@@ -1270,7 +1270,7 @@ Métricas canônicas em 2026-08-24: **1.029 vídeos únicos** · **11.132.922 vi
Resilience Guide Circuit breakers, cooldowns, queue, anti-thundering herd, TLS spoofing Auto-Combo Engine 16-factor scoring, mode packs, self-healing Proxy Guide 3-level proxy system, 1proxy marketplace, registry CRUD
-
Free Tiers Consolidated directory: 38 documented recurring pools / 446 cataloged free-tier entries
+
Free Tiers Consolidated directory: 38 documented recurring pools / 437 cataloged free-tier entries Features Gallery Visual dashboard tour with screenshots Codebase Documentation Beginner-friendly codebase walkthrough
diff --git a/docs/diagrams/free-tier-budget.svg b/docs/diagrams/free-tier-budget.svg
index 51267b3ae2..72d1219cb2 100644
--- a/docs/diagrams/free-tier-budget.svg
+++ b/docs/diagrams/free-tier-budget.svg
@@ -1,4 +1,4 @@
-
+
Pool-deduplicated chart of the 20 recurring free-token pools with positive published budgets, plus signup credits and uncapped providers shown separately.
@@ -64,7 +64,7 @@
~1.51B
FREE TOKENS / MONTH · STEADY
up to ~2.13B in your first month — signup credits
- documented free tiers · 38 recurring pools · 446 catalog entries · one endpoint
+ documented free tiers · 38 recurring pools · 437 catalog entries · one endpoint
;
- executor.ensureThinkingBudget(body, "nvidia/nvidia-nemotron-nano-9b-v2");
+ executor.ensureThinkingBudget(body, "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning");
assert.equal(body.max_tokens, 4096);
});
diff --git a/tests/unit/free-models.test.ts b/tests/unit/free-models.test.ts
index e857db1bdf..0d4ae6a566 100644
--- a/tests/unit/free-models.test.ts
+++ b/tests/unit/free-models.test.ts
@@ -57,15 +57,12 @@ test("isFreeModel: a model id listed in the free catalog for that provider is fr
assert.equal(isFreeModel(sample.provider, { id: sample.modelId }), true);
});
-test("isFreeModel: NVIDIA GLM 5.2 is included in the reviewed trial catalog", () => {
- assert.equal(isFreeModel("nvidia", { id: "z-ai/glm-5.2" }), true);
+test("isFreeModel: NVIDIA GPT OSS 120B remains in the reviewed trial catalog", () => {
+ assert.equal(isFreeModel("nvidia", { id: "openai/gpt-oss-120b" }), true);
});
test("selectModelsForImport: passthrough when importFreeOnly is false", () => {
- const models = [
- { id: "a:free" },
- { id: "b", pricing: { prompt: "0.01", completion: "0.02" } },
- ];
+ const models = [{ id: "a:free" }, { id: "b", pricing: { prompt: "0.01", completion: "0.02" } }];
const result = selectModelsForImport("openrouter", models, false);
assert.equal(result.models.length, 2);
assert.equal(result.freeFilterEmpty, false);
@@ -130,8 +127,14 @@ test("sortModelsFreeFirst: deterministic (alphabetical) within each group, regar
],
{ isFree: (m) => m.isFree, key: (m) => m.id }
);
- assert.deepEqual(a.map((m) => m.id), ["a", "b", "c"]);
- assert.deepEqual(b.map((m) => m.id), ["a", "b", "c"]);
+ assert.deepEqual(
+ a.map((m) => m.id),
+ ["a", "b", "c"]
+ );
+ assert.deepEqual(
+ b.map((m) => m.id),
+ ["a", "b", "c"]
+ );
});
test("sortModelsFreeFirst: does not mutate the input array", () => {
@@ -141,5 +144,8 @@ test("sortModelsFreeFirst: does not mutate the input array", () => {
];
const before = items.map((m) => m.id);
sortModelsFreeFirst(items, { isFree: (m) => m.isFree, key: (m) => m.id });
- assert.deepEqual(items.map((m) => m.id), before);
+ assert.deepEqual(
+ items.map((m) => m.id),
+ before
+ );
});
diff --git a/tests/unit/guardrails/combo-vision-provider-id-12112.test.ts b/tests/unit/guardrails/combo-vision-provider-id-12112.test.ts
