summaryrefslogtreecommitdiffhomepage
path: root/internal/llm/models
diff options
context:
space:
mode:
Diffstat (limited to 'internal/llm/models')
-rw-r--r--internal/llm/models/anthropic.go97
-rw-r--r--internal/llm/models/azure.go168
-rw-r--r--internal/llm/models/bedrock.go25
-rw-r--r--internal/llm/models/gemini.go67
-rw-r--r--internal/llm/models/groq.go89
-rw-r--r--internal/llm/models/models.go54
-rw-r--r--internal/llm/models/openai.go196
-rw-r--r--internal/llm/models/openrouter.go327
-rw-r--r--internal/llm/models/vertexai.go38
-rw-r--r--internal/llm/models/xai.go61
10 files changed, 0 insertions, 1122 deletions
diff --git a/internal/llm/models/anthropic.go b/internal/llm/models/anthropic.go
deleted file mode 100644
index f67a74842..000000000
--- a/internal/llm/models/anthropic.go
+++ /dev/null
@@ -1,97 +0,0 @@
-package models
-
-const (
- ProviderAnthropic ModelProvider = "anthropic"
-
- // Models
- Claude35Sonnet ModelID = "claude-3.5-sonnet"
- Claude3Haiku ModelID = "claude-3-haiku"
- Claude37Sonnet ModelID = "claude-3.7-sonnet"
- Claude35Haiku ModelID = "claude-3.5-haiku"
- Claude3Opus ModelID = "claude-3-opus"
- Claude4Sonnet ModelID = "claude-4-sonnet"
-)
-
-// https://docs.anthropic.com/en/docs/about-claude/models/all-models
-var AnthropicModels = map[ModelID]Model{
- Claude35Sonnet: {
- ID: Claude35Sonnet,
- Name: "Claude 3.5 Sonnet",
- Provider: ProviderAnthropic,
- APIModel: "claude-3-5-sonnet-latest",
- CostPer1MIn: 3.0,
- CostPer1MInCached: 3.75,
- CostPer1MOutCached: 0.30,
- CostPer1MOut: 15.0,
- ContextWindow: 200000,
- DefaultMaxTokens: 5000,
- SupportsAttachments: true,
- },
- Claude3Haiku: {
- ID: Claude3Haiku,
- Name: "Claude 3 Haiku",
- Provider: ProviderAnthropic,
- APIModel: "claude-3-haiku-20240307", // doesn't support "-latest"
- CostPer1MIn: 0.25,
- CostPer1MInCached: 0.30,
- CostPer1MOutCached: 0.03,
- CostPer1MOut: 1.25,
- ContextWindow: 200000,
- DefaultMaxTokens: 4096,
- SupportsAttachments: true,
- },
- Claude37Sonnet: {
- ID: Claude37Sonnet,
- Name: "Claude 3.7 Sonnet",
- Provider: ProviderAnthropic,
- APIModel: "claude-3-7-sonnet-latest",
- CostPer1MIn: 3.0,
- CostPer1MInCached: 3.75,
- CostPer1MOutCached: 0.30,
- CostPer1MOut: 15.0,
- ContextWindow: 200000,
- DefaultMaxTokens: 50000,
- CanReason: true,
- SupportsAttachments: true,
- },
- Claude4Sonnet: {
- ID: Claude4Sonnet,
- Name: "Claude 4 Sonnet",
- Provider: ProviderAnthropic,
- APIModel: "claude-sonnet-4-20250514",
- CostPer1MIn: 3.0,
- CostPer1MInCached: 3.75,
- CostPer1MOutCached: 0.30,
- CostPer1MOut: 15.0,
- ContextWindow: 200000,
- DefaultMaxTokens: 50000,
- CanReason: true,
- SupportsAttachments: true,
- },
- Claude35Haiku: {
- ID: Claude35Haiku,
- Name: "Claude 3.5 Haiku",
- Provider: ProviderAnthropic,
- APIModel: "claude-3-5-haiku-latest",
- CostPer1MIn: 0.80,
- CostPer1MInCached: 1.0,
- CostPer1MOutCached: 0.08,
- CostPer1MOut: 4.0,
- ContextWindow: 200000,
- DefaultMaxTokens: 4096,
- SupportsAttachments: true,
- },
- Claude3Opus: {
- ID: Claude3Opus,
- Name: "Claude 3 Opus",
- Provider: ProviderAnthropic,
- APIModel: "claude-3-opus-latest",
- CostPer1MIn: 15.0,
- CostPer1MInCached: 18.75,
- CostPer1MOutCached: 1.50,
- CostPer1MOut: 75.0,
- ContextWindow: 200000,
- DefaultMaxTokens: 4096,
- SupportsAttachments: true,
- },
-}
diff --git a/internal/llm/models/azure.go b/internal/llm/models/azure.go
deleted file mode 100644
index 416597302..000000000
--- a/internal/llm/models/azure.go
+++ /dev/null
@@ -1,168 +0,0 @@
-package models
-
-const ProviderAzure ModelProvider = "azure"
-
-const (
- AzureGPT41 ModelID = "azure.gpt-4.1"
- AzureGPT41Mini ModelID = "azure.gpt-4.1-mini"
- AzureGPT41Nano ModelID = "azure.gpt-4.1-nano"
- AzureGPT45Preview ModelID = "azure.gpt-4.5-preview"
- AzureGPT4o ModelID = "azure.gpt-4o"
- AzureGPT4oMini ModelID = "azure.gpt-4o-mini"
- AzureO1 ModelID = "azure.o1"
- AzureO1Mini ModelID = "azure.o1-mini"
- AzureO3 ModelID = "azure.o3"
- AzureO3Mini ModelID = "azure.o3-mini"
- AzureO4Mini ModelID = "azure.o4-mini"
-)
-
-var AzureModels = map[ModelID]Model{
- AzureGPT41: {
- ID: AzureGPT41,
- Name: "Azure OpenAI – GPT 4.1",
- Provider: ProviderAzure,
- APIModel: "gpt-4.1",
- CostPer1MIn: OpenAIModels[GPT41].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[GPT41].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[GPT41].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[GPT41].CostPer1MOutCached,
- ContextWindow: OpenAIModels[GPT41].ContextWindow,
- DefaultMaxTokens: OpenAIModels[GPT41].DefaultMaxTokens,
- SupportsAttachments: true,
- },
- AzureGPT41Mini: {
- ID: AzureGPT41Mini,
