aljaz/opencode
1
0
Fork 0
mirror of https://github.com/aljazceru/opencode.git synced 2026-01-06 09:24:55 +01:00
Code Issues Packages Projects Releases Wiki Activity

feat: add support for images

Browse Source
This commit is contained in:
phantomreactor
2025-05-03 01:53:58 +05:30
committed by adamdottv
parent 0095832be3
commit ff0ef3bb43
30 changed files with 1323 additions and 468 deletions
Download Patch File Download Diff File Expand all files Collapse all files

107
internal/llm/models/anthropic.go
View File

@@ -14,64 +14,69 @@ const (
// 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,
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,
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,
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,
},
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,
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,
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,
},
}

241
internal/llm/models/azure.go
View File

@@ -18,140 +18,151 @@ const (
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,
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,
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,
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,
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,
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,
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,
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,
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,
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,
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,
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,
},
}

84
internal/llm/models/gemini.go
View File

@@ -12,52 +12,56 @@ const (
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,
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,
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,
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,
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,
},
}

81
internal/llm/models/groq.go
View File

@@ -28,55 +28,60 @@ var GroqModels = map[ModelID]Model{
ContextWindow: 128_000,
DefaultMaxTokens: 50000,
// for some reason, the groq api doesn't like the reasoningEffort parameter
CanReason: false,
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,
ContextWindow: 128_000, // 10M when?
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,
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,
ContextWindow: 128_000,
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,
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,
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,
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,
},
}

23
internal/llm/models/models.go
View File

@@ -8,17 +8,18 @@ type (
)
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"`
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"`
}
// Model IDs

260
internal/llm/models/openai.go
View File

@@ -19,151 +19,163 @@ const (
var OpenAIModels = map[ModelID]Model{
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,
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,
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,
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,
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,
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,
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,
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,
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,
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,
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,
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,
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,
},
}