mirror of
https://github.com/RooVetGit/Roo-Code.git
synced 2026-08-28 05:27:24 +00:00
517 lines
14 KiB
TypeScript
517 lines
14 KiB
TypeScript
export type ApiProvider =
|
|
| "anthropic"
|
|
| "openrouter"
|
|
| "bedrock"
|
|
| "vertex"
|
|
| "openai"
|
|
| "ollama"
|
|
| "lmstudio"
|
|
| "gemini"
|
|
| "openai-native"
|
|
| "deepseek"
|
|
| "mistral"
|
|
| "vscode-lm"
|
|
| "litellm"
|
|
|
|
export interface ApiHandlerOptions {
|
|
apiModelId?: string
|
|
apiKey?: string // anthropic
|
|
liteLlmBaseUrl?: string
|
|
liteLlmModelId?: string
|
|
anthropicBaseUrl?: string
|
|
openRouterApiKey?: string
|
|
openRouterModelId?: string
|
|
openRouterModelInfo?: ModelInfo
|
|
awsAccessKey?: string
|
|
awsSecretKey?: string
|
|
awsSessionToken?: string
|
|
awsRegion?: string
|
|
awsUseCrossRegionInference?: boolean
|
|
vertexProjectId?: string
|
|
vertexRegion?: string
|
|
openAiBaseUrl?: string
|
|
openAiApiKey?: string
|
|
openAiModelId?: string
|
|
ollamaModelId?: string
|
|
ollamaBaseUrl?: string
|
|
lmStudioModelId?: string
|
|
lmStudioBaseUrl?: string
|
|
geminiApiKey?: string
|
|
openAiNativeApiKey?: string
|
|
deepSeekApiKey?: string
|
|
mistralApiKey?: string
|
|
azureApiVersion?: string
|
|
vsCodeLmModelSelector?: any
|
|
}
|
|
|
|
export type ApiConfiguration = ApiHandlerOptions & {
|
|
apiProvider?: ApiProvider
|
|
}
|
|
|
|
// Models
|
|
|
|
export interface ModelInfo {
|
|
maxTokens?: number
|
|
contextWindow?: number
|
|
supportsImages?: boolean
|
|
supportsComputerUse?: boolean
|
|
supportsPromptCache: boolean // this value is hardcoded for now
|
|
inputPrice?: number
|
|
outputPrice?: number
|
|
cacheWritesPrice?: number
|
|
cacheReadsPrice?: number
|
|
description?: string
|
|
}
|
|
|
|
// Anthropic
|
|
// https://docs.anthropic.com/en/docs/about-claude/models // prices updated 2025-01-02
|
|
export type AnthropicModelId = keyof typeof anthropicModels
|
|
export const anthropicDefaultModelId: AnthropicModelId = "claude-3-5-sonnet-20241022"
|
|
export const anthropicModels = {
|
|
"claude-3-5-sonnet-20241022": {
|
|
maxTokens: 8192,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsComputerUse: true,
|
|
supportsPromptCache: true,
|
|
inputPrice: 3.0, // $3 per million input tokens
|
|
outputPrice: 15.0, // $15 per million output tokens
|
|
cacheWritesPrice: 3.75, // $3.75 per million tokens
|
|
cacheReadsPrice: 0.3, // $0.30 per million tokens
|
|
},
|
|
"claude-3-5-haiku-20241022": {
|
|
maxTokens: 8192,
|
|
contextWindow: 200_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: true,
|
|
inputPrice: 0.8,
|
|
outputPrice: 4.0,
|
|
cacheWritesPrice: 1.0,
|
|
cacheReadsPrice: 0.08,
|
|
},
|
|
"claude-3-opus-20240229": {
|
|
maxTokens: 4096,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: true,
|
|
inputPrice: 15.0,
|
|
outputPrice: 75.0,
|
|
cacheWritesPrice: 18.75,
|
|
cacheReadsPrice: 1.5,
|
|
},
|
|
"claude-3-haiku-20240307": {
|
|
maxTokens: 4096,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: true,
|
|
inputPrice: 0.25,
|
|
outputPrice: 1.25,
|
|
cacheWritesPrice: 0.3,
|
|
cacheReadsPrice: 0.03,
|
|
},
|
|
} as const satisfies Record<string, ModelInfo> // as const assertion makes the object deeply readonly
|
|
|
|
// AWS Bedrock
|
|
// https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html
|
|
export type BedrockModelId = keyof typeof bedrockModels
|
|
export const bedrockDefaultModelId: BedrockModelId = "anthropic.claude-3-5-sonnet-20241022-v2:0"
|
|
export const bedrockModels = {
|
|
"anthropic.claude-3-5-sonnet-20241022-v2:0": {
|
|