- Name: "Azure OpenAI – GPT 4.1 mini",
- Provider: ProviderAzure,
- APIModel: "gpt-4.1-mini",
- CostPer1MIn: OpenAIModels[GPT41Mini].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[GPT41Mini].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[GPT41Mini].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[GPT41Mini].CostPer1MOutCached,
- ContextWindow: OpenAIModels[GPT41Mini].ContextWindow,
- DefaultMaxTokens: OpenAIModels[GPT41Mini].DefaultMaxTokens,
- SupportsAttachments: true,
- },
- AzureGPT41Nano: {
- ID: AzureGPT41Nano,
- Name: "Azure OpenAI – GPT 4.1 nano",
- Provider: ProviderAzure,
- APIModel: "gpt-4.1-nano",
- CostPer1MIn: OpenAIModels[GPT41Nano].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[GPT41Nano].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[GPT41Nano].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[GPT41Nano].CostPer1MOutCached,
- ContextWindow: OpenAIModels[GPT41Nano].ContextWindow,
- DefaultMaxTokens: OpenAIModels[GPT41Nano].DefaultMaxTokens,
- SupportsAttachments: true,
- },
- AzureGPT45Preview: {
- ID: AzureGPT45Preview,
- Name: "Azure OpenAI – GPT 4.5 preview",
- Provider: ProviderAzure,
- APIModel: "gpt-4.5-preview",
- CostPer1MIn: OpenAIModels[GPT45Preview].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[GPT45Preview].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[GPT45Preview].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[GPT45Preview].CostPer1MOutCached,
- ContextWindow: OpenAIModels[GPT45Preview].ContextWindow,
- DefaultMaxTokens: OpenAIModels[GPT45Preview].DefaultMaxTokens,
- SupportsAttachments: true,
- },
- AzureGPT4o: {
- ID: AzureGPT4o,
- Name: "Azure OpenAI – GPT-4o",
- Provider: ProviderAzure,
- APIModel: "gpt-4o",
- CostPer1MIn: OpenAIModels[GPT4o].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[GPT4o].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[GPT4o].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[GPT4o].CostPer1MOutCached,
- ContextWindow: OpenAIModels[GPT4o].ContextWindow,
- DefaultMaxTokens: OpenAIModels[GPT4o].DefaultMaxTokens,
- SupportsAttachments: true,
- },
- AzureGPT4oMini: {
- ID: AzureGPT4oMini,
- Name: "Azure OpenAI – GPT-4o mini",
- Provider: ProviderAzure,
- APIModel: "gpt-4o-mini",
- CostPer1MIn: OpenAIModels[GPT4oMini].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[GPT4oMini].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[GPT4oMini].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[GPT4oMini].CostPer1MOutCached,
- ContextWindow: OpenAIModels[GPT4oMini].ContextWindow,
- DefaultMaxTokens: OpenAIModels[GPT4oMini].DefaultMaxTokens,
- SupportsAttachments: true,
- },
- AzureO1: {
- ID: AzureO1,
- Name: "Azure OpenAI – O1",
- Provider: ProviderAzure,
- APIModel: "o1",
- CostPer1MIn: OpenAIModels[O1].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[O1].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[O1].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[O1].CostPer1MOutCached,
- ContextWindow: OpenAIModels[O1].ContextWindow,
- DefaultMaxTokens: OpenAIModels[O1].DefaultMaxTokens,
- CanReason: OpenAIModels[O1].CanReason,
- SupportsAttachments: true,
- },
- AzureO1Mini: {
- ID: AzureO1Mini,
- Name: "Azure OpenAI – O1 mini",
- Provider: ProviderAzure,
- APIModel: "o1-mini",
- CostPer1MIn: OpenAIModels[O1Mini].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[O1Mini].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[O1Mini].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[O1Mini].CostPer1MOutCached,
- ContextWindow: OpenAIModels[O1Mini].ContextWindow,
- DefaultMaxTokens: OpenAIModels[O1Mini].DefaultMaxTokens,
- CanReason: OpenAIModels[O1Mini].CanReason,
- SupportsAttachments: true,
- },
- AzureO3: {
- ID: AzureO3,
- Name: "Azure OpenAI – O3",
- Provider: ProviderAzure,
- APIModel: "o3",
- CostPer1MIn: OpenAIModels[O3].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[O3].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[O3].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[O3].CostPer1MOutCached,
- ContextWindow: OpenAIModels[O3].ContextWindow,
- DefaultMaxTokens: OpenAIModels[O3].DefaultMaxTokens,
- CanReason: OpenAIModels[O3].CanReason,
- SupportsAttachments: true,
- },
- AzureO3Mini: {
- ID: AzureO3Mini,
- Name: "Azure OpenAI – O3 mini",
- Provider: ProviderAzure,
- APIModel: "o3-mini",
- CostPer1MIn: OpenAIModels[O3Mini].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[O3Mini].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[O3Mini].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[O3Mini].CostPer1MOutCached,
- ContextWindow: OpenAIModels[O3Mini].ContextWindow,
