1.16.7 Release

(cherry picked from commit 22b32d571d)

README.md

@@ -21,8 +21,12 @@ Or fork & run on Vercel
 
 [//]: # (big-AGI is an open book; see the **[ready-to-ship and future ideas](https://github.com/users/enricoros/projects/4/views/2)** in our open roadmap)
 
-### What's New in 1.16.1...1.16.3 · Jun 20, 2024 (patch releases)
+### What's New in 1.16.1...1.16.7 · Aug 7, 2024 (patch releases)
 
+- 1.16.7: OpenAI support for GPT-4o 2024-08-06
+- 1.16.6: Groq support for Llama 3.1 models
+- 1.16.5: GPT-4o Mini support
+- 1.16.4: 8192 tokens support for Claude 3.5 Sonnet
 - 1.16.3: Anthropic Claude 3.5 Sonnet model support
 - 1.16.2: Improve web downloads, as text, markdwon, or HTML
 - 1.16.2: Proper support for Gemini models

docs/changelog.md

@@ -10,8 +10,12 @@ by release.
 - milestone: [1.17.0](https://github.com/enricoros/big-agi/milestone/17)
 - work in progress: [big-AGI open roadmap](https://github.com/users/enricoros/projects/4/views/2), [help here](https://github.com/users/enricoros/projects/4/views/4)
 
-### What's New in 1.16.1...1.16.3 · Jun 20, 2024 (patch releases)
+### What's New in 1.16.1...1.16.7 · Aug 7, 2024 (patch releases)
 
+- 1.16.7: OpenAI support for GPT-4o 2024-08-06
+- 1.16.6: Groq support for Llama 3.1 models
+- 1.16.5: GPT-4o Mini support
+- 1.16.4: 8192 tokens support for Claude 3.5 Sonnet
 - 1.16.3: Anthropic Claude 3.5 Sonnet model support
 - 1.16.2: Improve web downloads, as text, markdwon, or HTML
 - 1.16.2: Proper support for Gemini models

src/apps/chat/components/message/ChatMessage.tsx

@@ -280,6 +280,7 @@ export function ChatMessage(props: {
   const wasEdited = !!messageUpdated;
 
   const textSel = selText ? selText : messageText;
+  // WARNING: if you get an issue here, you're downgrading from the new Big-AGI 2 data format to 1.x.
   const isSpecialT2I = textSel.startsWith('https://images.prodia.xyz/') || textSel.startsWith('/draw ') || textSel.startsWith('/imagine ') || textSel.startsWith('/img ');
   const couldDiagram = textSel.length >= 100 && !isSpecialT2I;
   const couldImagine = textSel.length >= 3 && !isSpecialT2I;

src/apps/news/news.data.tsx

@@ -61,7 +61,7 @@ export const NewsItems: NewsItem[] = [
     ]
   }*/
   {
-    versionCode: '1.16.3',
+    versionCode: '1.16.7',
     versionName: 'Crystal Clear',
     versionDate: new Date('2024-06-07T05:00:00Z'),
     // versionDate: new Date('2024-05-13T19:00:00Z'),
@@ -80,6 +80,10 @@ export const NewsItems: NewsItem[] = [
       { text: <>1.16.1: Support for <B>OpenAI</B> <B href='https://openai.com/index/hello-gpt-4o/'>GPT-4o</B></> },
       { text: <>1.16.2: Proper <B>Gemini</B> support, <B>HTML/Markdown</B> downloads, and latest <B>Mistral</B></> },
       { text: <>1.16.3: Support for <B href='https://www.anthropic.com/news/claude-3-5-sonnet'>Claude 3.5 Sonnet</B> (refresh your <B>Anthropic</B> models)</> },
+      { text: <>1.16.4: <B>8192 tokens</B> support for Claude 3.5 Sonnet</> },
+      { text: <>1.16.5: OpenAI <B>GPT-4o Mini</B> support</> },
+      { text: <>1.16.6: Groq <B>Llama 3.1</B> support</> },
+      { text: <>1.16.7: Gpt-4o  <B>2024-08-06</B></> },
     ],
   },
   {

src/apps/news/news.version.tsx

@@ -7,7 +7,7 @@ import { useAppStateStore } from '~/common/state/store-appstate';
 