index 734e13e2fe..c4ddaf6fe9 100644
--- a/tests/unit/guardrails/combo-vision-provider-id-12112.test.ts
+++ b/tests/unit/guardrails/combo-vision-provider-id-12112.test.ts
@@ -3,29 +3,27 @@ import assert from "node:assert/strict";
process.env.DATA_DIR = `/tmp/omniroute-test-12112-${Date.now()}`;
-const { getComboVisionBridgeDecision } = await import(
- "../../../src/lib/guardrails/visionBridge.ts"
-);
+const { getComboVisionBridgeDecision } =
+ await import("../../../src/lib/guardrails/visionBridge.ts");
const combosDb = await import("../../../src/lib/db/combos.ts");
const core = await import("../../../src/lib/db/core.ts");
-const { isVisionIncompatibleTarget } = await import(
- "../../../open-sse/services/combo/comboStructure.ts"
-);
+const { isVisionIncompatibleTarget } =
+ await import("../../../open-sse/services/combo/comboStructure.ts");
import type { ResolvedComboTarget } from "../../../open-sse/services/combo/types.ts";
test.after(() => {
core.resetDbInstance();
});
-test("#12112: checkComboVision respects providerId for namespaced vision models (e.g. nvidia/nemotron-nano-12b-v2-vl)", async () => {
- // Model 'nvidia/nemotron-nano-12b-v2-vl' is declared with supportsVision: true in nvidia provider registry.
+test("#12112: checkComboVision respects providerId for namespaced vision models (e.g. nvidia/nemotron-3-nano-omni-30b-a3b-reasoning)", async () => {
+ // Model 'nvidia/nemotron-3-nano-omni-30b-a3b-reasoning' is declared with supportsVision: true in nvidia provider registry.
// It has a slash in model id and requires providerId="nvidia" to resolve capabilities.
await combosDb.createCombo({
name: "nvidia-vision-combo-12112",
models: [
{
providerId: "nvidia",
- model: "nvidia/nemotron-nano-12b-v2-vl",
+ model: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
weight: 1,
},
],
@@ -44,7 +42,7 @@ test("#12112: isVisionIncompatibleTarget passes providerId to resolve vision cap
kind: "model",
stepId: "step-1",
executionKey: "step-1",
- modelStr: "nvidia/nemotron-nano-12b-v2-vl",
+ modelStr: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
provider: "nvidia",
providerId: "nvidia",
connectionId: "conn-1",
@@ -64,6 +62,6 @@ test("#12112: isVisionIncompatibleTarget passes providerId to resolve vision cap
assert.equal(
incompatible,
false,
- "Target with providerId='nvidia' and model='nvidia/nemotron-nano-12b-v2-vl' must be vision-compatible"
+ "Target with providerId='nvidia' and model='nvidia/nemotron-3-nano-omni-30b-a3b-reasoning' must be vision-compatible"
);
});
diff --git a/tests/unit/model-capabilities-registry.test.ts b/tests/unit/model-capabilities-registry.test.ts
index 7bb82681db..98adbbf21a 100644
--- a/tests/unit/model-capabilities-registry.test.ts
+++ b/tests/unit/model-capabilities-registry.test.ts
@@ -203,7 +203,7 @@ test("GPT OSS and DeepSeek Reasoner models support tool calling", () => {
// GPT OSS models should not be blocked by the heuristic
assert.equal(modelCapabilities.supportsToolCalling("fake-provider/gpt-oss-120b"), true);
assert.equal(modelCapabilities.supportsToolCalling("gpt-oss-120b"), true);
- assert.equal(modelCapabilities.supportsToolCalling("nvidia/openai/gpt-oss-20b"), false); // in registry
+ assert.equal(modelCapabilities.supportsToolCalling("nvidia/openai/gpt-oss-120b"), false); // in registry
// DeepSeek Reasoner supports tool calling
assert.equal(modelCapabilities.supportsToolCalling("deepseek-reasoner"), true);
