diff --git a/pkg/llm/registry_gen.go b/pkg/llm/registry_gen.go
index 19a5c043a..2523ec629 100644
--- a/pkg/llm/registry_gen.go
+++ b/pkg/llm/registry_gen.go
@@ -14,21 +14,401 @@
 
 // Code generated by genmodels; DO NOT EDIT.
 // Source: https://openrouter.ai/api/v1/models
-// Generated: 2026-04-15T06:30:41Z
+// Generated: 2026-07-02T16:30:25Z
 
 package llm
 
 var generatedModels = map[string]ModelDefinition{
-	"anthropic/claude-opus-4.6-fast": {
-		Name:            "Anthropic: Claude Opus 4.6 (Fast)",
+	"anthropic/claude-sonnet-5": {
+		Name:            "Anthropic: Claude Sonnet 5",
 		ContextLength:   1000000,
 		MaxOutputTokens: 128000,
+		Supports: SupportedParameters{
+			Temperature:       false,
+			TopP:              false,
+			TopK:              false,
+			FrequencyPenalty:  false,
+			PresencePenalty:   false,
+			Stop:              true,
+			Seed:              false,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"google/gemini-3.1-flash-lite-image": {
+		Name:            "Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)",
+		ContextLength:   65536,
+		MaxOutputTokens: 66000,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
 			TopK:              false,
 			FrequencyPenalty:  false,
 			PresencePenalty:   false,
+			Stop:              false,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        false,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: false,
+			Reasoning:         true,
+		},
+	},
+	"google/gemini-3.1-flash-image": {
+		Name:            "Google: Nano Banana 2 (Gemini 3.1 Flash Image)",
+		ContextLength:   131072,
+		MaxOutputTokens: 32768,
+		Supports: SupportedParameters{
+			Temperature:       true,
+			TopP:              true,
+			TopK:              false,
+			FrequencyPenalty:  false,
+			PresencePenalty:   false,
+			Stop:              false,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        false,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"google/gemini-3-pro-image": {
+		Name:            "Google: Nano Banana Pro (Gemini 3 Pro Image)",
+		ContextLength:   65536,
+		MaxOutputTokens: 32768,
+		Supports: SupportedParameters{
+			Temperature:       true,
+			TopP:              true,
+			TopK:              false,
+			FrequencyPenalty:  false,
+			PresencePenalty:   false,
+			Stop:              true,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"anthropic/claude-fable-5": {
+		Name:            "Anthropic: Claude Fable 5",
+		ContextLength:   1000000,
+		MaxOutputTokens: 128000,
+		Supports: SupportedParameters{
+			Temperature:       false,
+			TopP:              false,
+			TopK:              false,
+			FrequencyPenalty:  false,
+			PresencePenalty:   false,
+			Stop:              true,
+			Seed:              false,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"anthropic/claude-opus-4.8-fast": {
+		Name:            "Anthropic: Claude Opus 4.8 (Fast)",
+		ContextLength:   1000000,
+		MaxOutputTokens: 128000,
+		Supports: SupportedParameters{
+			Temperature:       false,
+			TopP:              false,
+			TopK:              false,
+			FrequencyPenalty:  false,
+			PresencePenalty:   false,
+			Stop:              true,
+			Seed:              false,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"anthropic/claude-opus-4.8": {
+		Name:            "Anthropic: Claude Opus 4.8",
+		ContextLength:   1000000,
+		MaxOutputTokens: 128000,
+		Supports: SupportedParameters{
+			Temperature:       false,
+			TopP:              false,
+			TopK:              false,
+			FrequencyPenalty:  false,
+			PresencePenalty:   false,
+			Stop:              true,
+			Seed:              false,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"x-ai/grok-build-0.1": {
+		Name:            "xAI: Grok Build 0.1",
+		ContextLength:   256000,
+		MaxOutputTokens: 0,
+		Supports: SupportedParameters{
+			Temperature:       true,
+			TopP:              true,
+			TopK:              false,
+			FrequencyPenalty:  true,
+			PresencePenalty:   true,
+			Stop:              true,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"google/gemini-3.5-flash": {
+		Name:            "Google: Gemini 3.5 Flash",
+		ContextLength:   1048576,
+		MaxOutputTokens: 65536,
+		Supports: SupportedParameters{
+			Temperature:       true,
+			TopP:              true,
+			TopK:              false,
+			FrequencyPenalty:  false,
+			PresencePenalty:   false,
+			Stop:              true,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"anthropic/claude-opus-4.7-fast": {
+		Name:            "Anthropic: Claude Opus 4.7 (Fast)",
+		ContextLength:   1000000,
+		MaxOutputTokens: 128000,
+		Supports: SupportedParameters{
+			Temperature:       false,
+			TopP:              false,
+			TopK:              false,
+			FrequencyPenalty:  false,
+			PresencePenalty:   false,
+			Stop:              true,
+			Seed:              false,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"google/gemini-3.1-flash-lite": {
+		Name:            "Google: Gemini 3.1 Flash Lite",
+		ContextLength:   1048576,
+		MaxOutputTokens: 65536,
+		Supports: SupportedParameters{
+			Temperature:       true,