 
 // update this variable every time you want to broadcast a new version to clients
-export const incrementalNewsVersion: number = 16.1; // not notifying for 16.3
+export const incrementalNewsVersion: number = 16.1; // not notifying for 1.16.7
 
 
 interface NewsState {

src/common/util/modelUtils.ts

@@ -8,8 +8,11 @@ export function prettyBaseModel(model: string | undefined): string {
   if (!model) return '';
   if (model.includes('gpt-4-vision-preview')) return 'GPT-4 Vision';
   if (model.includes('gpt-4-1106-preview')) return 'GPT-4 Turbo';
-  if (model.includes('gpt-4-32k')) return 'gpt-4-32k';
-  if (model.includes('gpt-4')) return 'gpt-4';
+  if (model.includes('gpt-4-32k')) return 'GPT-4-32k';
+  if (model.includes('gpt-4o-mini')) return 'GPT-4o Mini';
+  if (model.includes('gpt-4o')) return 'GPT-4o';
+  if (model.includes('gpt-4-turbo')) return 'GPT-4 Turbo';
+  if (model.includes('gpt-4')) return 'GPT-4';
   if (model.includes('gpt-3.5-turbo-instruct')) return '3.5 Turbo Instruct';
   if (model.includes('gpt-3.5-turbo-1106')) return '3.5 Turbo 16k';
   if (model.includes('gpt-3.5-turbo-16k')) return '3.5 Turbo 16k';

src/modules/llms/server/anthropic/anthropic.models.ts

@@ -27,7 +27,7 @@ export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: bo
     created: roundTime('2024-06-20 06:00'),
     description: 'The most intelligent Claude model',
     contextWindow: 200000, // Characters
-    maxCompletionTokens: 4096,
+    maxCompletionTokens: 8192,
     trainingDataCutoff: 'Apr 2024',
     interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
     pricing: { chatIn: 3, chatOut: 15 },

src/modules/llms/server/anthropic/anthropic.router.ts

@@ -17,7 +17,9 @@ import { hardcodedAnthropicModels } from './anthropic.models';
 // Default hosts
 const DEFAULT_API_VERSION_HEADERS = {
   'anthropic-version': '2023-06-01',
-  'anthropic-beta': 'messages-2023-12-15',
+  // Former Betas:
+  // - messages-2023-12-15: to use the Messages API
+  'anthropic-beta': 'max-tokens-3-5-sonnet-2024-07-15',
 };
 const DEFAULT_MAX_TOKENS = 2048;
 const DEFAULT_ANTHROPIC_HOST = 'api.anthropic.com';

