max token is now dynamically handle for each model

app/lib/.server/llm/constants.ts

@@ -1,5 +1,5 @@
 // see https://docs.anthropic.com/en/docs/about-claude/models
-export const MAX_TOKENS = 4096;
+export const MAX_TOKENS = 8000;
 
 // limits the number of model responses that can be returned in a single request
 export const MAX_RESPONSE_SEGMENTS = 2;

app/lib/.server/llm/stream-text.ts

@@ -41,10 +41,9 @@ function extractPropertiesFromMessage(message: Message): { model: string; provid
 
   return { model, provider, content: cleanedContent };
 }
-
 export function streamText(
-  messages: Messages, 
-  env: Env, 
+  messages: Messages,
+  env: Env,
   options?: StreamingOptions,
   apiKeys?: Record<string, string>
 ) {
@@ -64,13 +63,21 @@ export function streamText(
       return { ...message, content };
     }
 
-    return message; // No changes for non-user messages
+    return message; 
   });
 
+  const modelDetails = MODEL_LIST.find((m) => m.name === currentModel);
+
+  const dynamicMaxTokens =
+    modelDetails && modelDetails.maxTokenAllowed
+      ? Math.min(MAX_TOKENS, modelDetails.maxTokenAllowed)
+      : MAX_TOKENS;
+  console.log(dynamicMaxTokens)
+
   return _streamText({
     model: getModel(currentProvider, currentModel, env, apiKeys),
     system: getSystemPrompt(),
-    maxTokens: MAX_TOKENS,
+    maxTokens: dynamicMaxTokens,
     messages: convertToCoreMessages(processedMessages),
     ...options,
   });