+			TopP:              true,
+			TopK:              false,
+			FrequencyPenalty:  false,
+			PresencePenalty:   false,
+			Stop:              true,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"openai/gpt-chat-latest": {
+		Name:            "OpenAI: GPT Chat Latest",
+		ContextLength:   400000,
+		MaxOutputTokens: 128000,
+		Supports: SupportedParameters{
+			Temperature:       false,
+			TopP:              false,
+			TopK:              false,
+			FrequencyPenalty:  true,
+			PresencePenalty:   true,
+			Stop:              true,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         false,
+		},
+	},
+	"x-ai/grok-4.3": {
+		Name:            "xAI: Grok 4.3",
+		ContextLength:   1000000,
+		MaxOutputTokens: 0,
+		Supports: SupportedParameters{
+			Temperature:       true,
+			TopP:              true,
+			TopK:              false,
+			FrequencyPenalty:  true,
+			PresencePenalty:   true,
+			Stop:              true,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"mistralai/mistral-medium-3-5": {
+		Name:            "Mistral: Mistral Medium 3.5",
+		ContextLength:   262144,
+		MaxOutputTokens: 0,
+		Supports: SupportedParameters{
+			Temperature:       true,
+			TopP:              true,
+			TopK:              false,
+			FrequencyPenalty:  true,
+			PresencePenalty:   true,
+			Stop:              true,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"openai/gpt-5.5-pro": {
+		Name:            "OpenAI: GPT-5.5 Pro",
+		ContextLength:   1050000,
+		MaxOutputTokens: 128000,
+		Supports: SupportedParameters{
+			Temperature:       false,
+			TopP:              false,
+			TopK:              false,
+			FrequencyPenalty:  false,
+			PresencePenalty:   false,
+			Stop:              false,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"openai/gpt-5.5": {
+		Name:            "OpenAI: GPT-5.5",
+		ContextLength:   1050000,
+		MaxOutputTokens: 128000,
+		Supports: SupportedParameters{
+			Temperature:       false,
+			TopP:              false,
+			TopK:              false,
+			FrequencyPenalty:  false,
+			PresencePenalty:   false,
+			Stop:              false,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"deepseek/deepseek-v4-pro": {
+		Name:            "DeepSeek: DeepSeek V4 Pro",
+		ContextLength:   1048576,
+		MaxOutputTokens: 384000,
+		Supports: SupportedParameters{
+			Temperature:       true,
+			TopP:              true,
+			TopK:              true,
+			FrequencyPenalty:  true,
+			PresencePenalty:   true,
+			Stop:              true,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"deepseek/deepseek-v4-flash": {
+		Name:            "DeepSeek: DeepSeek V4 Flash",
+		ContextLength:   1048576,
+		MaxOutputTokens: 0,
+		Supports: SupportedParameters{
+			Temperature:       true,
+			TopP:              true,
+			TopK:              true,
+			FrequencyPenalty:  true,
+			PresencePenalty:   true,
+			Stop:              true,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"openai/gpt-5.4-image-2": {
+		Name:            "OpenAI: GPT-5.4 Image 2",
+		ContextLength:   272000,
+		MaxOutputTokens: 128000,
+		Supports: SupportedParameters{
+			Temperature:       false,
+			TopP:              false,
+			TopK:              false,
+			FrequencyPenalty:  true,
+			PresencePenalty:   true,
+			Stop:              true,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        false,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         true,
+		},
+	},
+	"anthropic/claude-opus-4.7": {
+		Name:            "Anthropic: Claude Opus 4.7",
+		ContextLength:   1000000,
+		MaxOutputTokens: 128000,
+		Supports: SupportedParameters{
+			Temperature:       false,
+			TopP:              false,
+			TopK:              false,
+			FrequencyPenalty:  false,
+			PresencePenalty:   false,
 			Stop:              true,
 			Seed:              false,
 			MaxTokens:         true,
@@ -46,16 +426,16 @@ var generatedModels = map[string]ModelDefinition{
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              false,
+			TopK:              true,
+			FrequencyPenalty:  true,
+			PresencePenalty:   true,
+			Stop:              true,
 			Seed:              true,
 			MaxTokens:         true,
 			ToolChoice:        true,
 			ParallelToolCalls: false,
 			ResponseFormat:    true,
-			StructuredOutputs: false,
+			StructuredOutputs: true,
 			Reasoning:         true,
 		},
 	},
@@ -82,14 +462,14 @@ var generatedModels = map[string]ModelDefinition{
 	"google/gemma-4-31b-it:free": {
 		Name:            "Google: Gemma 4 31B (free)",
 		ContextLength:   262144,
-		MaxOutputTokens: 32768,
+		MaxOutputTokens: 8192,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
-			TopK:              false,
+			TopK:              true,
 			FrequencyPenalty:  false,
 			PresencePenalty:   false,
-			Stop:              false,
+			Stop:              true,
 			Seed:              true,
 			MaxTokens:         true,
 			ToolChoice:        true,
@@ -102,7 +482,7 @@ var generatedModels = map[string]ModelDefinition{
 	"google/gemma-4-31b-it": {
 		Name:            "Google: Gemma 4 31B",
 		ContextLength:   262144,
-		MaxOutputTokens: 0,