src/modules/llms/server/openai/models.cba.ts

@@ -0,0 +1,84 @@
+// here for reference only - for future mapping of CBA scores to the model IDs
+// const modelIdToPrefixMap: { [key: string]: string } = {
+//   // Anthropic models
+//   'Claude 3.5 Sonnet': 'claude-3-5-sonnet-20240620',
+//   'Claude 3 Opus': 'claude-3-opus-20240229',
+//   'Claude 3 Sonnet': 'claude-3-sonnet-20240229',
+//   'Claude 3 Haiku': 'claude-3-haiku-20240307',
+//   'Claude-2.1': 'claude-2.1',
+//   'Claude-2.0': 'claude-2.0',
+//   'Claude-1': '', // No exact match
+//   'Claude-Instant-1': 'claude-instant-1.2', // Closest match
+//
+//   // Gemini models
+//   'Gemini-1.5-Pro-Exp-0801': 'models/gemini-1.5-pro-latest', // Closest match
+//   'Gemini Advanced App (2024-05-14)': '', // No exact match
+//   'Gemini-1.5-Pro-001': 'models/gemini-1.5-pro-001',
+//   'Gemini-1.5-Pro-Preview-0409': 'models/gemini-1.5-pro-latest', // Closest match
+//   'Gemini-1.5-Flash-001': 'models/gemini-1.5-flash-001',
+//   'Gemini App (2024-01-24)': '', // No exact match
+//   'Gemini-1.0-Pro-001': 'models/gemini-1.0-pro-001',
+//   'Gemini Pro': 'models/gemini-pro',
+//
+//   // OpenAI models (from the previous file)
+//   'GPT-4o-2024-05-13': 'gpt-4o-2024-05-13',
+//   'GPT-4o-mini-2024-07-18': 'gpt-4o-mini-2024-07-18',
+//   'GPT-4-Turbo-2024-04-09': 'gpt-4-turbo-2024-04-09',
+//   'GPT-4-1106-preview': 'gpt-4-1106-preview',
+//   'GPT-4-0125-preview': 'gpt-4-0125-preview',
+//   'GPT-4-0314': 'gpt-4-0314',
+//   'GPT-4-0613': 'gpt-4-0613',
+//   'GPT-3.5-Turbo-0613': 'gpt-3.5-turbo-0613',
+//   'GPT-3.5-Turbo-0314': 'gpt-3.5-turbo-0314',
+//   'GPT-3.5-Turbo-0125': 'gpt-3.5-turbo-0125',
+//
+//   // Mistral models (from the previous file)
+//   'Mistral-Large-2402': 'mistral-large-2402',
+//   'Mixtral-8x7b-Instruct-v0.1': 'mistralai/Mixtral-8x7B-Instruct-v0.1',
+//
+//   // Other models without matches
+//   'Gemini-1.5-Pro-Exp-0801': '',
+//   'Meta-Llama-3.1-405b-Instruct': '',
+//   'Gemini-1.5-Pro-001': '',
+//   'Meta-Llama-3.1-70b-Instruct': '',
+//   'Yi-Large-preview': '',
+//   'Deepseek-v2-API-0628': '',
+//   'Gemma-2-27b-it': '',
+//   'Yi-Large': '',
+//   'Nemotron-4-340B-Instruct': '',
+//   'GLM-4-0520': '',
+//   'Llama-3-70b-Instruct': '',
+//   'Reka-Core-20240501': '',
+//   'Command R+': '',
+//   'Gemma-2-9b-it': '',
+//   'Qwen2-72B-Instruct': '',
+//   'GLM-4-0116': '',
+//   'Qwen-Max-0428': '',
+//   'DeepSeek-Coder-V2-Instruct': '',
+//   'Reka-Flash-Preview-20240611': '',
+//   'Meta-Llama-3.1-8b-Instruct': '',
+//   'Qwen1.5-110B-Chat': '',
+//   'Yi-1.5-34B-Chat': '',
+//   'Reka-Flash-21B-online': '',
+//   'Llama-3-8b-Instruct': '',
+//   'Command R': '',
+//   'Reka-Flash-21B': '',
+//   'Qwen1.5-72B-Chat': '',
+//   'Mixtral-8x22b-Instruct-v0.1': '',
+//   'Zephyr-ORPO-141b-A35b-v0.1': '',
+//   'Qwen1.5-32B-Chat': '',
+//   'Mistral-Next': '',
+//   'Phi-3-Medium-4k-Instruct': '',
+//   'Starling-LM-7B-beta': '',
+//   'Yi-34B-Chat': '',
+//   'Qwen1.5-14B-Chat': '',
+//   'WizardLM-70B-v1.0': '',
+//   'Tulu-2-DPO-70B': '',
+//   'DBRX-Instruct-Preview': '',
+//   'Phi-3-Small-8k-Instruct': '',
+//   'Llama-2-70b-chat': '',
+//   'OpenChat-3.5-0106': '',
+//   'Vicuna-33B': '',
+//   'Snowflake Arctic Instruct': '',
+//   'Starling-LM-7B-alpha': '',
+// };

src/modules/llms/server/openai/models.data.ts

@@ -9,9 +9,37 @@ import { wireTogetherAIListOutputSchema } from './togetherai.wiretypes';
 
 
 // [Azure] / [OpenAI]
+// https://platform.openai.com/docs/models
 const _knownOpenAIChatModels: ManualMappings = [
 