app/utils/constants.ts

@@ -12,12 +12,12 @@ const PROVIDER_LIST: ProviderInfo[] = [
   {
     name: 'Anthropic',
     staticModels: [
-      { name: 'claude-3-5-sonnet-latest', label: 'Claude 3.5 Sonnet (new)', provider: 'Anthropic' },
-      { name: 'claude-3-5-sonnet-20240620', label: 'Claude 3.5 Sonnet (old)', provider: 'Anthropic' },
-      { name: 'claude-3-5-haiku-latest', label: 'Claude 3.5 Haiku (new)', provider: 'Anthropic' },
-      { name: 'claude-3-opus-latest', label: 'Claude 3 Opus', provider: 'Anthropic' },
-      { name: 'claude-3-sonnet-20240229', label: 'Claude 3 Sonnet', provider: 'Anthropic' },
-      { name: 'claude-3-haiku-20240307', label: 'Claude 3 Haiku', provider: 'Anthropic' }
+      { name: 'claude-3-5-sonnet-latest', label: 'Claude 3.5 Sonnet (new)', provider: 'Anthropic', maxTokenAllowed: 8000 },
+      { name: 'claude-3-5-sonnet-20240620', label: 'Claude 3.5 Sonnet (old)', provider: 'Anthropic', maxTokenAllowed: 8000 },
+      { name: 'claude-3-5-haiku-latest', label: 'Claude 3.5 Haiku (new)', provider: 'Anthropic', maxTokenAllowed: 8000 },
+      { name: 'claude-3-opus-latest', label: 'Claude 3 Opus', provider: 'Anthropic', maxTokenAllowed: 8000 },
+      { name: 'claude-3-sonnet-20240229', label: 'Claude 3 Sonnet', provider: 'Anthropic', maxTokenAllowed: 8000 },
+      { name: 'claude-3-haiku-20240307', label: 'Claude 3 Haiku', provider: 'Anthropic', maxTokenAllowed: 8000 }
     ],
     getApiKeyLink: "https://console.anthropic.com/settings/keys",
   },
@@ -36,36 +36,37 @@ const PROVIDER_LIST: ProviderInfo[] = [
   {
     name: 'Cohere',
     staticModels: [
-      { name: 'command-r-plus-08-2024', label: 'Command R plus Latest', provider: 'Cohere' },
-      { name: 'command-r-08-2024', label: 'Command R Latest', provider: 'Cohere' },
-      { name: 'command-r-plus', label: 'Command R plus', provider: 'Cohere' },
-      { name: 'command-r', label: 'Command R', provider: 'Cohere' },
-      { name: 'command', label: 'Command', provider: 'Cohere' },
-      { name: 'command-nightly', label: 'Command Nightly', provider: 'Cohere' },
-      { name: 'command-light', label: 'Command Light', provider: 'Cohere' },
-      { name: 'command-light-nightly', label: 'Command Light Nightly', provider: 'Cohere' },
-      { name: 'c4ai-aya-expanse-8b', label: 'c4AI Aya Expanse 8b', provider: 'Cohere' },
-      { name: 'c4ai-aya-expanse-32b', label: 'c4AI Aya Expanse 32b', provider: 'Cohere' },
+      { name: 'command-r-plus-08-2024', label: 'Command R plus Latest', provider: 'Cohere', maxTokenAllowed: 4096 },
+      { name: 'command-r-08-2024', label: 'Command R Latest', provider: 'Cohere', maxTokenAllowed: 4096 },
+      { name: 'command-r-plus', label: 'Command R plus', provider: 'Cohere', maxTokenAllowed: 4096 },
+      { name: 'command-r', label: 'Command R', provider: 'Cohere', maxTokenAllowed: 4096 },
+      { name: 'command', label: 'Command', provider: 'Cohere', maxTokenAllowed: 4096 },
+      { name: 'command-nightly', label: 'Command Nightly', provider: 'Cohere', maxTokenAllowed: 4096 },
+      { name: 'command-light', label: 'Command Light', provider: 'Cohere', maxTokenAllowed: 4096 },
+      { name: 'command-light-nightly', label: 'Command Light Nightly', provider: 'Cohere', maxTokenAllowed: 4096 },
+      { name: 'c4ai-aya-expanse-8b', label: 'c4AI Aya Expanse 8b', provider: 'Cohere', maxTokenAllowed: 4096 },
+      { name: 'c4ai-aya-expanse-32b', label: 'c4AI Aya Expanse 32b', provider: 'Cohere', maxTokenAllowed: 4096 },
     ],