diff --git a/tests/unit/nvidia-410-model-scope.test.ts b/tests/unit/nvidia-410-model-scope.test.ts
index 0d72fe1345..9865e1f5f8 100644
--- a/tests/unit/nvidia-410-model-scope.test.ts
+++ b/tests/unit/nvidia-410-model-scope.test.ts
@@ -15,7 +15,7 @@ const auth = await import("../../src/sse/services/auth.ts");
const fallback = await import("../../open-sse/services/accountFallback.ts");
const DEAD_MODEL = "deepseek-ai/deepseek-v4-pro";
-const HEALTHY_MODEL = "z-ai/glm-5.2";
+const HEALTHY_MODEL = "nvidia/nemotron-3.5-lightning-30b-a3b";
const GONE_BODY = JSON.stringify({
type: "about:blank",
diff --git a/tests/unit/nvidia-eol-catalog.test.ts b/tests/unit/nvidia-eol-catalog.test.ts
index ea8708d19e..f5319d08e0 100644
--- a/tests/unit/nvidia-eol-catalog.test.ts
+++ b/tests/unit/nvidia-eol-catalog.test.ts
@@ -13,20 +13,15 @@ const documentedFreeIds = new Set(
const reviewedIds = new Set(reviewedLiveIds);
-test("NVIDIA registry excludes retired DeepSeek V4 models", () => {
- assert.ok(
- !registryIds.has("deepseek-ai/deepseek-v4-pro"),
- "retired deepseek-ai/deepseek-v4-pro must not be advertised"
- );
-
- assert.ok(
- !registryIds.has("deepseek-ai/deepseek-v4-flash"),
- "retired deepseek-ai/deepseek-v4-flash must not be advertised"
- );
-});
-
-test("NVIDIA static lifecycle metadata excludes known EOL models", () => {
- for (const modelId of ["z-ai/glm-5.1", "deepseek-ai/deepseek-v4-pro"]) {
+test("NVIDIA static catalog metadata excludes superseded model ids", () => {
+ for (const modelId of [
+ "z-ai/glm-5.1",
+ "z-ai/glm-5.2",
+ "deepseek-ai/deepseek-v4-pro",
+ "deepseek-ai/deepseek-v4-flash",
+ "minimaxai/minimax-m2.7",
+ ]) {
+ assert.ok(!registryIds.has(modelId), `${modelId} must not remain in the NVIDIA registry`);
assert.ok(
!reviewedIds.has(modelId),
`${modelId} must not remain in the reviewed NVIDIA hosted-model snapshot`
@@ -39,16 +34,9 @@ test("NVIDIA static lifecycle metadata excludes known EOL models", () => {
}
});
-test("NVIDIA cleanup preserves the healthy GLM replacement", () => {
- assert.ok(registryIds.has("z-ai/glm-5.2"), "z-ai/glm-5.2 must remain in the NVIDIA registry");
-
- assert.ok(
- reviewedIds.has("z-ai/glm-5.2"),
- "z-ai/glm-5.2 must remain in the reviewed NVIDIA hosted-model snapshot"
- );
-
- assert.ok(
- documentedFreeIds.has("z-ai/glm-5.2"),
- "z-ai/glm-5.2 must remain in the NVIDIA free-model catalog"
- );
+test("NVIDIA reviewed snapshot matches the registry and trial entries remain valid", () => {
+ assert.deepEqual([...reviewedIds], [...registryIds]);
+ for (const modelId of documentedFreeIds) {
+ assert.ok(registryIds.has(modelId), `${modelId} must exist in the NVIDIA hosted catalog`);
+ }
});
diff --git a/tests/unit/nvidia-minimax-m3-removed-3329.test.ts b/tests/unit/nvidia-minimax-m3-removed-3329.test.ts
index 77e0ce4822..f0c8b6d502 100644
--- a/tests/unit/nvidia-minimax-m3-removed-3329.test.ts
+++ b/tests/unit/nvidia-minimax-m3-removed-3329.test.ts
@@ -4,16 +4,16 @@ import assert from "node:assert/strict";
const { getRegistryEntry } = await import("../../open-sse/config/providerRegistry.ts");
// #3329: `minimaxai/minimax-m3` was registered in the nvidia (NVIDIA NIM) tier,
-// but NVIDIA NIM does not host it — every request returns `404 page not found`,
-// while sibling models on the same provider (e.g. `minimaxai/minimax-m2.7`)
-// work. Advertising a model that 404s is a catalog bug; it is removed from the
-// nvidia tier until NVIDIA actually serves it. It remains on the tiers that do
-// (minimax / minimax-cn / opencode / etc.).