+		MaxOutputTokens: 262144,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -341,15 +721,15 @@ var generatedModels = map[string]ModelDefinition{
 	},
 	"google/gemini-3.1-flash-image-preview": {
 		Name:            "Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)",
-		ContextLength:   65536,
-		MaxOutputTokens: 65536,
+		ContextLength:   131072,
+		MaxOutputTokens: 32768,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
 			TopK:              false,
 			FrequencyPenalty:  false,
 			PresencePenalty:   false,
-			Stop:              true,
+			Stop:              false,
 			Seed:              true,
 			MaxTokens:         true,
 			ToolChoice:        false,
@@ -361,7 +741,7 @@ var generatedModels = map[string]ModelDefinition{
 	},
 	"google/gemini-3.1-pro-preview-customtools": {
 		Name:            "Google: Gemini 3.1 Pro Preview Custom Tools",
-		ContextLength:   1048576,
+		ContextLength:   1048756,
 		MaxOutputTokens: 65536,
 		Supports: SupportedParameters{
 			Temperature:       true,
@@ -369,7 +749,7 @@ var generatedModels = map[string]ModelDefinition{
 			TopK:              false,
 			FrequencyPenalty:  false,
 			PresencePenalty:   false,
-			Stop:              true,
+			Stop:              false,
 			Seed:              true,
 			MaxTokens:         true,
 			ToolChoice:        true,
@@ -522,7 +902,7 @@ var generatedModels = map[string]ModelDefinition{
 	"google/gemini-3-flash-preview": {
 		Name:            "Google: Gemini 3 Flash Preview",
 		ContextLength:   1048576,
-		MaxOutputTokens: 65536,
+		MaxOutputTokens: 65535,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -539,30 +919,10 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         true,
 		},
 	},
-	"mistralai/mistral-small-creative": {
-		Name:            "Mistral: Mistral Small Creative",
-		ContextLength:   32768,
-		MaxOutputTokens: 0,
-		Supports: SupportedParameters{
-			Temperature:       false,
-			TopP:              false,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              false,
-			Seed:              false,
-			MaxTokens:         false,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    false,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
 	"openai/gpt-5.2-chat": {
 		Name:            "OpenAI: GPT-5.2 Chat",
 		ContextLength:   128000,
-		MaxOutputTokens: 32000,
+		MaxOutputTokens: 16384,
 		Supports: SupportedParameters{
 			Temperature:       false,
 			TopP:              false,
@@ -759,30 +1119,10 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         false,
 		},
 	},
-	"deepseek/deepseek-v3.2-speciale": {
-		Name:            "DeepSeek: DeepSeek V3.2 Speciale",
-		ContextLength:   163840,
-		MaxOutputTokens: 163840,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              true,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        false,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         true,
-		},
-	},
 	"deepseek/deepseek-v3.2": {
 		Name:            "DeepSeek: DeepSeek V3.2",
-		ContextLength:   163840,
-		MaxOutputTokens: 0,
+		ContextLength:   131072,
+		MaxOutputTokens: 64000,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -839,26 +1179,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         true,
 		},
 	},
-	"x-ai/grok-4.1-fast": {
-		Name:            "xAI: Grok 4.1 Fast",
-		ContextLength:   2000000,
-		MaxOutputTokens: 30000,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              false,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         true,
-		},
-	},
 	"openai/gpt-5.1": {
 		Name:            "OpenAI: GPT-5.1",
 		ContextLength:   400000,
@@ -882,7 +1202,7 @@ var generatedModels = map[string]ModelDefinition{
 	"openai/gpt-5.1-chat": {
 		Name:            "OpenAI: GPT-5.1 Chat",
 		ContextLength:   128000,
-		MaxOutputTokens: 16384,
+		MaxOutputTokens: 32000,
 		Supports: SupportedParameters{
 			Temperature:       false,
 			TopP:              false,
@@ -922,7 +1242,7 @@ var generatedModels = map[string]ModelDefinition{
 	"openai/gpt-5.1-codex-mini": {
 		Name:            "OpenAI: GPT-5.1-Codex-Mini",
 		ContextLength:   400000,
-		MaxOutputTokens: 128000,
+		MaxOutputTokens: 100000,
 		Supports: SupportedParameters{
 			Temperature:       false,
 			TopP:              false,
@@ -1015,7 +1335,7 @@ var generatedModels = map[string]ModelDefinition{
 			ToolChoice:        true,
 			ParallelToolCalls: false,
 			ResponseFormat:    true,
-			StructuredOutputs: false,
+			StructuredOutputs: true,
 			Reasoning:         true,
 		},
 	},
@@ -1032,7 +1352,7 @@ var generatedModels = map[string]ModelDefinition{
 			Stop:              true,
 			Seed:              true,
 			MaxTokens:         true,
-			ToolChoice:        true,
+			ToolChoice:        false,
 			ParallelToolCalls: false,
 			ResponseFormat:    true,
 			StructuredOutputs: true,
@@ -1072,7 +1392,7 @@ var generatedModels = map[string]ModelDefinition{
 			Stop:              true,
 			Seed:              true,
 			MaxTokens:         true,
-			ToolChoice:        true,
+			ToolChoice:        false,
 			ParallelToolCalls: false,
 			ResponseFormat:    true,