- DefaultMaxTokens: OpenAIModels[O3Mini].DefaultMaxTokens,
- CanReason: OpenAIModels[O3Mini].CanReason,
- SupportsAttachments: false,
- },
- AzureO4Mini: {
- ID: AzureO4Mini,
- Name: "Azure OpenAI – O4 mini",
- Provider: ProviderAzure,
- APIModel: "o4-mini",
- CostPer1MIn: OpenAIModels[O4Mini].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[O4Mini].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[O4Mini].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[O4Mini].CostPer1MOutCached,
- ContextWindow: OpenAIModels[O4Mini].ContextWindow,
- DefaultMaxTokens: OpenAIModels[O4Mini].DefaultMaxTokens,
- CanReason: OpenAIModels[O4Mini].CanReason,
- SupportsAttachments: true,
- },
-}
diff --git a/internal/llm/models/bedrock.go b/internal/llm/models/bedrock.go
deleted file mode 100644
index 06f825654..000000000
--- a/internal/llm/models/bedrock.go
+++ /dev/null
@@ -1,25 +0,0 @@
-package models
-
-const (
- ProviderBedrock ModelProvider = "bedrock"
-
- // Models
- BedrockClaude37Sonnet ModelID = "bedrock.claude-3.7-sonnet"
-)
-
-var BedrockModels = map[ModelID]Model{
- BedrockClaude37Sonnet: {
- ID: BedrockClaude37Sonnet,
- Name: "Bedrock: Claude 3.7 Sonnet",
- Provider: ProviderBedrock,
- APIModel: "anthropic.claude-3-7-sonnet-20250219-v1:0",
- CostPer1MIn: 3.0,
- CostPer1MInCached: 3.75,
- CostPer1MOutCached: 0.30,
- CostPer1MOut: 15.0,
- ContextWindow: 200_000,
- DefaultMaxTokens: 50_000,
- CanReason: true,
- SupportsAttachments: true,
- },
-}
diff --git a/internal/llm/models/gemini.go b/internal/llm/models/gemini.go
deleted file mode 100644
index f73910166..000000000
--- a/internal/llm/models/gemini.go
+++ /dev/null
@@ -1,67 +0,0 @@
-package models
-
-const (
- ProviderGemini ModelProvider = "gemini"
-
- // Models
- Gemini25Flash ModelID = "gemini-2.5-flash"
- Gemini25 ModelID = "gemini-2.5"
- Gemini20Flash ModelID = "gemini-2.0-flash"
- Gemini20FlashLite ModelID = "gemini-2.0-flash-lite"
-)
-
-var GeminiModels = map[ModelID]Model{
- Gemini25Flash: {
- ID: Gemini25Flash,
- Name: "Gemini 2.5 Flash",
- Provider: ProviderGemini,
- APIModel: "gemini-2.5-flash-preview-04-17",
- CostPer1MIn: 0.15,
- CostPer1MInCached: 0,
- CostPer1MOutCached: 0,
- CostPer1MOut: 0.60,
- ContextWindow: 1000000,
- DefaultMaxTokens: 50000,
- SupportsAttachments: true,
- },
- Gemini25: {
- ID: Gemini25,
- Name: "Gemini 2.5 Pro",
- Provider: ProviderGemini,
- APIModel: "gemini-2.5-pro-preview-03-25",
- CostPer1MIn: 1.25,
- CostPer1MInCached: 0,
- CostPer1MOutCached: 0,
- CostPer1MOut: 10,
- ContextWindow: 1000000,
- DefaultMaxTokens: 50000,
- SupportsAttachments: true,
- },
-
- Gemini20Flash: {
- ID: Gemini20Flash,
- Name: "Gemini 2.0 Flash",
- Provider: ProviderGemini,
- APIModel: "gemini-2.0-flash",
- CostPer1MIn: 0.10,
- CostPer1MInCached: 0,
- CostPer1MOutCached: 0,
- CostPer1MOut: 0.40,
- ContextWindow: 1000000,
- DefaultMaxTokens: 6000,
- SupportsAttachments: true,
- },
- Gemini20FlashLite: {
- ID: Gemini20FlashLite,
- Name: "Gemini 2.0 Flash Lite",
- Provider: ProviderGemini,
- APIModel: "gemini-2.0-flash-lite",
- CostPer1MIn: 0.05,
- CostPer1MInCached: 0,
- CostPer1MOutCached: 0,
- CostPer1MOut: 0.30,
- ContextWindow: 1000000,
- DefaultMaxTokens: 6000,
- SupportsAttachments: true,
- },
-}
diff --git a/internal/llm/models/groq.go b/internal/llm/models/groq.go
deleted file mode 100644
index 0a54053de..000000000
--- a/internal/llm/models/groq.go
+++ /dev/null
@@ -1,89 +0,0 @@
-package models
-
-const (
- ProviderGROQ ModelProvider = "groq"
-
- // GROQ
- QWENQwq ModelID = "qwen-qwq"
-
- // GROQ preview models
- Llama4Scout ModelID = "meta-llama/llama-4-scout-17b-16e-instruct"
- Llama4Maverick ModelID = "meta-llama/llama-4-maverick-17b-128e-instruct"
- Llama3_3_70BVersatile ModelID = "llama-3.3-70b-versatile"
- DeepseekR1DistillLlama70b ModelID = "deepseek-r1-distill-llama-70b"
-)
-
-var GroqModels = map[ModelID]Model{
- //
- // GROQ
- QWENQwq: {
- ID: QWENQwq,
- Name: "Qwen Qwq",
- Provider: ProviderGROQ,
- APIModel: "qwen-qwq-32b",
- CostPer1MIn: 0.29,
- CostPer1MInCached: 0.275,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 0.39,
- ContextWindow: 128_000,
- DefaultMaxTokens: 50000,
- // for some reason, the groq api doesn't like the reasoningEffort parameter
- CanReason: false,
- SupportsAttachments: false,
- },
-
- Llama4Scout: {
- ID: Llama4Scout,
- Name: "Llama4Scout",
- Provider: ProviderGROQ,
- APIModel: "meta-llama/llama-4-scout-17b-16e-instruct",
- CostPer1MIn: 0.11,
- CostPer1MInCached: 0,
- CostPer1MOutCached: 0,
- CostPer1MOut: 0.34,
- DefaultMaxTokens: 8192,
- ContextWindow: 128_000, // 10M when?