+// but NVIDIA NIM does not host it — every request returns `404 page not found`.
+// Advertising a model that 404s is a catalog bug; it stays absent from the
+// NVIDIA tier while remaining available from providers that actually serve it.
test("nvidia tier does not advertise minimaxai/minimax-m3 (404 upstream) (#3329)", () => {
const nvidia = getRegistryEntry("nvidia");
assert.ok(nvidia, "nvidia registry entry must exist");
const ids = (nvidia.models ?? []).map((m) => m.id);
assert.ok(!ids.includes("minimaxai/minimax-m3"), "minimaxai/minimax-m3 must not be in nvidia");
- // sanity: the working sibling stays listed
- assert.ok(ids.includes("minimaxai/minimax-m2.7"), "minimaxai/minimax-m2.7 stays available");
+ assert.ok(
+ !ids.includes("minimaxai/minimax-m2.7"),
+ "removed minimaxai/minimax-m2.7 must stay out"
+ );
});
diff --git a/tests/unit/nvidia-nim-catalog-expansion-2373.test.ts b/tests/unit/nvidia-nim-catalog-expansion-2373.test.ts
deleted file mode 100644
index 32d14a8a00..0000000000
--- a/tests/unit/nvidia-nim-catalog-expansion-2373.test.ts
+++ /dev/null
@@ -1,81 +0,0 @@
-import test from "node:test";
-import assert from "node:assert/strict";
-
-import { nvidiaProvider } from "../../open-sse/config/providers/registry/nvidia/index.ts";
-
-// Port of decolua/9router#2373 ("fix(nvidia): expand NIM chat model catalog"). Upstream's
-// PR also added a per-model `thinkingFormat`/`kind` capability shape in a legacy
-// open-sse/providers/capabilities.js file that has no equivalent in OmniRoute — reasoning
-// translation here is per-PROVIDER (open-sse/translator/paramSupport.ts,
-// executors/default.ts, both gated on `this.provider === "nvidia"`), not per-model, so
-// only the catalog (RegistryModel.supportsReasoning/supportsVision) needed porting.
-// Embedding/ASR/TTS entries from the same upstream PR are already covered by
-// open-sse/config/embeddingRegistry.ts and audioRegistry.ts, so they are not duplicated
-// here. `minimaxai/minimax-m3` is intentionally excluded — see the #3329 guard
-// (nvidia-minimax-m3-removed-3329.test.ts).
-const modelIds = new Set(nvidiaProvider.models.map((m) => m.id));
-
-test("#2373: NVIDIA NIM registry gains the newly-observed chat-completions models", () => {
- for (const id of [
- "abacusai/dracarys-llama-3.1-70b-instruct",
- "google/gemma-2-2b-it",
- "google/gemma-3n-e2b-it",
- "meta/llama-3.1-8b-instruct",
- "meta/llama-3.2-11b-vision-instruct",
- "meta/llama-4-maverick-17b-128e-instruct",
- "meta/llama-guard-4-12b",
- "mistralai/ministral-14b-instruct-2512",
- "mistralai/mistral-medium-3.5-128b",
- "mistralai/mistral-nemotron",
- "mistralai/mixtral-8x7b-instruct-v0.1",
- "nvidia/ising-calibration-1-35b-a3b",
- "nvidia/llama-3.1-nemoguard-8b-content-safety",
- "nvidia/llama-3.3-nemotron-super-49b-v1.5",
- "nvidia/nemotron-3-nano-30b-a3b",
- "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
- "nvidia/nemotron-nano-12b-v2-vl",
- "nvidia/nvidia-nemotron-nano-9b-v2",
- "qwen/qwen3-next-80b-a3b-instruct",
- "sarvamai/sarvam-m",
- "stockmark/stockmark-2-100b-instruct",
- "upstage/solar-10.7b-instruct",
- ]) {
- assert.ok(modelIds.has(id), `expected nvidia registry to include ${id}`);
- }
-});
-
-test("#2373: reasoning-capable NVIDIA-hosted models are flagged supportsReasoning", () => {
- const reasoningIds = [