 			StructuredOutputs: true,
@@ -1242,7 +1562,7 @@ var generatedModels = map[string]ModelDefinition{
 	"deepseek/deepseek-v3.1-terminus": {
 		Name:            "DeepSeek: DeepSeek V3.1 Terminus",
 		ContextLength:   163840,
-		MaxOutputTokens: 0,
+		MaxOutputTokens: 32768,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -1259,50 +1579,10 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         true,
 		},
 	},
-	"x-ai/grok-4-fast": {
-		Name:            "xAI: Grok 4 Fast",
-		ContextLength:   2000000,
-		MaxOutputTokens: 30000,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              false,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         true,
-		},
-	},
-	"x-ai/grok-code-fast-1": {
-		Name:            "xAI: Grok Code Fast 1",
-		ContextLength:   256000,
-		MaxOutputTokens: 10000,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         true,
-		},
-	},
 	"deepseek/deepseek-chat-v3.1": {
 		Name:            "DeepSeek: DeepSeek V3.1",
-		ContextLength:   32768,
-		MaxOutputTokens: 7168,
+		ContextLength:   163840,
+		MaxOutputTokens: 32768,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -1319,26 +1599,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         true,
 		},
 	},
-	"openai/gpt-4o-audio-preview": {
-		Name:            "OpenAI: GPT-4o Audio",
-		ContextLength:   128000,
-		MaxOutputTokens: 16384,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         false,
-		},
-	},
 	"mistralai/mistral-medium-3.1": {
 		Name:            "Mistral: Mistral Medium 3.1",
 		ContextLength:   131072,
@@ -1445,8 +1705,8 @@ var generatedModels = map[string]ModelDefinition{
 		MaxOutputTokens: 131072,
 		Supports: SupportedParameters{
 			Temperature:       true,
-			TopP:              false,
-			TopK:              false,
+			TopP:              true,
+			TopK:              true,
 			FrequencyPenalty:  false,
 			PresencePenalty:   false,
 			Stop:              true,
@@ -1462,7 +1722,7 @@ var generatedModels = map[string]ModelDefinition{
 	"openai/gpt-oss-120b": {
 		Name:            "OpenAI: gpt-oss-120b",
 		ContextLength:   131072,
-		MaxOutputTokens: 0,
+		MaxOutputTokens: 131072,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -1482,20 +1742,20 @@ var generatedModels = map[string]ModelDefinition{
 	"openai/gpt-oss-20b:free": {
 		Name:            "OpenAI: gpt-oss-20b (free)",
 		ContextLength:   131072,
-		MaxOutputTokens: 8192,
+		MaxOutputTokens: 32768,
 		Supports: SupportedParameters{
 			Temperature:       true,
-			TopP:              false,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
+			TopP:              true,
+			TopK:              true,
+			FrequencyPenalty:  true,
+			PresencePenalty:   true,
 			Stop:              true,
 			Seed:              true,
 			MaxTokens:         true,
 			ToolChoice:        true,
 			ParallelToolCalls: false,
-			ResponseFormat:    false,
-			StructuredOutputs: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
 			Reasoning:         true,
 		},
 	},
@@ -1579,90 +1839,10 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         true,
 		},
 	},
-	"mistralai/devstral-medium": {
-		Name:            "Mistral: Devstral Medium",
-		ContextLength:   131072,
-		MaxOutputTokens: 0,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         false,
-		},
-	},
-	"mistralai/devstral-small": {
-		Name:            "Mistral: Devstral Small 1.1",
-		ContextLength:   131072,
-		MaxOutputTokens: 0,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         false,
-		},
-	},
-	"x-ai/grok-4": {
-		Name:            "xAI: Grok 4",
-		ContextLength:   256000,
-		MaxOutputTokens: 0,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              false,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         true,
-		},
-	},
-	"google/gemma-3n-e2b-it:free": {
-		Name:            "Google: Gemma 3n 2B (free)",
-		ContextLength:   8192,
-		MaxOutputTokens: 2048,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              false,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        false,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
 	"mistralai/mistral-small-3.2-24b-instruct": {
 		Name:            "Mistral: Mistral Small 3.2 24B",
 		ContextLength:   128000,
-		MaxOutputTokens: 0,
+		MaxOutputTokens: 16384,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -1739,46 +1919,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         true,
 		},
 	},
-	"x-ai/grok-3-mini": {
-		Name:            "xAI: Grok 3 Mini",
-		ContextLength:   131072,
-		MaxOutputTokens: 0,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         true,
-		},
-	},
-	"x-ai/grok-3": {
-		Name:            "xAI: Grok 3",
-		ContextLength:   131072,
-		MaxOutputTokens: 0,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         false,
-		},
-	},
 	"google/gemini-2.5-pro-preview": {
 		Name:            "Google: Gemini 2.5 Pro Preview 06-05",
 		ContextLength:   1048576,
@@ -1802,7 +1942,7 @@ var generatedModels = map[string]ModelDefinition{
 	"deepseek/deepseek-r1-0528": {
 		Name:            "DeepSeek: R1 0528",
 		ContextLength:   163840,