     getApiKeyLink: 'https://dashboard.cohere.com/api-keys'
   },
   {
     name: 'OpenRouter',
     staticModels: [
-      { name: 'gpt-4o', label: 'GPT-4o', provider: 'OpenAI' },
+      { name: 'gpt-4o', label: 'GPT-4o', provider: 'OpenAI', maxTokenAllowed: 8000 },
       {
         name: 'anthropic/claude-3.5-sonnet',
         label: 'Anthropic: Claude 3.5 Sonnet (OpenRouter)',
         provider: 'OpenRouter'
+        , maxTokenAllowed: 8000
       },
-      { name: 'anthropic/claude-3-haiku', label: 'Anthropic: Claude 3 Haiku (OpenRouter)', provider: 'OpenRouter' },
-      { name: 'deepseek/deepseek-coder', label: 'Deepseek-Coder V2 236B (OpenRouter)', provider: 'OpenRouter' },
-      { name: 'google/gemini-flash-1.5', label: 'Google Gemini Flash 1.5 (OpenRouter)', provider: 'OpenRouter' },
-      { name: 'google/gemini-pro-1.5', label: 'Google Gemini Pro 1.5 (OpenRouter)', provider: 'OpenRouter' },
-      { name: 'x-ai/grok-beta', label: 'xAI Grok Beta (OpenRouter)', provider: 'OpenRouter' },
-      { name: 'mistralai/mistral-nemo', label: 'OpenRouter Mistral Nemo (OpenRouter)', provider: 'OpenRouter' },
-      { name: 'qwen/qwen-110b-chat', label: 'OpenRouter Qwen 110b Chat (OpenRouter)', provider: 'OpenRouter' },
-      { name: 'cohere/command', label: 'Cohere Command (OpenRouter)', provider: 'OpenRouter' }
+      { name: 'anthropic/claude-3-haiku', label: 'Anthropic: Claude 3 Haiku (OpenRouter)', provider: 'OpenRouter', maxTokenAllowed: 8000 },
+      { name: 'deepseek/deepseek-coder', label: 'Deepseek-Coder V2 236B (OpenRouter)', provider: 'OpenRouter', maxTokenAllowed: 8000 },
+      { name: 'google/gemini-flash-1.5', label: 'Google Gemini Flash 1.5 (OpenRouter)', provider: 'OpenRouter', maxTokenAllowed: 8000 },
+      { name: 'google/gemini-pro-1.5', label: 'Google Gemini Pro 1.5 (OpenRouter)', provider: 'OpenRouter', maxTokenAllowed: 8000 },
+      { name: 'x-ai/grok-beta', label: 'xAI Grok Beta (OpenRouter)', provider: 'OpenRouter', maxTokenAllowed: 8000 },
+      { name: 'mistralai/mistral-nemo', label: 'OpenRouter Mistral Nemo (OpenRouter)', provider: 'OpenRouter', maxTokenAllowed: 8000 },
+      { name: 'qwen/qwen-110b-chat', label: 'OpenRouter Qwen 110b Chat (OpenRouter)', provider: 'OpenRouter', maxTokenAllowed: 8000 },
+      { name: 'cohere/command', label: 'Cohere Command (OpenRouter)', provider: 'OpenRouter', maxTokenAllowed: 4096 }
     ],
     getDynamicModels: getOpenRouterModels,
     getApiKeyLink: 'https://openrouter.ai/settings/keys',
@@ -73,70 +74,70 @@ const PROVIDER_LIST: ProviderInfo[] = [
   }, {
     name: 'Google',
     staticModels: [
-      { name: 'gemini-1.5-flash-latest', label: 'Gemini 1.5 Flash', provider: 'Google' },
-      { name: 'gemini-1.5-flash-002', label: 'Gemini 1.5 Flash-002', provider: 'Google' },
-      { name: 'gemini-1.5-flash-8b', label: 'Gemini 1.5 Flash-8b', provider: 'Google' },
-      { name: 'gemini-1.5-pro-latest', label: 'Gemini 1.5 Pro', provider: 'Google' },
-      { name: 'gemini-1.5-pro-002', label: 'Gemini 1.5 Pro-002', provider: 'Google' },
-      { name: 'gemini-exp-1114', label: 'Gemini exp-1114', provider: 'Google' }
+      { name: 'gemini-1.5-flash-latest', label: 'Gemini 1.5 Flash', provider: 'Google', maxTokenAllowed: 8192 },
+      { name: 'gemini-1.5-flash-002', label: 'Gemini 1.5 Flash-002', provider: 'Google', maxTokenAllowed: 8192 },
+      { name: 'gemini-1.5-flash-8b', label: 'Gemini 1.5 Flash-8b', provider: 'Google', maxTokenAllowed: 8192 },