- "nvidia/ising-calibration-1-35b-a3b",
- "nvidia/nemotron-3-nano-30b-a3b",
- "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
- "nvidia/nemotron-nano-12b-v2-vl",
- "nvidia/nvidia-nemotron-nano-9b-v2",
- "qwen/qwen3-next-80b-a3b-instruct",
- ];
- for (const id of reasoningIds) {
- const model = nvidiaProvider.models.find((m) => m.id === id);
- assert.ok(model, `model ${id} must exist`);
- assert.equal(model?.supportsReasoning, true, `${id} must be supportsReasoning: true`);
- }
-});
-
-test("#2373/#3329: minimaxai/minimax-m3 stays excluded from the nvidia tier", () => {
- assert.ok(
- !modelIds.has("minimaxai/minimax-m3"),
- "minimaxai/minimax-m3 must not be re-added to the nvidia registry (404 upstream, #3329)"
- );
- // sanity: the working sibling stays listed
- assert.ok(modelIds.has("minimaxai/minimax-m2.7"), "minimaxai/minimax-m2.7 stays available");
-});
-
-test("#2373: non-chat model kinds (NER/diffusion) from the upstream PR are not ported into the chat registry", () => {
- assert.ok(
- !modelIds.has("nvidia/gliner-pii"),
- "nvidia/gliner-pii is an NER/PII tagger, not a chat-completions model"
- );
- assert.ok(
- !modelIds.has("google/diffusiongemma-26b-a4b-it"),
- "google/diffusiongemma-26b-a4b-it is a diffusion model, not a chat-completions model"
- );
-});
diff --git a/tests/unit/nvidia-nim-registry-6108.test.ts b/tests/unit/nvidia-nim-registry-6108.test.ts
index b9c12d9992..702747656d 100644
--- a/tests/unit/nvidia-nim-registry-6108.test.ts
+++ b/tests/unit/nvidia-nim-registry-6108.test.ts
@@ -3,21 +3,45 @@ import assert from "node:assert/strict";
import { nvidiaProvider } from "../../open-sse/config/providers/registry/nvidia/index.ts";
-// Regression guard for #6108: the static NVIDIA NIM model registry had gone
-// stale — z-ai/glm-5.1 was EOL'd (410) 2026-07-02, while glm-5.2 and
-// nvidia/nemotron-3-ultra-550b-a55b were absent. minimaxai/minimax-m3 stays
-// excluded per the #3329 guard (nvidia-minimax-m3-removed-3329.test.ts) — the
-// single 200 probe in #6108 wasn't reproducible enough to override it.
-const modelIds = new Set(nvidiaProvider.models.map((m) => m.id));
+const EXPECTED_MODEL_IDS = [
+ "moonshotai/kimi-k3",
+ "deepseek-ai/deepseek-v4-pro-0813",
+ "deepseek-ai/deepseek-v4-flash-0731",
+ "meta/muse-glimmer-30b",
+ "poolside/laguna-xs-2.1",
+ "google/gemma-4-31b-it",
+ "google/diffusiongemma-26b-a4b-it",
+ "nvidia/nemotron-3-ultra-550b-a55b",
+ "nvidia/nemotron-3-super-120b-a12b",
+ "nvidia/nemotron-3.5-lightning-30b-a3b",
+ "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
+ "openai/gpt-oss-120b",
+] as const;
-test("#6108: NVIDIA NIM registry contains the refreshed live models", () => {
- assert.ok(modelIds.has("z-ai/glm-5.2"), "z-ai/glm-5.2 must be present");
- assert.ok(
- modelIds.has("nvidia/nemotron-3-ultra-550b-a55b"),
- "nvidia/nemotron-3-ultra-550b-a55b must be present"
+test("NVIDIA NIM registry exactly matches the current hosted-model catalog", () => {
+ assert.deepEqual(
+ nvidiaProvider.models.map((model) => model.id),
+ EXPECTED_MODEL_IDS
);
});
-test("#6108: NVIDIA NIM registry no longer lists EOL z-ai/glm-5.1", () => {
- assert.ok(!modelIds.has("z-ai/glm-5.1"), "EOL z-ai/glm-5.1 must be removed");
+test("NVIDIA NIM registry preserves known model capabilities", () => {