-		MaxOutputTokens: 0,
+		MaxOutputTokens: 32768,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -1826,7 +1966,7 @@ var generatedModels = map[string]ModelDefinition{
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
-			TopK:              true,
+			TopK:              false,
 			FrequencyPenalty:  false,
 			PresencePenalty:   false,
 			Stop:              true,
@@ -1859,26 +1999,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         true,
 		},
 	},
-	"google/gemma-3n-e4b-it:free": {
-		Name:            "Google: Gemma 3n 4B (free)",
-		ContextLength:   8192,
-		MaxOutputTokens: 2048,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              false,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        false,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
 	"google/gemma-3n-e4b-it": {
 		Name:            "Google: Gemma 3n 4B",
 		ContextLength:   32768,
@@ -1894,8 +2014,8 @@ var generatedModels = map[string]ModelDefinition{
 			MaxTokens:         true,
 			ToolChoice:        false,
 			ParallelToolCalls: false,
-			ResponseFormat:    false,
-			StructuredOutputs: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
 			Reasoning:         false,
 		},
 	},
@@ -1942,7 +2062,7 @@ var generatedModels = map[string]ModelDefinition{
 	"meta-llama/llama-guard-4-12b": {
 		Name:            "Meta: Llama Guard 4 12B",
 		ContextLength:   163840,
-		MaxOutputTokens: 0,
+		MaxOutputTokens: 16384,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -2079,46 +2199,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         false,
 		},
 	},
-	"x-ai/grok-3-mini-beta": {
-		Name:            "xAI: Grok 3 Mini Beta",
-		ContextLength:   131072,
-		MaxOutputTokens: 0,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: false,
-			Reasoning:         true,
-		},
-	},
-	"x-ai/grok-3-beta": {
-		Name:            "xAI: Grok 3 Beta",
-		ContextLength:   131072,
-		MaxOutputTokens: 0,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
 	"meta-llama/llama-4-maverick": {
 		Name:            "Meta: Llama 4 Maverick",
 		ContextLength:   1048576,
@@ -2141,7 +2221,7 @@ var generatedModels = map[string]ModelDefinition{
 	},
 	"meta-llama/llama-4-scout": {
 		Name:            "Meta: Llama 4 Scout",
-		ContextLength:   327680,
+		ContextLength:   10000000,
 		MaxOutputTokens: 16384,
 		Supports: SupportedParameters{
 			Temperature:       true,
@@ -2162,7 +2242,7 @@ var generatedModels = map[string]ModelDefinition{
 	"deepseek/deepseek-chat-v3-0324": {
 		Name:            "DeepSeek: DeepSeek V3 0324",
 		ContextLength:   163840,
-		MaxOutputTokens: 0,
+		MaxOutputTokens: 16384,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -2176,7 +2256,7 @@ var generatedModels = map[string]ModelDefinition{
 			ParallelToolCalls: false,
 			ResponseFormat:    true,
 			StructuredOutputs: true,
-			Reasoning:         true,
+			Reasoning:         false,
 		},
 	},
 	"openai/o1-pro": {
@@ -2202,39 +2282,19 @@ var generatedModels = map[string]ModelDefinition{
 	"mistralai/mistral-small-3.1-24b-instruct": {
 		Name:            "Mistral: Mistral Small 3.1 24B",
 		ContextLength:   128000,
-		MaxOutputTokens: 0,
+		MaxOutputTokens: 128000,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
 			TopK:              true,
 			FrequencyPenalty:  true,
 			PresencePenalty:   true,
-			Stop:              false,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        false,
-			ParallelToolCalls: false,
-			ResponseFormat:    false,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
-	"google/gemma-3-4b-it:free": {
-		Name:            "Google: Gemma 3 4B (free)",
-		ContextLength:   32768,
-		MaxOutputTokens: 8192,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
 			Stop:              true,
 			Seed:              true,
 			MaxTokens:         true,
 			ToolChoice:        false,
 			ParallelToolCalls: false,
-			ResponseFormat:    true,
+			ResponseFormat:    false,
 			StructuredOutputs: false,
 			Reasoning:         false,
 		},
@@ -2242,7 +2302,7 @@ var generatedModels = map[string]ModelDefinition{
 	"google/gemma-3-4b-it": {
 		Name:            "Google: Gemma 3 4B",
 		ContextLength:   131072,
-		MaxOutputTokens: 0,
+		MaxOutputTokens: 16384,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -2255,34 +2315,14 @@ var generatedModels = map[string]ModelDefinition{
 			ToolChoice:        false,
 			ParallelToolCalls: false,
 			ResponseFormat:    true,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
-	"google/gemma-3-12b-it:free": {
-		Name:            "Google: Gemma 3 12B (free)",
-		ContextLength:   32768,
-		MaxOutputTokens: 8192,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        false,
-			ParallelToolCalls: false,
-			ResponseFormat:    false,
-			StructuredOutputs: false,
+			StructuredOutputs: true,
 			Reasoning:         false,
 		},
 	},
 	"google/gemma-3-12b-it": {
 		Name:            "Google: Gemma 3 12B",
 		ContextLength:   131072,
-		MaxOutputTokens: 0,
+		MaxOutputTokens: 16384,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -2292,7 +2332,7 @@ var generatedModels = map[string]ModelDefinition{
