diff --git a/src/modules/llms/server/openai/models/openai.models.ts b/src/modules/llms/server/openai/models/openai.models.ts
index 4cf46c865..f24433412 100644
--- a/src/modules/llms/server/openai/models/openai.models.ts
+++ b/src/modules/llms/server/openai/models/openai.models.ts
@@ -14,7 +14,7 @@ export const _knownOpenAIChatModels: ManualMappings = [
   {
     idPrefix: 'gpt-4o',
     label: 'GPT-4o',
-    description: 'High-intelligence flagship model for complex, multi-step tasks. GPT-4o is cheaper and faster than GPT-4 Turbo. Currently points to gpt-4o-2024-08-06.',
+    description: 'High-intelligence flagship model. Currently points to gpt-4o-2024-08-06.',
     symLink: 'gpt-4o-2024-08-06',
     hidden: true,
     // copied from symlinked
@@ -29,7 +29,7 @@ export const _knownOpenAIChatModels: ManualMappings = [
     isLatest: true,
     idPrefix: 'gpt-4o-2024-11-20',
     label: 'GPT-4o (2024-11-20)',
-    description: 'Latest gpt-4o snapshot from November 20th, 2024.',
+    description: 'Snapshot of gpt-4o from November 20th, 2024.',
     contextWindow: 128000,
     maxCompletionTokens: 16384,
     trainingDataCutoff: 'Oct 2023',
@@ -40,7 +40,7 @@ export const _knownOpenAIChatModels: ManualMappings = [
   {
     idPrefix: 'gpt-4o-2024-08-06',
     label: 'GPT-4o (2024-08-06)',
-    description: 'First snapshot that supports Structured Outputs. gpt-4o currently points to this version.',
+    description: 'Snapshot that supports Structured Outputs. gpt-4o currently points to this version.',
     contextWindow: 128000,
     maxCompletionTokens: 16384,
     trainingDataCutoff: 'Oct 2023',
@@ -64,7 +64,7 @@ export const _knownOpenAIChatModels: ManualMappings = [
   {
     idPrefix: 'chatgpt-4o-latest',
     label: 'ChatGPT-4o Latest',
-    description: 'The chatgpt-4o-latest model version continuously points to the version of GPT-4o used in ChatGPT, and is updated frequently, when there are significant changes.',
+    description: 'The chatgpt-4o-latest model version continuously points to the version of GPT-4o used in ChatGPT, and is updated frequently.',
     contextWindow: 128000,
     maxCompletionTokens: 16384,
     trainingDataCutoff: 'Oct 2023',
@@ -85,7 +85,7 @@ export const _knownOpenAIChatModels: ManualMappings = [
     maxCompletionTokens: 16384,
     trainingDataCutoff: 'Oct 2023',
     interfaces: [LLM_IF_OAI_NeedsAudio],
-    chatPrice: { input: 2.5, output: 10 /* TODO: AUDIO 100/200 */ },
+    chatPrice: { input: 2.5, output: 10 /* AUDIO PRICING UNSUPPORTED 100/200 */ },
     isPreview: true,
   },
   {
@@ -96,19 +96,19 @@ export const _knownOpenAIChatModels: ManualMappings = [
     maxCompletionTokens: 16384,
     trainingDataCutoff: 'Oct 2023',
     interfaces: [LLM_IF_OAI_NeedsAudio],
-    chatPrice: { input: 2.5, output: 10 /* TODO: AUDIO 40/80 */ },
+    chatPrice: { input: 2.5, output: 10 /* AUDIO PRICING UNSUPPORTED 100/200 */ },
     isPreview: true,
     hidden: true,
   },
   {
     idPrefix: 'gpt-4o-audio-preview-2024-10-01',
     label: 'GPT-4o Audio Preview (2024-10-01)',
-    description: 'Current snapshot for the Audio API model.',
+    description: 'Snapshot for the Audio API model.',
     contextWindow: 128000,
     maxCompletionTokens: 16384,
     trainingDataCutoff: 'Oct 2023',
     interfaces: [LLM_IF_OAI_NeedsAudio],
-    chatPrice: { input: 2.5, output: 10 /* TODO: AUDIO 100/200 */ },
+    chatPrice: { input: 2.5, output: 10 /* AUDIO PRICING UNSUPPORTED IS 100/200 */ },
     isPreview: true,
     hidden: true,
   },
@@ -117,7 +117,7 @@ export const _knownOpenAIChatModels: ManualMappings = [
   {
     idPrefix: 'gpt-4o-realtime-preview',
     label: 'GPT-4o Realtime Preview',
-    description: 'Preview release for the Realtime API. Points to the latest snapshot of GPT-4o Realtime Preview model: gpt-4o-realtime-preview-2024-12-17.',