+ const byId = new Map(nvidiaProvider.models.map((model) => [model.id, model]));
+
+ for (const id of [
+ "deepseek-ai/deepseek-v4-pro-0813",
+ "deepseek-ai/deepseek-v4-flash-0731",
+ "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
+ ]) {
+ assert.equal(byId.get(id)?.supportsReasoning, true, `${id} must support reasoning`);
+ }
+
+ const omni = byId.get("nvidia/nemotron-3-nano-omni-30b-a3b-reasoning");
+ assert.equal(omni?.supportsVision, true, "Nemotron 3 Nano Omni must support vision");
+
+ assert.equal(
+ byId.get("openai/gpt-oss-120b")?.toolCalling,
+ false,
+ "openai/gpt-oss-120b must keep tool calling disabled"
+ );
});
diff --git a/tests/unit/nvidia-nim-validator.test.ts b/tests/unit/nvidia-nim-validator.test.ts
index f6f82e44f6..b6c2c5518d 100644
--- a/tests/unit/nvidia-nim-validator.test.ts
+++ b/tests/unit/nvidia-nim-validator.test.ts
@@ -135,7 +135,7 @@ test("nvidia specialty validator falls back to stable chat validation model", as
calls.some((u) => u.endsWith("/chat/completions")),
`should fall back to /chat/completions, called: ${JSON.stringify(calls)}`
);
- assert.equal(payload?.model, "meta/llama-3.1-8b-instruct");
+ assert.equal(payload?.model, "nvidia/nemotron-3.5-lightning-30b-a3b");
}
);
});
diff --git a/tests/unit/nvidia-passthrough-models-6773.test.ts b/tests/unit/nvidia-passthrough-models-6773.test.ts
index 915b541413..9275367845 100644
--- a/tests/unit/nvidia-passthrough-models-6773.test.ts
+++ b/tests/unit/nvidia-passthrough-models-6773.test.ts
@@ -2,8 +2,8 @@
* Regression test for #6773 — NVIDIA NIM models listed available:true but 404 at router.
*
* Root cause: the `nvidia` provider registry entry multiplexes many distinct
- * third-party vendor models (z-ai/, minimaxai/, deepseek-ai/, qwen/,
- * mistralai/, stepfun-ai/, moonshotai/, openai/, nvidia/) behind ONE base URL
+ * third-party vendor models (moonshotai/, deepseek-ai/, nvidia/, meta/,
+ * poolside/, google/, openai/) behind ONE base URL
* and ONE API key connection — architecturally identical to `modelscope`,
* `synthetic`, and `kilo-gateway`, which all set `passthroughModels: true` so
* that a single model's 404/429 stays scoped to that model instead of cooling
@@ -24,8 +24,8 @@ test("#6773: nvidia registry entry sets passthroughModels", () => {
entry?.passthroughModels,
true,
"nvidia multiplexes many third-party vendor models behind one connection " +
- "(z-ai/, minimaxai/, deepseek-ai/, qwen/, mistralai/, stepfun-ai/, " +
- "moonshotai/, openai/, nvidia/) — it should set passthroughModels: true " +
+ "(moonshotai/, deepseek-ai/, nvidia/, meta/, poolside/, google/, " +
+ "openai/) — it should set passthroughModels: true " +
"like modelscope/synthetic/kilo-gateway, so a single stale model 404 " +
"does not cool down the whole connection for all other models"
);
@@ -33,7 +33,7 @@ test("#6773: nvidia registry entry sets passthroughModels", () => {
test("#6773: hasPerModelQuota('nvidia') is true, so a 404 on one nvidia model is model-scoped", () => {
assert.equal(
- accountFallback.hasPerModelQuota("nvidia", "z-ai/glm-5.2"),
+ accountFallback.hasPerModelQuota("nvidia", "nvidia/nemotron-3.5-lightning-30b-a3b"),
true,
"expected nvidia to use per-model lockout (like gemini/github/codex/compatible " +
"providers) so a 404 on one model doesn't cool down the other nvidia models"