-  // GPT-4o -> 2024-05-13
+  // GPT-4o mini
+  {
+    idPrefix: 'gpt-4o-mini-2024-07-18',
+    label: 'GPT-4o Mini (2024-07-18)',
+    description: 'Affordable model for fast, lightweight tasks. GPT-4o mini is cheaper and more capable than GPT-3.5 Turbo.',
+    contextWindow: 128000,
+    maxCompletionTokens: 16384,
+    trainingDataCutoff: 'Oct 2023',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
+    pricing: { chatIn: 0.15, chatOut: 0.60 },
+    benchmark: { cbaElo: 1277, cbaMmlu: 82.0 },
+  },
+  {
+    idPrefix: 'gpt-4o-mini',
+    label: 'GPT-4o mini',
+    description: 'Currently points to gpt-4o-mini-2024-07-18.',
+    symLink: 'gpt-4o-mini-2024-07-18',
+    hidden: true,
+    // copied from symlinked
+    contextWindow: 128000,
+    maxCompletionTokens: 16384,
+    trainingDataCutoff: 'Oct 2023',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
+    pricing: { chatIn: 0.15, chatOut: 0.60 },
+    benchmark: { cbaElo: 1277, cbaMmlu: 82.0 },
+  },
+
+  // GPT-4o -> 2024-05-13 (will be update to 2024-08-06 in the future (3 weeks notice))
   {
     idPrefix: 'gpt-4o',
     label: 'GPT-4o',
@@ -24,10 +52,21 @@ const _knownOpenAIChatModels: ManualMappings = [
     trainingDataCutoff: 'Oct 2023',
     interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
     pricing: { chatIn: 5, chatOut: 15 },
-    benchmark: { cbaElo: 1310 },
+    benchmark: { cbaElo: 1286 },
   },
   {
     isLatest: true,
+    idPrefix: 'gpt-4o-2024-08-06',
+    label: 'GPT-4o (2024-08-06)',
+    description: 'Latest snapshot that supports Structured Outputs',
+    contextWindow: 128000,
+    maxCompletionTokens: 16384,
+    trainingDataCutoff: 'Oct 2023',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
+    pricing: { chatIn: 2.5, chatOut: 10 },
+    benchmark: { cbaElo: 1286 + 1 },
+  },
+  {
     idPrefix: 'gpt-4o-2024-05-13',
     label: 'GPT-4o (2024-05-13)',
     description: 'Advanced, multimodal flagship model that’s cheaper and faster than GPT-4 Turbo.',
@@ -36,7 +75,8 @@ const _knownOpenAIChatModels: ManualMappings = [
     trainingDataCutoff: 'Oct 2023',
     interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
     pricing: { chatIn: 5, chatOut: 15 },
-    benchmark: { cbaElo: 1310 },
+    benchmark: { cbaElo: 1286 },
+    hidden: true,
   },
 
   // GPT4 Turbo with Vision -> 2024-04-09
@@ -52,7 +92,7 @@ const _knownOpenAIChatModels: ManualMappings = [
     trainingDataCutoff: 'Dec 2023',
     interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
     pricing: { chatIn: 10, chatOut: 30 },
-    benchmark: { cbaElo: 1261 },
+    benchmark: { cbaElo: 1257 },
   },
   {
     idPrefix: 'gpt-4-turbo-2024-04-09',
@@ -63,7 +103,7 @@ const _knownOpenAIChatModels: ManualMappings = [
     trainingDataCutoff: 'Dec 2023',
     interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
     pricing: { chatIn: 10, chatOut: 30 },
-    benchmark: { cbaElo: 1261 },
+    benchmark: { cbaElo: 1257 },
   },
 
   // GPT4 Turbo Previews
@@ -80,32 +120,30 @@ const _knownOpenAIChatModels: ManualMappings = [
     trainingDataCutoff: 'Dec 2023',
     interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
     pricing: { chatIn: 10, chatOut: 30 },
-    benchmark: { cbaElo: 1251 },
+    benchmark: { cbaElo: 1245 },
   },
   {
     idPrefix: 'gpt-4-0125-preview', // GPT-4 Turbo preview model
     label: 'GPT-4 Turbo (0125)',
-    description: 'GPT-4 Turbo preview model intended to reduce cases of "laziness" where the model doesn\'t complete a task. Returns a maximum of 4,096 output tokens.',
-    isPreview: true,
+    description: 'GPT-4 Turbo preview model intended to reduce cases of "laziness" where the model doesn\'t complete a task.',
     contextWindow: 128000,
     maxCompletionTokens: 4096,
     trainingDataCutoff: 'Dec 2023',
     interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
     pricing: { chatIn: 10, chatOut: 30 },
-    benchmark: { cbaElo: 1251 },
+    benchmark: { cbaElo: 1245 },
     hidden: true,
   },
   {
     idPrefix: 'gpt-4-1106-preview', // GPT-4 Turbo preview model
     label: 'GPT-4 Turbo (1106)',
-    description: 'GPT-4 Turbo preview model featuring improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Returns a maximum of 4,096 output tokens.',
-    isPreview: true,
+    description: 'GPT-4 Turbo preview model featuring improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more.',
     contextWindow: 128000,
     maxCompletionTokens: 4096,
     trainingDataCutoff: 'Apr 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
     pricing: { chatIn: 10, chatOut: 30 },
-    benchmark: { cbaElo: 1255 },
+    benchmark: { cbaElo: 1251 },
     hidden: true,
   },
 
