models

Documentation

Index

• Constants
• Variables
• type Model
• type ModelID
• type ModelProvider

Constants

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"
)

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"
)

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"
)

const (
	ProviderOpenAI ModelProvider = "openai"

	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"
)

Variables

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,
	},
	Claude3Haiku: {
		ID:                 Claude3Haiku,
		Name:               "Claude 3 Haiku",
		Provider:           ProviderAnthropic,
		APIModel:           "claude-3-haiku-20240307",
		CostPer1MIn:        0.25,
		CostPer1MInCached:  0.30,
		CostPer1MOutCached: 0.03,
		CostPer1MOut:       1.25,
		ContextWindow:      200000,
		DefaultMaxTokens:   4096,
	},
	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,
	},
	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,
	},
	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,
	},
}

https://docs.anthropic.com/en/docs/about-claude/models/all-models

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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
}

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,
	},
	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,
	},

	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,
	},
	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,
	},
}

var GroqModels = map[ModelID]Model{

	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,

		CanReason: 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,
	},

	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,
	},

	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,
	},

	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,
	},
}

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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
	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,
	},
}

var ProviderPopularity = map[ModelProvider]int{
	ProviderAnthropic: 1,
	ProviderOpenAI:    2,
	ProviderGemini:    3,
	ProviderGROQ:      4,
	ProviderBedrock:   5,
}

Providers in order of popularity

var SupportedModels = 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,
	},
}

Types

type Model

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"`
}

type ModelID

type ModelID string

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"
)

const (
	// Bedrock
	BedrockClaude37Sonnet ModelID = "bedrock.claude-3.7-sonnet"
)

Model IDs

type ModelProvider

type ModelProvider string

const (
	ProviderBedrock ModelProvider = "bedrock"
	// ForTests
	ProviderMock ModelProvider = "__mock"
)

const ProviderAzure ModelProvider = "azure"