 100644 --- a/src/lib/inference/nvidia-featured-models.ts +++ b/src/lib/inference/nvidia-featured-models.ts @@ -18,6 +18,7 @@ export const NVIDIA_FEATURED_MODELS_URL = const RETIRED_NVIDIA_FEATURED_MODEL_IDS = new Set([ "z-ai/glm-5.1", // Retired from NVIDIA Endpoints in #6069. "moonshotai/kimi-k2.6", // Catalogs still list it after its backing route was removed. + "deepseek-ai/deepseek-v4-pro", // Retired from NVIDIA Endpoints on 2026-08-07; its route returns HTTP 410. ]); const MAX_NVIDIA_FEATURED_CATALOG_BYTES = 1024 * 1024; const MAX_NVIDIA_FEATURED_MODELS = 100;