+    description: 'Preview release for the Realtime API. Points to: gpt-4o-realtime-preview-2024-12-17.',
     symLink: 'gpt-4o-realtime-preview-2024-12-17',
     hidden: true,
     // copied from symlinked
@@ -125,30 +125,30 @@ export const _knownOpenAIChatModels: ManualMappings = [
     maxCompletionTokens: 4096,
     trainingDataCutoff: 'Oct 2023',
     interfaces: [LLM_IF_OAI_Realtime /* TBA FC, AUDIO */],
-    chatPrice: { input: 5, cache: { cType: 'oai-ac', read: 2.5 }, output: 20 /* TODO: AUDIO 100/200 */ },
+    chatPrice: { input: 5, cache: { cType: 'oai-ac', read: 2.5 }, output: 20 /* AUDIO PRICING UNSUPPORTED 100/200 */ },
     isPreview: true,
   },
   {
     idPrefix: 'gpt-4o-realtime-preview-2024-12-17',
     label: 'GPT-4o Realtime Preview (2024-12-17)',
-    description: 'Snapshot for the Realtime API model. Supports low-latency, multimodal experiences including speech-to-speech capabilities.',
+    description: 'Snapshot for the Realtime API model.',
     contextWindow: 128000,
     maxCompletionTokens: 4096,
     trainingDataCutoff: 'Oct 2023',
     interfaces: [LLM_IF_OAI_Realtime],
-    chatPrice: { input: 5, cache: { cType: 'oai-ac', read: 2.5 }, output: 20 },
+    chatPrice: { input: 5, cache: { cType: 'oai-ac', read: 2.5 }, output: 20 /* AUDIO PRICING UNSUPPORTED 100/200 */ },
     isPreview: true,
     hidden: true,
   },
   {
     idPrefix: 'gpt-4o-realtime-preview-2024-10-01',
     label: 'GPT-4o Realtime Preview (2024-10-01)',
-    description: 'Current snapshot for the Realtime API model. Supports low-latency, multimodal experiences including speech-to-speech capabilities.',
+    description: 'Snapshot for the Realtime API model.',
     contextWindow: 128000,
     maxCompletionTokens: 4096,
     trainingDataCutoff: 'Oct 2023',
     interfaces: [LLM_IF_OAI_Realtime /* TBA FC, AUDIO */],
-    chatPrice: { input: 5, cache: { cType: 'oai-ac', read: 2.5 }, output: 20 /* TODO: AUDIO 100/200 */ },
+    chatPrice: { input: 5, cache: { cType: 'oai-ac', read: 2.5 }, output: 20 /* AUDIO PRICING UNSUPPORTED 100/200 */ },
     isPreview: true,
     hidden: true,
   },
@@ -191,7 +191,7 @@ export const _knownOpenAIChatModels: ManualMappings = [
     maxCompletionTokens: 16384,
     trainingDataCutoff: 'Oct 2023',
     interfaces: [LLM_IF_OAI_NeedsAudio],
-    chatPrice: { input: 0.15, output: 0.6 /* TODO: AUDIO 10/20 */ },
+    chatPrice: { input: 0.15, output: 0.6 /* AUDIO PRICING UNSUPPORTED 10/20 */ },
     isPreview: true,
   },
   {
@@ -202,14 +202,14 @@ export const _knownOpenAIChatModels: ManualMappings = [
     maxCompletionTokens: 16384,
     trainingDataCutoff: 'Oct 2023',
     interfaces: [LLM_IF_OAI_NeedsAudio],
-    chatPrice: { input: 0.15, output: 0.6 /* TODO: AUDIO 10/20 */ },
+    chatPrice: { input: 0.15, output: 0.6 /* AUDIO PRICING UNSUPPORTED 10/20 */ },
     isPreview: true,
     hidden: true,
   },
   {
     idPrefix: 'gpt-4o-mini-realtime-preview',
     label: 'GPT-4o Mini Realtime Preview',
-    description: 'Preview release for the Realtime API. Points to the latest snapshot of GPT-4o Mini Realtime Preview model: gpt-4o-mini-realtime-preview-2024-12-17.',
+    description: 'Preview release for the Realtime API. Points to: gpt-4o-mini-realtime-preview-2024-12-17.',
     symLink: 'gpt-4o-mini-realtime-preview-2024-12-17',
     hidden: true,
     // copied from symlinked
@@ -223,7 +223,7 @@ export const _knownOpenAIChatModels: ManualMappings = [
   {
     idPrefix: 'gpt-4o-mini-realtime-preview-2024-12-17',
     label: 'GPT-4o Mini Realtime Preview (2024-12-17)',
-    description: 'Snapshot for the Realtime API model. Supports low-latency, multimodal experiences including speech-to-speech capabilities.',
+    description: 'Snapshot for the Realtime API model.',
     contextWindow: 128000,
     maxCompletionTokens: 4096,
     trainingDataCutoff: 'Oct 2023',