 			Stop:              true,
 			Seed:              true,
 			MaxTokens:         true,
-			ToolChoice:        false,
+			ToolChoice:        true,
 			ParallelToolCalls: false,
 			ResponseFormat:    true,
 			StructuredOutputs: true,
@@ -2339,26 +2379,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         false,
 		},
 	},
-	"google/gemma-3-27b-it:free": {
-		Name:            "Google: Gemma 3 27B (free)",
-		ContextLength:   131072,
-		MaxOutputTokens: 8192,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        false,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
 	"google/gemma-3-27b-it": {
 		Name:            "Google: Gemma 3 27B",
 		ContextLength:   131072,
@@ -2372,7 +2392,7 @@ var generatedModels = map[string]ModelDefinition{
 			Stop:              true,
 			Seed:              true,
 			MaxTokens:         true,
-			ToolChoice:        false,
+			ToolChoice:        true,
 			ParallelToolCalls: false,
 			ResponseFormat:    true,
 			StructuredOutputs: true,
@@ -2439,66 +2459,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         true,
 		},
 	},
-	"google/gemini-2.0-flash-lite-001": {
-		Name:            "Google: Gemini 2.0 Flash Lite",
-		ContextLength:   1048576,
-		MaxOutputTokens: 8192,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         false,
-		},
-	},
-	"anthropic/claude-3.7-sonnet": {
-		Name:            "Anthropic: Claude 3.7 Sonnet",
-		ContextLength:   200000,
-		MaxOutputTokens: 128000,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              true,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              true,
-			Seed:              false,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    false,
-			StructuredOutputs: false,
-			Reasoning:         true,
-		},
-	},
-	"anthropic/claude-3.7-sonnet:thinking": {
-		Name:            "Anthropic: Claude 3.7 Sonnet (thinking)",
-		ContextLength:   200000,
-		MaxOutputTokens: 64000,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              true,
-			Seed:              false,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    false,
-			StructuredOutputs: false,
-			Reasoning:         true,
-		},
-	},
 	"mistralai/mistral-saba": {
 		Name:            "Mistral: Saba",
 		ContextLength:   32768,
@@ -2519,26 +2479,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         false,
 		},
 	},
-	"meta-llama/llama-guard-3-8b": {
-		Name:            "Llama Guard 3 8B",
-		ContextLength:   131072,
-		MaxOutputTokens: 0,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              true,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              false,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        false,
-			ParallelToolCalls: false,
-			ResponseFormat:    false,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
 	"openai/o3-mini-high": {
 		Name:            "OpenAI: o3 Mini High",
 		ContextLength:   200000,
@@ -2559,26 +2499,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         true,
 		},
 	},
-	"google/gemini-2.0-flash-001": {
-		Name:            "Google: Gemini 2.0 Flash",
-		ContextLength:   1048576,
-		MaxOutputTokens: 8192,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         false,
-		},
-	},
 	"openai/o3-mini": {
 		Name:            "OpenAI: o3 Mini",
 		ContextLength:   200000,
@@ -2615,28 +2535,8 @@ var generatedModels = map[string]ModelDefinition{
 			ToolChoice:        false,
 			ParallelToolCalls: false,
 			ResponseFormat:    true,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
-	"deepseek/deepseek-r1-distill-qwen-32b": {
-		Name:            "DeepSeek: R1 Distill Qwen 32B",
-		ContextLength:   32768,
-		MaxOutputTokens: 32768,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              false,
-			MaxTokens:         true,
-			ToolChoice:        false,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
 			StructuredOutputs: true,
-			Reasoning:         true,
+			Reasoning:         false,
 		},
 	},
 	"perplexity/sonar": {
@@ -2661,8 +2561,8 @@ var generatedModels = map[string]ModelDefinition{
 	},
 	"deepseek/deepseek-r1-distill-llama-70b": {
 		Name:            "DeepSeek: R1 Distill Llama 70B",
-		ContextLength:   131072,
-		MaxOutputTokens: 16384,
+		ContextLength:   128000,
+		MaxOutputTokens: 8192,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -2674,14 +2574,14 @@ var generatedModels = map[string]ModelDefinition{
 			MaxTokens:         true,
 			ToolChoice:        false,
 			ParallelToolCalls: false,
-			ResponseFormat:    true,
+			ResponseFormat:    false,
 			StructuredOutputs: false,
 			Reasoning:         true,
 		},
 	},
 	"deepseek/deepseek-r1": {
 		Name:            "DeepSeek: R1",
-		ContextLength:   64000,
+		ContextLength:   163840,
 		MaxOutputTokens: 16000,
 		Supports: SupportedParameters{
 			Temperature:       true,
@@ -2694,15 +2594,15 @@ var generatedModels = map[string]ModelDefinition{
 			MaxTokens:         true,
 			ToolChoice:        true,
 			ParallelToolCalls: false,
-			ResponseFormat:    false,
-			StructuredOutputs: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