@@ -182,7 +220,7 @@ const _knownOpenAIChatModels: ManualMappings = [
     trainingDataCutoff: 'Sep 2021',
     interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
     pricing: { chatIn: 30, chatOut: 60 },
-    benchmark: { cbaElo: 1164 },
+    benchmark: { cbaElo: 1161 },
   },
   {
     idPrefix: 'gpt-4-0314',
@@ -192,7 +230,7 @@ const _knownOpenAIChatModels: ManualMappings = [
     trainingDataCutoff: 'Sep 2021',
     interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
     pricing: { chatIn: 30, chatOut: 60 },
-    benchmark: { cbaElo: 1189 },
+    benchmark: { cbaElo: 1186 },
     hidden: true,
   },
   {
@@ -206,7 +244,8 @@ const _knownOpenAIChatModels: ManualMappings = [
     trainingDataCutoff: 'Sep 2021',
     interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
     pricing: { chatIn: 30, chatOut: 60 },
-    benchmark: { cbaElo: 1164 },
+    benchmark: { cbaElo: 1161 },
+    isLegacy: true,
   },
 
 
@@ -222,23 +261,22 @@ const _knownOpenAIChatModels: ManualMappings = [
     hidden: true,
   },
 
-
-  // 3.5-Turbo-16k's
+  // 3.5-Turbo's (16ks)
   {
     idPrefix: 'gpt-3.5-turbo-0125',
     label: '3.5-Turbo (0125)',
-    description: 'The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls. Returns a maximum of 4,096 output tokens.',
+    description: 'The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.',
     contextWindow: 16385,
     maxCompletionTokens: 4096,
     trainingDataCutoff: 'Sep 2021',
     interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
     pricing: { chatIn: 0.5, chatOut: 1.5 },
-    benchmark: { cbaElo: 1104 },
+    benchmark: { cbaElo: 1105 },
   },
   {
     idPrefix: 'gpt-3.5-turbo-1106',
     label: '3.5-Turbo (1106)',
-    description: 'The latest GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more.',
+    description: 'GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more.',
     contextWindow: 16385,
     maxCompletionTokens: 4096,
     trainingDataCutoff: 'Sep 2021',
@@ -250,7 +288,7 @@ const _knownOpenAIChatModels: ManualMappings = [
   {
     idPrefix: 'gpt-3.5-turbo',
     label: '3.5-Turbo',
-    description: 'Currently points to gpt-3.5-turbo-0125.',
+    description: 'Currently points to gpt-3.5-turbo-0125. As of July 2024, gpt-4o-mini should be used in place of gpt-3.5-turbo, as it is cheaper, more capable, multimodal, and just as fast.',
     symLink: 'gpt-3.5-turbo-0125',
     hidden: true,
     // copied
@@ -259,7 +297,7 @@ const _knownOpenAIChatModels: ManualMappings = [
     trainingDataCutoff: 'Sep 2021',
     interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
     pricing: { chatIn: 0.5, chatOut: 1.5 },
-    benchmark: { cbaElo: 1104 },
+    benchmark: { cbaElo: 1105 },
   },
 