+      { name: 'gemini-1.5-pro-latest', label: 'Gemini 1.5 Pro', provider: 'Google', maxTokenAllowed: 8192 },
+      { name: 'gemini-1.5-pro-002', label: 'Gemini 1.5 Pro-002', provider: 'Google', maxTokenAllowed: 8192 },
+      { name: 'gemini-exp-1114', label: 'Gemini exp-1114', provider: 'Google', maxTokenAllowed: 8192 }
     ],
     getApiKeyLink: 'https://aistudio.google.com/app/apikey'
   }, {
     name: 'Groq',
     staticModels: [
-      { name: 'llama-3.1-70b-versatile', label: 'Llama 3.1 70b (Groq)', provider: 'Groq' },
-      { name: 'llama-3.1-8b-instant', label: 'Llama 3.1 8b (Groq)', provider: 'Groq' },
-      { name: 'llama-3.2-11b-vision-preview', label: 'Llama 3.2 11b (Groq)', provider: 'Groq' },
-      { name: 'llama-3.2-3b-preview', label: 'Llama 3.2 3b (Groq)', provider: 'Groq' },
-      { name: 'llama-3.2-1b-preview', label: 'Llama 3.2 1b (Groq)', provider: 'Groq' }
+      { name: 'llama-3.1-70b-versatile', label: 'Llama 3.1 70b (Groq)', provider: 'Groq', maxTokenAllowed: 8000 },
+      { name: 'llama-3.1-8b-instant', label: 'Llama 3.1 8b (Groq)', provider: 'Groq', maxTokenAllowed: 8000 },
+      { name: 'llama-3.2-11b-vision-preview', label: 'Llama 3.2 11b (Groq)', provider: 'Groq', maxTokenAllowed: 8000 },
+      { name: 'llama-3.2-3b-preview', label: 'Llama 3.2 3b (Groq)', provider: 'Groq', maxTokenAllowed: 8000 },
+      { name: 'llama-3.2-1b-preview', label: 'Llama 3.2 1b (Groq)', provider: 'Groq', maxTokenAllowed: 8000 }
     ],
     getApiKeyLink: 'https://console.groq.com/keys'
   },
   {
     name: 'HuggingFace',
     staticModels: [
-      { name: 'Qwen/Qwen2.5-Coder-32B-Instruct', label: 'Qwen2.5-Coder-32B-Instruct (HuggingFace)', provider: 'HuggingFace' },
-      { name: '01-ai/Yi-1.5-34B-Chat', label: 'Yi-1.5-34B-Chat (HuggingFace)', provider: 'HuggingFace' },
-      { name: 'codellama/CodeLlama-34b-Instruct-hf', label: 'CodeLlama-34b-Instruct (HuggingFace)', provider: 'HuggingFace' },
-      { name: 'NousResearch/Hermes-3-Llama-3.1-8B', label: 'Hermes-3-Llama-3.1-8B (HuggingFace)', provider: 'HuggingFace' }
+      { name: 'Qwen/Qwen2.5-Coder-32B-Instruct', label: 'Qwen2.5-Coder-32B-Instruct (HuggingFace)', provider: 'HuggingFace', maxTokenAllowed: 8000 },
+      { name: '01-ai/Yi-1.5-34B-Chat', label: 'Yi-1.5-34B-Chat (HuggingFace)', provider: 'HuggingFace', maxTokenAllowed: 8000 },
+      { name: 'codellama/CodeLlama-34b-Instruct-hf', label: 'CodeLlama-34b-Instruct (HuggingFace)', provider: 'HuggingFace', maxTokenAllowed: 8000 },
+      { name: 'NousResearch/Hermes-3-Llama-3.1-8B', label: 'Hermes-3-Llama-3.1-8B (HuggingFace)', provider: 'HuggingFace', maxTokenAllowed: 8000 }
     ],
     getApiKeyLink: 'https://huggingface.co/settings/tokens'
   },
-  
+
   {
     name: 'OpenAI',
     staticModels: [
-      { name: 'gpt-4o-mini', label: 'GPT-4o Mini', provider: 'OpenAI' },
-      { name: 'gpt-4-turbo', label: 'GPT-4 Turbo', provider: 'OpenAI' },
-      { name: 'gpt-4', label: 'GPT-4', provider: 'OpenAI' },
-      { name: 'gpt-3.5-turbo', label: 'GPT-3.5 Turbo', provider: 'OpenAI' }
+      { name: 'gpt-4o-mini', label: 'GPT-4o Mini', provider: 'OpenAI', maxTokenAllowed: 8000 },
+      { name: 'gpt-4-turbo', label: 'GPT-4 Turbo', provider: 'OpenAI', maxTokenAllowed: 8000 },
+      { name: 'gpt-4', label: 'GPT-4', provider: 'OpenAI', maxTokenAllowed: 8000 },
+      { name: 'gpt-3.5-turbo', label: 'GPT-3.5 Turbo', provider: 'OpenAI', maxTokenAllowed: 8000 }
     ],
     getApiKeyLink: "https://platform.openai.com/api-keys",
   }, {
     name: 'xAI',
     staticModels: [