 			Reasoning:         true,
 		},
 	},
 	"deepseek/deepseek-chat": {
 		Name:            "DeepSeek: DeepSeek V3",
-		ContextLength:   163840,
-		MaxOutputTokens: 163840,
+		ContextLength:   131072,
+		MaxOutputTokens: 16000,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -2715,7 +2615,7 @@ var generatedModels = map[string]ModelDefinition{
 			ToolChoice:        true,
 			ParallelToolCalls: false,
 			ResponseFormat:    true,
-			StructuredOutputs: false,
+			StructuredOutputs: true,
 			Reasoning:         false,
 		},
 	},
@@ -2741,7 +2641,7 @@ var generatedModels = map[string]ModelDefinition{
 	},
 	"meta-llama/llama-3.3-70b-instruct:free": {
 		Name:            "Meta: Llama 3.3 70B Instruct (free)",
-		ContextLength:   65536,
+		ContextLength:   131072,
 		MaxOutputTokens: 0,
 		Supports: SupportedParameters{
 			Temperature:       true,
@@ -2859,26 +2759,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         false,
 		},
 	},
-	"mistralai/mistral-large-2411": {
-		Name:            "Mistral Large 2411",
-		ContextLength:   131072,
-		MaxOutputTokens: 0,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         false,
-		},
-	},
 	"mistralai/mistral-large-2407": {
 		Name:            "Mistral Large 2407",
 		ContextLength:   131072,
@@ -2899,46 +2779,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         false,
 		},
 	},
-	"mistralai/pixtral-large-2411": {
-		Name:            "Mistral: Pixtral Large 2411",
-		ContextLength:   131072,
-		MaxOutputTokens: 0,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         false,
-		},
-	},
-	"anthropic/claude-3.5-haiku": {
-		Name:            "Anthropic: Claude 3.5 Haiku",
-		ContextLength:   200000,
-		MaxOutputTokens: 8192,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              true,
-			FrequencyPenalty:  false,
-			PresencePenalty:   false,
-			Stop:              true,
-			Seed:              false,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    false,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
 	"meta-llama/llama-3.2-3b-instruct:free": {
 		Name:            "Meta: Llama 3.2 3B Instruct (free)",
 		ContextLength:   131072,
@@ -2961,15 +2801,15 @@ var generatedModels = map[string]ModelDefinition{
 	},
 	"meta-llama/llama-3.2-3b-instruct": {
 		Name:            "Meta: Llama 3.2 3B Instruct",
-		ContextLength:   80000,
-		MaxOutputTokens: 0,
+		ContextLength:   131072,
+		MaxOutputTokens: 80000,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
 			TopK:              true,
 			FrequencyPenalty:  true,
 			PresencePenalty:   true,
-			Stop:              false,
+			Stop:              true,
 			Seed:              true,
 			MaxTokens:         true,
 			ToolChoice:        false,
@@ -2981,15 +2821,15 @@ var generatedModels = map[string]ModelDefinition{
 	},
 	"meta-llama/llama-3.2-1b-instruct": {
 		Name:            "Meta: Llama 3.2 1B Instruct",
-		ContextLength:   60000,
-		MaxOutputTokens: 0,
+		ContextLength:   131072,
+		MaxOutputTokens: 60000,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
 			TopK:              true,
 			FrequencyPenalty:  true,
 			PresencePenalty:   true,
-			Stop:              false,
+			Stop:              true,
 			Seed:              true,
 			MaxTokens:         true,
 			ToolChoice:        false,
@@ -3041,7 +2881,7 @@ var generatedModels = map[string]ModelDefinition{
 	},
 	"meta-llama/llama-3.1-8b-instruct": {
 		Name:            "Meta: Llama 3.1 8B Instruct",
-		ContextLength:   16384,
+		ContextLength:   131072,
 		MaxOutputTokens: 16384,
 		Supports: SupportedParameters{
 			Temperature:       true,
@@ -3062,26 +2902,6 @@ var generatedModels = map[string]ModelDefinition{
 	"meta-llama/llama-3.1-70b-instruct": {
 		Name:            "Meta: Llama 3.1 70B Instruct",
 		ContextLength:   131072,
-		MaxOutputTokens: 0,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              true,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
-	"mistralai/mistral-nemo": {
-		Name:            "Mistral: Mistral Nemo",
-		ContextLength:   131072,
 		MaxOutputTokens: 16384,
 		Supports: SupportedParameters{
 			Temperature:       true,
@@ -3099,14 +2919,14 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         false,
 		},
 	},
-	"openai/gpt-4o-mini-2024-07-18": {
-		Name:            "OpenAI: GPT-4o-mini (2024-07-18)",
-		ContextLength:   128000,
-		MaxOutputTokens: 16384,
+	"mistralai/mistral-nemo": {
+		Name:            "Mistral: Mistral Nemo",
+		ContextLength:   131072,
+		MaxOutputTokens: 0,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
-			TopK:              false,
+			TopK:              true,
 			FrequencyPenalty:  true,
 			PresencePenalty:   true,
 			Stop:              true,
@@ -3139,30 +2959,30 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         false,
 		},
 	},
+	"openai/gpt-4o-mini-2024-07-18": {
+		Name:            "OpenAI: GPT-4o-mini (2024-07-18)",
+		ContextLength:   128000,
+		MaxOutputTokens: 16384,
+		Supports: SupportedParameters{
+			Temperature:       true,
+			TopP:              true,
+			TopK:              false,