@@ -50,7 +50,7 @@ test("#6773: checkFallbackError + lockModelIfPerModelQuota scope a single-model
404,
"Not Found",
0,
- "z-ai/glm-5.2",
+ "nvidia/nemotron-3.5-lightning-30b-a3b",
"nvidia",
null,
null,
@@ -66,7 +66,7 @@ test("#6773: checkFallbackError + lockModelIfPerModelQuota scope a single-model
const locked = accountFallback.lockModelIfPerModelQuota(
"nvidia",
"conn-6773",
- "z-ai/glm-5.2",
+ "nvidia/nemotron-3.5-lightning-30b-a3b",
"unknown",
result.cooldownMs ?? 30_000
);
diff --git a/tests/unit/nvidia-validation-model-3116.test.ts b/tests/unit/nvidia-validation-model-3116.test.ts
index 1d52f68059..da7e541fd2 100644
--- a/tests/unit/nvidia-validation-model-3116.test.ts
+++ b/tests/unit/nvidia-validation-model-3116.test.ts
@@ -2,7 +2,7 @@
* #3116 — NVIDIA key validation probed the first catalog model (`z-ai/glm-5.1`), which
* requires the "Public API Endpoints" account permission and can hang/be DEGRADED,
* making a *valid* key fail with a misleading "Upstream Error". The probe now defaults to
- * the universally-available `meta/llama-3.1-8b-instruct`, with a per-connection override.
+ * a lightweight model from the current hosted catalog, with a per-connection override.
*/
import test from "node:test";
import assert from "node:assert/strict";
@@ -12,10 +12,10 @@ import {
resolveNvidiaValidationModel,
} from "../../src/lib/providers/nvidiaValidationModel.ts";
-test("defaults to a stable, permission-free NVIDIA model (not the gated glm-5.1)", () => {
- assert.equal(NVIDIA_DEFAULT_VALIDATION_MODEL, "meta/llama-3.1-8b-instruct");
- assert.equal(resolveNvidiaValidationModel(), "meta/llama-3.1-8b-instruct");
- assert.equal(resolveNvidiaValidationModel({}), "meta/llama-3.1-8b-instruct");
+test("defaults to a lightweight model in the current NVIDIA catalog", () => {
+ assert.equal(NVIDIA_DEFAULT_VALIDATION_MODEL, "nvidia/nemotron-3.5-lightning-30b-a3b");
+ assert.equal(resolveNvidiaValidationModel(), "nvidia/nemotron-3.5-lightning-30b-a3b");
+ assert.equal(resolveNvidiaValidationModel({}), "nvidia/nemotron-3.5-lightning-30b-a3b");
assert.notEqual(resolveNvidiaValidationModel(undefined), "z-ai/glm-5.1");
});
@@ -25,5 +25,8 @@ test("honors a per-connection validationModelId override", () => {
"nvidia/llama-3.3-nemotron-super-49b"
);
// blank/whitespace override falls back to the default
- assert.equal(resolveNvidiaValidationModel({ validationModelId: " " }), NVIDIA_DEFAULT_VALIDATION_MODEL);
+ assert.equal(
+ resolveNvidiaValidationModel({ validationModelId: " " }),
+ NVIDIA_DEFAULT_VALIDATION_MODEL
+ );
});
diff --git a/tests/unit/opencode-go-effort-aliases-8353.test.ts b/tests/unit/opencode-go-effort-aliases-8353.test.ts
index 762de5fcd2..c743623f93 100644
--- a/tests/unit/opencode-go-effort-aliases-8353.test.ts
+++ b/tests/unit/opencode-go-effort-aliases-8353.test.ts
@@ -283,12 +283,3 @@ test("#10788 registry base rows declare the same tiers EFFORT_TIERS parses", ()
}
}
});
-
-test("#10788 nvidia z-ai/glm-5.2 declares reasoning with an empty tier list (binary switch)", () => {
- const entry = REGISTRY["nvidia"];
- assert.ok(entry?.models, "nvidia must expose models");
- const row = entry.models.find((m) => m.id === "z-ai/glm-5.2");
- assert.ok(row, "nvidia z-ai/glm-5.2 must exist");
- assert.equal(row.supportsReasoning, true);
- assert.deepEqual(row.supportedThinkingEfforts, []);
-});
+