- SupportsAttachments: true,
- },
-
- Llama4Maverick: {
- ID: Llama4Maverick,
- Name: "Llama4Maverick",
- Provider: ProviderGROQ,
- APIModel: "meta-llama/llama-4-maverick-17b-128e-instruct",
- CostPer1MIn: 0.20,
- CostPer1MInCached: 0,
- CostPer1MOutCached: 0,
- CostPer1MOut: 0.20,
- DefaultMaxTokens: 8192,
- ContextWindow: 128_000,
- SupportsAttachments: true,
- },
-
- Llama3_3_70BVersatile: {
- ID: Llama3_3_70BVersatile,
- Name: "Llama3_3_70BVersatile",
- Provider: ProviderGROQ,
- APIModel: "llama-3.3-70b-versatile",
- CostPer1MIn: 0.59,
- CostPer1MInCached: 0,
- CostPer1MOutCached: 0,
- CostPer1MOut: 0.79,
- ContextWindow: 128_000,
- SupportsAttachments: false,
- },
-
- DeepseekR1DistillLlama70b: {
- ID: DeepseekR1DistillLlama70b,
- Name: "DeepseekR1DistillLlama70b",
- Provider: ProviderGROQ,
- APIModel: "deepseek-r1-distill-llama-70b",
- CostPer1MIn: 0.75,
- CostPer1MInCached: 0,
- CostPer1MOutCached: 0,
- CostPer1MOut: 0.99,
- ContextWindow: 128_000,
- CanReason: true,
- SupportsAttachments: false,
- },
-}
diff --git a/internal/llm/models/models.go b/internal/llm/models/models.go
deleted file mode 100644
index bfdd0d2d8..000000000
--- a/internal/llm/models/models.go
+++ /dev/null
@@ -1,54 +0,0 @@
-package models
-
-import "maps"
-
-type (
- ModelID string
- ModelProvider string
-)
-
-type Model struct {
- ID ModelID `json:"id"`
- Name string `json:"name"`
- Provider ModelProvider `json:"provider"`
- APIModel string `json:"api_model"`
- CostPer1MIn float64 `json:"cost_per_1m_in"`
- CostPer1MOut float64 `json:"cost_per_1m_out"`
- CostPer1MInCached float64 `json:"cost_per_1m_in_cached"`
- CostPer1MOutCached float64 `json:"cost_per_1m_out_cached"`
- ContextWindow int64 `json:"context_window"`
- DefaultMaxTokens int64 `json:"default_max_tokens"`
- CanReason bool `json:"can_reason"`
- SupportsAttachments bool `json:"supports_attachments"`
-}
-
-const (
- // ForTests
- ProviderMock ModelProvider = "__mock"
-)
-
-// Providers in order of popularity
-var ProviderPopularity = map[ModelProvider]int{
- ProviderAnthropic: 1,
- ProviderOpenAI: 2,
- ProviderGemini: 3,
- ProviderGROQ: 4,
- ProviderOpenRouter: 5,
- ProviderBedrock: 6,
- ProviderAzure: 7,
- ProviderVertexAI: 8,
-}
-
-var SupportedModels = map[ModelID]Model{}
-
-func init() {
- maps.Copy(SupportedModels, AnthropicModels)
- maps.Copy(SupportedModels, BedrockModels)
- maps.Copy(SupportedModels, OpenAIModels)
- maps.Copy(SupportedModels, GeminiModels)
- maps.Copy(SupportedModels, GroqModels)
- maps.Copy(SupportedModels, AzureModels)
- maps.Copy(SupportedModels, OpenRouterModels)
- maps.Copy(SupportedModels, XAIModels)
- maps.Copy(SupportedModels, VertexAIGeminiModels)
-}
diff --git a/internal/llm/models/openai.go b/internal/llm/models/openai.go
deleted file mode 100644
index fdca5bed3..000000000
--- a/internal/llm/models/openai.go
+++ /dev/null
@@ -1,196 +0,0 @@
-package models
-
-const (
- ProviderOpenAI ModelProvider = "openai"
-
- CodexMini ModelID = "codex-mini"
- GPT41 ModelID = "gpt-4.1"
- GPT41Mini ModelID = "gpt-4.1-mini"
- GPT41Nano ModelID = "gpt-4.1-nano"
- GPT45Preview ModelID = "gpt-4.5-preview"
- GPT4o ModelID = "gpt-4o"
- GPT4oMini ModelID = "gpt-4o-mini"
- O1 ModelID = "o1"
- O1Pro ModelID = "o1-pro"
- O1Mini ModelID = "o1-mini"
- O3 ModelID = "o3"
- O3Mini ModelID = "o3-mini"
- O4Mini ModelID = "o4-mini"
-)
-
-var OpenAIModels = map[ModelID]Model{
- CodexMini: {
- ID: CodexMini,
- Name: "Codex Mini",
- Provider: ProviderOpenAI,
- APIModel: "codex-mini-latest",
- CostPer1MIn: 1.50,
- CostPer1MInCached: 0.375,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 6.00,
- ContextWindow: 200_000,
- DefaultMaxTokens: 100_000,
- CanReason: true,
- SupportsAttachments: true,
- },
- GPT41: {
- ID: GPT41,
- Name: "GPT 4.1",
- Provider: ProviderOpenAI,
- APIModel: "gpt-4.1",
- CostPer1MIn: 2.00,
- CostPer1MInCached: 0.50,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 8.00,
- ContextWindow: 1_047_576,
- DefaultMaxTokens: 20000,
- SupportsAttachments: true,
- },
- GPT41Mini: {
- ID: GPT41Mini,
- Name: "GPT 4.1 mini",
- Provider: ProviderOpenAI,
- APIModel: "gpt-4.1",
- CostPer1MIn: 0.40,
- CostPer1MInCached: 0.10,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 1.60,
- ContextWindow: 200_000,
- DefaultMaxTokens: 20000,
- SupportsAttachments: true,
- },
- GPT41Nano: {
- ID: GPT41Nano,
- Name: "GPT 4.1 nano",
- Provider: ProviderOpenAI,
- APIModel: "gpt-4.1-nano",
- CostPer1MIn: 0.10,
- CostPer1MInCached: 0.025,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 0.40,
- ContextWindow: 1_047_576,
- DefaultMaxTokens: 20000,
- SupportsAttachments: true,
- },
- GPT45Preview: {
- ID: GPT45Preview,
- Name: "GPT 4.5 preview",
- Provider: ProviderOpenAI,
- APIModel: "gpt-4.5-preview",
- CostPer1MIn: 75.00,