+			FrequencyPenalty:  true,
+			PresencePenalty:   true,
+			Stop:              true,
+			Seed:              true,
+			MaxTokens:         true,
+			ToolChoice:        true,
+			ParallelToolCalls: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
+			Reasoning:         false,
+		},
+	},
 	"google/gemma-2-27b-it": {
 		Name:            "Google: Gemma 2 27B",
 		ContextLength:   8192,
 		MaxOutputTokens: 2048,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              false,
-			MaxTokens:         true,
-			ToolChoice:        false,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         false,
-		},
-	},
-	"openai/gpt-4o-2024-05-13": {
-		Name:            "OpenAI: GPT-4o (2024-05-13)",
-		ContextLength:   128000,
-		MaxOutputTokens: 4096,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -3172,7 +2992,7 @@ var generatedModels = map[string]ModelDefinition{
 			Stop:              true,
 			Seed:              true,
 			MaxTokens:         true,
-			ToolChoice:        true,
+			ToolChoice:        false,
 			ParallelToolCalls: false,
 			ResponseFormat:    true,
 			StructuredOutputs: true,
@@ -3199,10 +3019,10 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         false,
 		},
 	},
-	"openai/gpt-4o:extended": {
-		Name:            "OpenAI: GPT-4o (extended)",
+	"openai/gpt-4o-2024-05-13": {
+		Name:            "OpenAI: GPT-4o (2024-05-13)",
 		ContextLength:   128000,
-		MaxOutputTokens: 64000,
+		MaxOutputTokens: 4096,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -3222,7 +3042,7 @@ var generatedModels = map[string]ModelDefinition{
 	"meta-llama/llama-3-8b-instruct": {
 		Name:            "Meta: Llama 3 8B Instruct",
 		ContextLength:   8192,
-		MaxOutputTokens: 16384,
+		MaxOutputTokens: 0,
 		Supports: SupportedParameters{
 			Temperature:       true,
 			TopP:              true,
@@ -3230,32 +3050,12 @@ var generatedModels = map[string]ModelDefinition{
 			FrequencyPenalty:  true,
 			PresencePenalty:   true,
 			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
-	"meta-llama/llama-3-70b-instruct": {
-		Name:            "Meta: Llama 3 70B Instruct",
-		ContextLength:   8192,
-		MaxOutputTokens: 8000,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              true,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              true,
+			Seed:              false,
 			MaxTokens:         true,
 			ToolChoice:        false,
 			ParallelToolCalls: false,
-			ResponseFormat:    false,
-			StructuredOutputs: false,
+			ResponseFormat:    true,
+			StructuredOutputs: true,
 			Reasoning:         false,
 		},
 	},
@@ -3339,26 +3139,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         false,
 		},
 	},
-	"openai/gpt-4-turbo-preview": {
-		Name:            "OpenAI: GPT-4 Turbo Preview",
-		ContextLength:   128000,
-		MaxOutputTokens: 4096,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         false,
-		},
-	},
 	"openai/gpt-3.5-turbo-0613": {
 		Name:            "OpenAI: GPT-3.5 Turbo (older v0613)",
 		ContextLength:   4095,
@@ -3379,28 +3159,8 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         false,
 		},
 	},
-	"mistralai/mixtral-8x7b-instruct": {
-		Name:            "Mistral: Mixtral 8x7B Instruct",
-		ContextLength:   32768,
-		MaxOutputTokens: 16384,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              true,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
-	"openai/gpt-4-1106-preview": {
-		Name:            "OpenAI: GPT-4 Turbo (older v1106)",
+	"openai/gpt-4-turbo-preview": {
+		Name:            "OpenAI: GPT-4 Turbo Preview",
 		ContextLength:   128000,
 		MaxOutputTokens: 4096,
 		Supports: SupportedParameters{
@@ -3439,26 +3199,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         false,
 		},
 	},
-	"mistralai/mistral-7b-instruct-v0.1": {
-		Name:            "Mistral: Mistral 7B Instruct v0.1",
-		ContextLength:   2824,
-		MaxOutputTokens: 0,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              true,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              false,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        false,
-			ParallelToolCalls: false,
-			ResponseFormat:    false,
-			StructuredOutputs: false,
-			Reasoning:         false,
-		},
-	},
 	"openai/gpt-3.5-turbo-16k": {
 		Name:            "OpenAI: GPT-3.5 Turbo 16k",
 		ContextLength:   16385,
@@ -3479,26 +3219,6 @@ var generatedModels = map[string]ModelDefinition{
 			Reasoning:         false,
 		},
 	},
-	"openai/gpt-4-0314": {
-		Name:            "OpenAI: GPT-4 (older v0314)",
-		ContextLength:   8191,
-		MaxOutputTokens: 4096,
-		Supports: SupportedParameters{
-			Temperature:       true,
-			TopP:              true,
-			TopK:              false,
-			FrequencyPenalty:  true,
-			PresencePenalty:   true,
-			Stop:              true,
-			Seed:              true,
-			MaxTokens:         true,
-			ToolChoice:        true,
-			ParallelToolCalls: false,
-			ResponseFormat:    true,
-			StructuredOutputs: true,
-			Reasoning:         false,
-		},
-	},
 	"openai/gpt-4": {
 		Name:            "OpenAI: GPT-4",
 		ContextLength:   8191,