 
@@ -859,41 +897,84 @@ export function perplexityAIModelSort(a: ModelDescriptionSchema, b: ModelDescrip
 const _knownGroqModels: ManualMappings = [
   {
     isLatest: true,
+    idPrefix: 'llama-3.1-405b-reasoning',
+    label: 'Llama 3.1 · 405B',
+    description: 'LLaMA 3.1 405B developed by Meta with a context window of 131,072 tokens. Supports tool use.',
+    contextWindow: 131072,
+    maxCompletionTokens: 8000,
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
+  },
+  {
+    isLatest: true,
+    idPrefix: 'llama-3.1-70b-versatile',
+    label: 'Llama 3.1 · 70B',
+    description: 'LLaMA 3.1 70B developed by Meta with a context window of 131,072 tokens. Supports tool use.',
+    contextWindow: 131072,
+    maxCompletionTokens: 8000,
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
+  },
+  {
+    isLatest: true,
+    idPrefix: 'llama-3.1-8b-instant',
+    label: 'Llama 3.1 · 8B',
+    description: 'LLaMA 3.1 8B developed by Meta with a context window of 131,072 tokens. Supports tool use.',
+    contextWindow: 131072,
+    maxCompletionTokens: 8000,
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
+  },
+  {
+    idPrefix: 'llama3-groq-70b-8192-tool-use-preview',
+    label: 'Llama 3 Groq · 70B Tool Use',
+    description: 'LLaMA 3 70B Tool Use developed by Groq with a context window of 8,192 tokens. Optimized for tool use.',
+    contextWindow: 8192,
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
+  },
+  {
+    idPrefix: 'llama3-groq-8b-8192-tool-use-preview',
+    label: 'Llama 3 Groq · 8B Tool Use',
+    description: 'LLaMA 3 8B Tool Use developed by Groq with a context window of 8,192 tokens. Optimized for tool use.',
+    contextWindow: 8192,
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
+  },
+  {
     idPrefix: 'llama3-70b-8192',
     label: 'Llama 3 · 70B',
-    description: 'LLaMA3 70b developed by Meta with a context window of 8,192 tokens.',
+    description: 'LLaMA3 70B developed by Meta with a context window of 8,192 tokens. Supports tool use.',
     contextWindow: 8192,
-    interfaces: [LLM_IF_OAI_Chat],
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
+    // isLegacy: true,
+    hidden: true,
   },
   {
-    // isLatest: true,
     idPrefix: 'llama3-8b-8192',
     label: 'Llama 3 · 8B',
-    description: 'LLaMA3 8b developed by Meta with a context window of 8,192 tokens.',
+    description: 'LLaMA3 8B developed by Meta with a context window of 8,192 tokens. Supports tool use.',
     contextWindow: 8192,
-    interfaces: [LLM_IF_OAI_Chat],
-  },
-  {
-    idPrefix: 'llama2-70b-4096',
-    label: 'Llama 2 · 70B',
-    description: 'LLaMA2 70b developed by Meta with a context window of 4,096 tokens.',
-    contextWindow: 4096,
-    interfaces: [LLM_IF_OAI_Chat],
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
+    // isLegacy: true,
     hidden: true,
   },
   {
     idPrefix: 'mixtral-8x7b-32768',
     label: 'Mixtral 8x7B',
-    description: 'Mixtral 8x7b developed by Mistral with a context window of 32,768 tokens.',
+    description: 'Mixtral 8x7B developed by Mistral with a context window of 32,768 tokens. Supports tool use.',
     contextWindow: 32768,
-    interfaces: [LLM_IF_OAI_Chat],
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
+  },
+  {
+    idPrefix: 'gemma2-9b-it',
+    label: 'Gemma 2 · 9B Instruct',
+    description: 'Gemma 2 9B developed by Google with a context window of 8,192 tokens. Supports tool use.',
+    contextWindow: 8192,
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
   },
   {
     idPrefix: 'gemma-7b-it',
     label: 'Gemma 1.1 · 7B Instruct',
-    description: 'Gemma 7b developed by Google with a context window of 8,192 tokens.',
+    description: 'Gemma 7B developed by Google with a context window of 8,192 tokens. Supports tool use.',
     contextWindow: 8192,
     interfaces: [LLM_IF_OAI_Chat],
+    hidden: true,
   },
 ];
 
@@ -910,6 +991,11 @@ export function groqModelToModelDescription(_model: unknown): ModelDescriptionSc
 }
 
 export function groqModelSortFn(a: ModelDescriptionSchema, b: ModelDescriptionSchema): number {
+  // sort hidden at the end
+  if (a.hidden && !b.hidden)
+    return 1;
+  if (!a.hidden && b.hidden)
+    return -1;
   // sort as per their order in the known models
   const aIndex = _knownGroqModels.findIndex(base => a.id.startsWith(base.idPrefix));
   const bIndex = _knownGroqModels.findIndex(base => b.id.startsWith(base.idPrefix));