- CostPer1MInCached: 37.50,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 150.00,
- ContextWindow: 128_000,
- DefaultMaxTokens: 15000,
- SupportsAttachments: true,
- },
- GPT4o: {
- ID: GPT4o,
- Name: "GPT 4o",
- Provider: ProviderOpenAI,
- APIModel: "gpt-4o",
- CostPer1MIn: 2.50,
- CostPer1MInCached: 1.25,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 10.00,
- ContextWindow: 128_000,
- DefaultMaxTokens: 4096,
- SupportsAttachments: true,
- },
- GPT4oMini: {
- ID: GPT4oMini,
- Name: "GPT 4o mini",
- Provider: ProviderOpenAI,
- APIModel: "gpt-4o-mini",
- CostPer1MIn: 0.15,
- CostPer1MInCached: 0.075,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 0.60,
- ContextWindow: 128_000,
- SupportsAttachments: true,
- },
- O1: {
- ID: O1,
- Name: "O1",
- Provider: ProviderOpenAI,
- APIModel: "o1",
- CostPer1MIn: 15.00,
- CostPer1MInCached: 7.50,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 60.00,
- ContextWindow: 200_000,
- DefaultMaxTokens: 50000,
- CanReason: true,
- SupportsAttachments: true,
- },
- O1Pro: {
- ID: O1Pro,
- Name: "o1 pro",
- Provider: ProviderOpenAI,
- APIModel: "o1-pro",
- CostPer1MIn: 150.00,
- CostPer1MInCached: 0.0,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 600.00,
- ContextWindow: 200_000,
- DefaultMaxTokens: 50000,
- CanReason: true,
- SupportsAttachments: true,
- },
- O1Mini: {
- ID: O1Mini,
- Name: "o1 mini",
- Provider: ProviderOpenAI,
- APIModel: "o1-mini",
- CostPer1MIn: 1.10,
- CostPer1MInCached: 0.55,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 4.40,
- ContextWindow: 128_000,
- DefaultMaxTokens: 50000,
- CanReason: true,
- SupportsAttachments: true,
- },
- O3: {
- ID: O3,
- Name: "o3",
- Provider: ProviderOpenAI,
- APIModel: "o3",
- CostPer1MIn: 10.00,
- CostPer1MInCached: 2.50,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 40.00,
- ContextWindow: 200_000,
- CanReason: true,
- SupportsAttachments: true,
- },
- O3Mini: {
- ID: O3Mini,
- Name: "o3 mini",
- Provider: ProviderOpenAI,
- APIModel: "o3-mini",
- CostPer1MIn: 1.10,
- CostPer1MInCached: 0.55,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 4.40,
- ContextWindow: 200_000,
- DefaultMaxTokens: 50000,
- CanReason: true,
- SupportsAttachments: false,
- },
- O4Mini: {
- ID: O4Mini,
- Name: "o4 mini",
- Provider: ProviderOpenAI,
- APIModel: "o4-mini",
- CostPer1MIn: 1.10,
- CostPer1MInCached: 0.275,
- CostPer1MOutCached: 0.0,
- CostPer1MOut: 4.40,
- ContextWindow: 128_000,
- DefaultMaxTokens: 50000,
- CanReason: true,
- SupportsAttachments: true,
- },
-}
diff --git a/internal/llm/models/openrouter.go b/internal/llm/models/openrouter.go
deleted file mode 100644
index faee734a0..000000000
--- a/internal/llm/models/openrouter.go
+++ /dev/null
@@ -1,327 +0,0 @@
-package models
-
-const (
- ProviderOpenRouter ModelProvider = "openrouter"
-
- OpenRouterGPT41 ModelID = "openrouter.gpt-4.1"
- OpenRouterGPT41Mini ModelID = "openrouter.gpt-4.1-mini"
- OpenRouterGPT41Nano ModelID = "openrouter.gpt-4.1-nano"
- OpenRouterGPT45Preview ModelID = "openrouter.gpt-4.5-preview"
- OpenRouterGPT4o ModelID = "openrouter.gpt-4o"
- OpenRouterGPT4oMini ModelID = "openrouter.gpt-4o-mini"
- OpenRouterO1 ModelID = "openrouter.o1"
- OpenRouterO1Pro ModelID = "openrouter.o1-pro"
- OpenRouterO1Mini ModelID = "openrouter.o1-mini"
- OpenRouterO3 ModelID = "openrouter.o3"
- OpenRouterO3Mini ModelID = "openrouter.o3-mini"
- OpenRouterO4Mini ModelID = "openrouter.o4-mini"
- OpenRouterGemini25Flash ModelID = "openrouter.gemini-2.5-flash"
- OpenRouterGemini25 ModelID = "openrouter.gemini-2.5"
- OpenRouterClaude35Sonnet ModelID = "openrouter.claude-3.5-sonnet"
- OpenRouterClaude3Haiku ModelID = "openrouter.claude-3-haiku"
- OpenRouterClaude37Sonnet ModelID = "openrouter.claude-3.7-sonnet"
- OpenRouterClaude35Haiku ModelID = "openrouter.claude-3.5-haiku"
- OpenRouterClaude3Opus ModelID = "openrouter.claude-3-opus"
- OpenRouterQwen235B ModelID = "openrouter.qwen-3-235b"
- OpenRouterQwen32B ModelID = "openrouter.qwen-3-32b"
- OpenRouterQwen30B ModelID = "openrouter.qwen-3-30b"
- OpenRouterQwen14B ModelID = "openrouter.qwen-3-14b"
- OpenRouterQwen8B ModelID = "openrouter.qwen-3-8b"
-)
-
-var OpenRouterModels = map[ModelID]Model{
- OpenRouterGPT41: {
- ID: OpenRouterGPT41,
- Name: "OpenRouter: GPT 4.1",
- Provider: ProviderOpenRouter,
- APIModel: "openai/gpt-4.1",
- CostPer1MIn: OpenAIModels[GPT41].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[GPT41].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[GPT41].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[GPT41].CostPer1MOutCached,
- ContextWindow: OpenAIModels[GPT41].ContextWindow,
- DefaultMaxTokens: OpenAIModels[GPT41].DefaultMaxTokens,
- },
- OpenRouterGPT41Mini: {
- ID: OpenRouterGPT41Mini,
- Name: "OpenRouter: GPT 4.1 mini",
- Provider: ProviderOpenRouter,