-      { name: 'grok-beta', label: 'xAI Grok Beta', provider: 'xAI' }
+      { name: 'grok-beta', label: 'xAI Grok Beta', provider: 'xAI', maxTokenAllowed: 8000 }
     ],
     getApiKeyLink: 'https://docs.x.ai/docs/quickstart#creating-an-api-key'
   }, {
     name: 'Deepseek',
     staticModels: [
-      { name: 'deepseek-coder', label: 'Deepseek-Coder', provider: 'Deepseek' },
-      { name: 'deepseek-chat', label: 'Deepseek-Chat', provider: 'Deepseek' }
+      { name: 'deepseek-coder', label: 'Deepseek-Coder', provider: 'Deepseek', maxTokenAllowed: 8000 },
+      { name: 'deepseek-chat', label: 'Deepseek-Chat', provider: 'Deepseek', maxTokenAllowed: 8000 }
     ],
     getApiKeyLink: 'https://platform.deepseek.com/api_keys'
   }, {
     name: 'Mistral',
     staticModels: [
-      { name: 'open-mistral-7b', label: 'Mistral 7B', provider: 'Mistral' },
-      { name: 'open-mixtral-8x7b', label: 'Mistral 8x7B', provider: 'Mistral' },
-      { name: 'open-mixtral-8x22b', label: 'Mistral 8x22B', provider: 'Mistral' },
-      { name: 'open-codestral-mamba', label: 'Codestral Mamba', provider: 'Mistral' },
-      { name: 'open-mistral-nemo', label: 'Mistral Nemo', provider: 'Mistral' },
-      { name: 'ministral-8b-latest', label: 'Mistral 8B', provider: 'Mistral' },
-      { name: 'mistral-small-latest', label: 'Mistral Small', provider: 'Mistral' },
-      { name: 'codestral-latest', label: 'Codestral', provider: 'Mistral' },
-      { name: 'mistral-large-latest', label: 'Mistral Large Latest', provider: 'Mistral' }
+      { name: 'open-mistral-7b', label: 'Mistral 7B', provider: 'Mistral', maxTokenAllowed: 8000 },
+      { name: 'open-mixtral-8x7b', label: 'Mistral 8x7B', provider: 'Mistral', maxTokenAllowed: 8000 },
+      { name: 'open-mixtral-8x22b', label: 'Mistral 8x22B', provider: 'Mistral', maxTokenAllowed: 8000 },
+      { name: 'open-codestral-mamba', label: 'Codestral Mamba', provider: 'Mistral', maxTokenAllowed: 8000 },
+      { name: 'open-mistral-nemo', label: 'Mistral Nemo', provider: 'Mistral', maxTokenAllowed: 8000 },
+      { name: 'ministral-8b-latest', label: 'Mistral 8B', provider: 'Mistral', maxTokenAllowed: 8000 },
+      { name: 'mistral-small-latest', label: 'Mistral Small', provider: 'Mistral', maxTokenAllowed: 8000 },
+      { name: 'codestral-latest', label: 'Codestral', provider: 'Mistral', maxTokenAllowed: 8000 },
+      { name: 'mistral-large-latest', label: 'Mistral Large Latest', provider: 'Mistral', maxTokenAllowed: 8000 }
     ],
     getApiKeyLink: 'https://console.mistral.ai/api-keys/'
   }, {
@@ -180,7 +181,8 @@ async function getOllamaModels(): Promise<ModelInfo[]> {
     return data.models.map((model: OllamaModel) => ({
       name: model.name,
       label: `${model.name} (${model.details.parameter_size})`,
-      provider: 'Ollama'
+      provider: 'Ollama',
+      maxTokenAllowed:8000,
     }));
   } catch (e) {
     return [];
@@ -233,8 +235,9 @@ async function getOpenRouterModels(): Promise<ModelInfo[]> {
     name: m.id,
     label: `${m.name} - in:$${(m.pricing.prompt * 1_000_000).toFixed(
       2)} out:$${(m.pricing.completion * 1_000_000).toFixed(2)} - context ${Math.floor(
-      m.context_length / 1000)}k`,
-    provider: 'OpenRouter'
+        m.context_length / 1000)}k`,
+    provider: 'OpenRouter',
+    maxTokenAllowed:8000,
   }));
 }
 

app/utils/types.ts

@@ -25,6 +25,7 @@ export interface ModelInfo {
   name: string;
   label: string;
   provider: string;
+  maxTokenAllowed: number;
 }
 
 export interface ProviderInfo {