- APIModel: "openai/gpt-4.1-mini",
- CostPer1MIn: OpenAIModels[GPT41Mini].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[GPT41Mini].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[GPT41Mini].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[GPT41Mini].CostPer1MOutCached,
- ContextWindow: OpenAIModels[GPT41Mini].ContextWindow,
- DefaultMaxTokens: OpenAIModels[GPT41Mini].DefaultMaxTokens,
- },
- OpenRouterGPT41Nano: {
- ID: OpenRouterGPT41Nano,
- Name: "OpenRouter: GPT 4.1 nano",
- Provider: ProviderOpenRouter,
- APIModel: "openai/gpt-4.1-nano",
- CostPer1MIn: OpenAIModels[GPT41Nano].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[GPT41Nano].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[GPT41Nano].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[GPT41Nano].CostPer1MOutCached,
- ContextWindow: OpenAIModels[GPT41Nano].ContextWindow,
- DefaultMaxTokens: OpenAIModels[GPT41Nano].DefaultMaxTokens,
- },
- OpenRouterGPT45Preview: {
- ID: OpenRouterGPT45Preview,
- Name: "OpenRouter: GPT 4.5 preview",
- Provider: ProviderOpenRouter,
- APIModel: "openai/gpt-4.5-preview",
- CostPer1MIn: OpenAIModels[GPT45Preview].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[GPT45Preview].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[GPT45Preview].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[GPT45Preview].CostPer1MOutCached,
- ContextWindow: OpenAIModels[GPT45Preview].ContextWindow,
- DefaultMaxTokens: OpenAIModels[GPT45Preview].DefaultMaxTokens,
- },
- OpenRouterGPT4o: {
- ID: OpenRouterGPT4o,
- Name: "OpenRouter: GPT 4o",
- Provider: ProviderOpenRouter,
- APIModel: "openai/gpt-4o",
- CostPer1MIn: OpenAIModels[GPT4o].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[GPT4o].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[GPT4o].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[GPT4o].CostPer1MOutCached,
- ContextWindow: OpenAIModels[GPT4o].ContextWindow,
- DefaultMaxTokens: OpenAIModels[GPT4o].DefaultMaxTokens,
- },
- OpenRouterGPT4oMini: {
- ID: OpenRouterGPT4oMini,
- Name: "OpenRouter: GPT 4o mini",
- Provider: ProviderOpenRouter,
- APIModel: "openai/gpt-4o-mini",
- CostPer1MIn: OpenAIModels[GPT4oMini].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[GPT4oMini].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[GPT4oMini].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[GPT4oMini].CostPer1MOutCached,
- ContextWindow: OpenAIModels[GPT4oMini].ContextWindow,
- },
- OpenRouterO1: {
- ID: OpenRouterO1,
- Name: "OpenRouter: O1",
- Provider: ProviderOpenRouter,
- APIModel: "openai/o1",
- CostPer1MIn: OpenAIModels[O1].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[O1].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[O1].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[O1].CostPer1MOutCached,
- ContextWindow: OpenAIModels[O1].ContextWindow,
- DefaultMaxTokens: OpenAIModels[O1].DefaultMaxTokens,
- CanReason: OpenAIModels[O1].CanReason,
- },
- OpenRouterO1Pro: {
- ID: OpenRouterO1Pro,
- Name: "OpenRouter: o1 pro",
- Provider: ProviderOpenRouter,
- APIModel: "openai/o1-pro",
- CostPer1MIn: OpenAIModels[O1Pro].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[O1Pro].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[O1Pro].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[O1Pro].CostPer1MOutCached,
- ContextWindow: OpenAIModels[O1Pro].ContextWindow,
- DefaultMaxTokens: OpenAIModels[O1Pro].DefaultMaxTokens,
- CanReason: OpenAIModels[O1Pro].CanReason,
- },
- OpenRouterO1Mini: {
- ID: OpenRouterO1Mini,
- Name: "OpenRouter: o1 mini",
- Provider: ProviderOpenRouter,
- APIModel: "openai/o1-mini",
- CostPer1MIn: OpenAIModels[O1Mini].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[O1Mini].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[O1Mini].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[O1Mini].CostPer1MOutCached,
- ContextWindow: OpenAIModels[O1Mini].ContextWindow,
- DefaultMaxTokens: OpenAIModels[O1Mini].DefaultMaxTokens,
- CanReason: OpenAIModels[O1Mini].CanReason,
- },
- OpenRouterO3: {
- ID: OpenRouterO3,
- Name: "OpenRouter: o3",
- Provider: ProviderOpenRouter,
- APIModel: "openai/o3",
- CostPer1MIn: OpenAIModels[O3].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[O3].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[O3].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[O3].CostPer1MOutCached,
- ContextWindow: OpenAIModels[O3].ContextWindow,
- DefaultMaxTokens: OpenAIModels[O3].DefaultMaxTokens,
- CanReason: OpenAIModels[O3].CanReason,
- },
- OpenRouterO3Mini: {
- ID: OpenRouterO3Mini,
- Name: "OpenRouter: o3 mini",
- Provider: ProviderOpenRouter,
- APIModel: "openai/o3-mini-high",
- CostPer1MIn: OpenAIModels[O3Mini].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[O3Mini].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[O3Mini].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[O3Mini].CostPer1MOutCached,
- ContextWindow: OpenAIModels[O3Mini].ContextWindow,
- DefaultMaxTokens: OpenAIModels[O3Mini].DefaultMaxTokens,
- CanReason: OpenAIModels[O3Mini].CanReason,
- },
- OpenRouterO4Mini: {
- ID: OpenRouterO4Mini,
- Name: "OpenRouter: o4 mini",
- Provider: ProviderOpenRouter,
- APIModel: "openai/o4-mini-high",
- CostPer1MIn: OpenAIModels[O4Mini].CostPer1MIn,
- CostPer1MInCached: OpenAIModels[O4Mini].CostPer1MInCached,
- CostPer1MOut: OpenAIModels[O4Mini].CostPer1MOut,
- CostPer1MOutCached: OpenAIModels[O4Mini].CostPer1MOutCached,
- ContextWindow: OpenAIModels[O4Mini].ContextWindow,
- DefaultMaxTokens: OpenAIModels[O4Mini].DefaultMaxTokens,
- CanReason: OpenAIModels[O4Mini].CanReason,
- },
- OpenRouterGemini25Flash: {
- ID: OpenRouterGemini25Flash,
- Name: "OpenRouter: Gemini 2.5 Flash",
- Provider: ProviderOpenRouter,
- APIModel: "google/gemini-2.5-flash-preview:thinking",
- CostPer1MIn: GeminiModels[Gemini25Flash].CostPer1MIn,
- CostPer1MInCached: GeminiModels[Gemini25Flash].CostPer1MInCached,
- CostPer1MOut: GeminiModels[Gemini25Flash].CostPer1MOut,
- CostPer1MOutCached: GeminiModels[Gemini25Flash].CostPer1MOutCached,
- ContextWindow: GeminiModels[Gemini25Flash].ContextWindow,
- DefaultMaxTokens: GeminiModels[Gemini25Flash].DefaultMaxTokens,
- },
- OpenRouterGemini25: {
- ID: OpenRouterGemini25,
- Name: "OpenRouter: Gemini 2.5 Pro",
- Provider: ProviderOpenRouter,
- APIModel: "google/gemini-2.5-pro-preview-03-25",
- CostPer1MIn: GeminiModels[Gemini25].CostPer1MIn,
- CostPer1MInCached: GeminiModels[Gemini25].CostPer1MInCached,
- CostPer1MOut: GeminiModels[Gemini25].CostPer1MOut,
- CostPer1MOutCached: GeminiModels[Gemini25].CostPer1MOutCached,
- ContextWindow: GeminiModels[Gemini25].ContextWindow,
- DefaultMaxTokens: GeminiModels[Gemini25].DefaultMaxTokens,
- },
- OpenRouterClaude35Sonnet: {
- ID: OpenRouterClaude35Sonnet,
- Name: "OpenRouter: Claude 3.5 Sonnet",
- Provider: ProviderOpenRouter,
- APIModel: "anthropic/claude-3.5-sonnet",
- CostPer1MIn: AnthropicModels[Claude35Sonnet].CostPer1MIn,
- CostPer1MInCached: AnthropicModels[Claude35Sonnet].CostPer1MInCached,
- CostPer1MOut: AnthropicModels[Claude35Sonnet].CostPer1MOut,
- CostPer1MOutCached: AnthropicModels[Claude35Sonnet].CostPer1MOutCached,
- ContextWindow: AnthropicModels[Claude35Sonnet].ContextWindow,
- DefaultMaxTokens: AnthropicModels[Claude35Sonnet].DefaultMaxTokens,
- },
- OpenRouterClaude3Haiku: {
- ID: OpenRouterClaude3Haiku,
- Name: "OpenRouter: Claude 3 Haiku",
- Provider: ProviderOpenRouter,
- APIModel: "anthropic/claude-3-haiku",
- CostPer1MIn: AnthropicModels[Claude3Haiku].CostPer1MIn,
- CostPer1MInCached: AnthropicModels[Claude3Haiku].CostPer1MInCached,
- CostPer1MOut: AnthropicModels[Claude3Haiku].CostPer1MOut,
- CostPer1MOutCached: AnthropicModels[Claude3Haiku].CostPer1MOutCached,
- ContextWindow: AnthropicModels[Claude3Haiku].ContextWindow,
- DefaultMaxTokens: AnthropicModels[Claude3Haiku].DefaultMaxTokens,
- },
- OpenRouterClaude37Sonnet: {
- ID: OpenRouterClaude37Sonnet,
- Name: "OpenRouter: Claude 3.7 Sonnet",
- Provider: ProviderOpenRouter,
- APIModel: "anthropic/claude-3.7-sonnet",
- CostPer1MIn: AnthropicModels[Claude37Sonnet].CostPer1MIn,
- CostPer1MInCached: AnthropicModels[Claude37Sonnet].CostPer1MInCached,
- CostPer1MOut: AnthropicModels[Claude37Sonnet].CostPer1MOut,
- CostPer1MOutCached: AnthropicModels[Claude37Sonnet].CostPer1MOutCached,
- ContextWindow: AnthropicModels[Claude37Sonnet].ContextWindow,
- DefaultMaxTokens: AnthropicModels[Claude37Sonnet].DefaultMaxTokens,
- CanReason: AnthropicModels[Claude37Sonnet].CanReason,
- },
- OpenRouterClaude35Haiku: {
- ID: OpenRouterClaude35Haiku,
- Name: "OpenRouter: Claude 3.5 Haiku",
- Provider: ProviderOpenRouter,
- APIModel: "anthropic/claude-3.5-haiku",
- CostPer1MIn: AnthropicModels[Claude35Haiku].CostPer1MIn,
- CostPer1MInCached: AnthropicModels[Claude35Haiku].CostPer1MInCached,
- CostPer1MOut: AnthropicModels[Claude35Haiku].CostPer1MOut,
- CostPer1MOutCached: AnthropicModels[Claude35Haiku].CostPer1MOutCached,
- ContextWindow: AnthropicModels[Claude35Haiku].ContextWindow,
- DefaultMaxTokens: AnthropicModels[Claude35Haiku].DefaultMaxTokens,
- },
- OpenRouterClaude3Opus: {
- ID: OpenRouterClaude3Opus,
- Name: "OpenRouter: Claude 3 Opus",
- Provider: ProviderOpenRouter,
- APIModel: "anthropic/claude-3-opus",
- CostPer1MIn: AnthropicModels[Claude3Opus].CostPer1MIn,
- CostPer1MInCached: AnthropicModels[Claude3Opus].CostPer1MInCached,
- CostPer1MOut: AnthropicModels[Claude3Opus].CostPer1MOut,
- CostPer1MOutCached: AnthropicModels[Claude3Opus].CostPer1MOutCached,
- ContextWindow: AnthropicModels[Claude3Opus].ContextWindow,
- DefaultMaxTokens: AnthropicModels[Claude3Opus].DefaultMaxTokens,
- },
- OpenRouterQwen235B: {
- ID: OpenRouterQwen235B,
- Name: "OpenRouter: Qwen3 235B A22B",
- Provider: ProviderOpenRouter,
- APIModel: "qwen/qwen3-235b-a22b",
- CostPer1MIn: 0.1,
- CostPer1MInCached: 0.1,
- CostPer1MOut: 0.1,
- CostPer1MOutCached: 0.1,
- ContextWindow: 40960,
- DefaultMaxTokens: 4096,
- },
- OpenRouterQwen32B: {
- ID: OpenRouterQwen32B,
- Name: "OpenRouter: Qwen3 32B",
- Provider: ProviderOpenRouter,
- APIModel: "qwen/qwen3-32b",
- CostPer1MIn: 0.1,
- CostPer1MInCached: 0.1,
- CostPer1MOut: 0.3,
- CostPer1MOutCached: 0.3,
- ContextWindow: 40960,
- DefaultMaxTokens: 4096,
- },
- OpenRouterQwen30B: {
- ID: OpenRouterQwen30B,
- Name: "OpenRouter: Qwen3 30B A3B",
- Provider: ProviderOpenRouter,
- APIModel: "qwen/qwen3-30b-a3b",
- CostPer1MIn: 0.1,
- CostPer1MInCached: 0.1,
- CostPer1MOut: 0.3,
- CostPer1MOutCached: 0.3,
- ContextWindow: 40960,
- DefaultMaxTokens: 4096,
- },
- OpenRouterQwen14B: {
- ID: OpenRouterQwen14B,
- Name: "OpenRouter: Qwen3 14B",
- Provider: ProviderOpenRouter,
- APIModel: "qwen/qwen3-14b",
- CostPer1MIn: 0.7,
- CostPer1MInCached: 0.7,
- CostPer1MOut: 0.24,
- CostPer1MOutCached: 0.24,
- ContextWindow: 40960,
- DefaultMaxTokens: 4096,
- },
- OpenRouterQwen8B: {
- ID: OpenRouterQwen8B,
- Name: "OpenRouter: Qwen3 8B",
- Provider: ProviderOpenRouter,
- APIModel: "qwen/qwen3-8b",
- CostPer1MIn: 0.35,
- CostPer1MInCached: 0.35,
- CostPer1MOut: 0.138,
- CostPer1MOutCached: 0.138,
- ContextWindow: 128000,
- DefaultMaxTokens: 4096,
- },
-}
diff --git a/internal/llm/models/vertexai.go b/internal/llm/models/vertexai.go
deleted file mode 100644
index d71dfc0be..000000000
--- a/internal/llm/models/vertexai.go
+++ /dev/null
@@ -1,38 +0,0 @@
-package models
-
-const (
- ProviderVertexAI ModelProvider = "vertexai"
-
- // Models
- VertexAIGemini25Flash ModelID = "vertexai.gemini-2.5-flash"
- VertexAIGemini25 ModelID = "vertexai.gemini-2.5"
-)
-
-var VertexAIGeminiModels = map[ModelID]Model{
- VertexAIGemini25Flash: {
- ID: VertexAIGemini25Flash,
- Name: "VertexAI: Gemini 2.5 Flash",
- Provider: ProviderVertexAI,
- APIModel: "gemini-2.5-flash-preview-04-17",
- CostPer1MIn: GeminiModels[Gemini25Flash].CostPer1MIn,
- CostPer1MInCached: GeminiModels[Gemini25Flash].CostPer1MInCached,
- CostPer1MOut: GeminiModels[Gemini25Flash].CostPer1MOut,
- CostPer1MOutCached: GeminiModels[Gemini25Flash].CostPer1MOutCached,
- ContextWindow: GeminiModels[Gemini25Flash].ContextWindow,
- DefaultMaxTokens: GeminiModels[Gemini25Flash].DefaultMaxTokens,
- SupportsAttachments: true,
- },
- VertexAIGemini25: {
- ID: VertexAIGemini25,
- Name: "VertexAI: Gemini 2.5 Pro",
- Provider: ProviderVertexAI,
- APIModel: "gemini-2.5-pro-preview-03-25",
- CostPer1MIn: GeminiModels[Gemini25].CostPer1MIn,
- CostPer1MInCached: GeminiModels[Gemini25].CostPer1MInCached,
- CostPer1MOut: GeminiModels[Gemini25].CostPer1MOut,
- CostPer1MOutCached: GeminiModels[Gemini25].CostPer1MOutCached,
- ContextWindow: GeminiModels[Gemini25].ContextWindow,
- DefaultMaxTokens: GeminiModels[Gemini25].DefaultMaxTokens,
- SupportsAttachments: true,
- },
-}
diff --git a/internal/llm/models/xai.go b/internal/llm/models/xai.go
deleted file mode 100644
index 00caf3b89..000000000
--- a/internal/llm/models/xai.go
+++ /dev/null
@@ -1,61 +0,0 @@
-package models
-
-const (
- ProviderXAI ModelProvider = "xai"
-
- XAIGrok3Beta ModelID = "grok-3-beta"
- XAIGrok3MiniBeta ModelID = "grok-3-mini-beta"
- XAIGrok3FastBeta ModelID = "grok-3-fast-beta"
- XAiGrok3MiniFastBeta ModelID = "grok-3-mini-fast-beta"
-)
-
-var XAIModels = map[ModelID]Model{
- XAIGrok3Beta: {
- ID: XAIGrok3Beta,
- Name: "Grok3 Beta",
- Provider: ProviderXAI,
- APIModel: "grok-3-beta",
- CostPer1MIn: 3.0,
- CostPer1MInCached: 0,
- CostPer1MOut: 15,
- CostPer1MOutCached: 0,
- ContextWindow: 131_072,
- DefaultMaxTokens: 20_000,
- },
- XAIGrok3MiniBeta: {
- ID: XAIGrok3MiniBeta,
- Name: "Grok3 Mini Beta",
- Provider: ProviderXAI,
- APIModel: "grok-3-mini-beta",
- CostPer1MIn: 0.3,
- CostPer1MInCached: 0,
- CostPer1MOut: 0.5,
- CostPer1MOutCached: 0,
- ContextWindow: 131_072,
- DefaultMaxTokens: 20_000,
- },
- XAIGrok3FastBeta: {
- ID: XAIGrok3FastBeta,
- Name: "Grok3 Fast Beta",
- Provider: ProviderXAI,
- APIModel: "grok-3-fast-beta",
- CostPer1MIn: 5,
- CostPer1MInCached: 0,
- CostPer1MOut: 25,
- CostPer1MOutCached: 0,
- ContextWindow: 131_072,
- DefaultMaxTokens: 20_000,
- },
- XAiGrok3MiniFastBeta: {
- ID: XAiGrok3MiniFastBeta,
- Name: "Grok3 Mini Fast Beta",
- Provider: ProviderXAI,
- APIModel: "grok-3-mini-fast-beta",
- CostPer1MIn: 0.6,
- CostPer1MInCached: 0,
- CostPer1MOut: 4.0,
- CostPer1MOutCached: 0,
- ContextWindow: 131_072,
- DefaultMaxTokens: 20_000,
- },
-}
generated by cgit v1.2.3 (git 2.39.1) at 2026-07-04 20:56:40 +0000