maxTokens: 8192,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsComputerUse: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 3.0,
|
|
outputPrice: 15.0,
|
|
},
|
|
"anthropic.claude-3-5-haiku-20241022-v1:0": {
|
|
maxTokens: 8192,
|
|
contextWindow: 200_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: false,
|
|
inputPrice: 1.0,
|
|
outputPrice: 5.0,
|
|
},
|
|
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
|
|
maxTokens: 8192,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 3.0,
|
|
outputPrice: 15.0,
|
|
},
|
|
"anthropic.claude-3-opus-20240229-v1:0": {
|
|
maxTokens: 4096,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 15.0,
|
|
outputPrice: 75.0,
|
|
},
|
|
"anthropic.claude-3-sonnet-20240229-v1:0": {
|
|
maxTokens: 4096,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 3.0,
|
|
outputPrice: 15.0,
|
|
},
|
|
"anthropic.claude-3-haiku-20240307-v1:0": {
|
|
maxTokens: 4096,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0.25,
|
|
outputPrice: 1.25,
|
|
},
|
|
} as const satisfies Record<string, ModelInfo>
|
|
|
|
// OpenRouter
|
|
// https://openrouter.ai/models?order=newest&supported_parameters=tools
|
|
export const openRouterDefaultModelId = "anthropic/claude-3.5-sonnet:beta" // will always exist in openRouterModels
|
|
export const openRouterDefaultModelInfo: ModelInfo = {
|
|
maxTokens: 8192,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsComputerUse: true,
|
|
supportsPromptCache: true,
|
|
inputPrice: 3.0,
|
|
outputPrice: 15.0,
|
|
cacheWritesPrice: 3.75,
|
|
cacheReadsPrice: 0.3,
|
|
description:
|
|
"The new Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:\n\n- Coding: New Sonnet scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding\n- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights\n- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone\n- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)\n\n#multimodal\n\n_This is a faster endpoint, made available in collaboration with Anthropic, that is self-moderated: response moderation happens on the provider's side instead of OpenRouter's. For requests that pass moderation, it's identical to the [Standard](/anthropic/claude-3.5-sonnet) variant._",
|
|
}
|
|
|
|
// Vertex AI
|
|
// https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/use-claude
|
|
export type VertexModelId = keyof typeof vertexModels
|
|
export const vertexDefaultModelId: VertexModelId = "claude-3-5-sonnet-v2@20241022"
|
|
export const vertexModels = {
|
|
"claude-3-5-sonnet-v2@20241022": {
|
|
maxTokens: 8192,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsComputerUse: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 3.0,
|
|
outputPrice: 15.0,
|
|
},
|
|
"claude-3-5-sonnet@20240620": {
|
|
maxTokens: 8192,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 3.0,
|
|
outputPrice: 15.0,
|
|
},
|
|
"claude-3-5-haiku@20241022": {
|
|
maxTokens: 8192,
|
|
contextWindow: 200_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: false,
|
|
inputPrice: 1.0,
|
|
outputPrice: 5.0,
|
|
},
|
|
"claude-3-opus@20240229": {
|
|
maxTokens: 4096,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 15.0,
|
|
outputPrice: 75.0,
|
|
},
|
|
"claude-3-haiku@20240307": {
|
|
maxTokens: 4096,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0.25,
|
|
outputPrice: 1.25,
|
|
},
|
|
} as const satisfies Record<string, ModelInfo>
|
|
|
|
export const openAiModelInfoSaneDefaults: ModelInfo = {
|
|
maxTokens: -1,
|
|
contextWindow: 128_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0,
|
|
outputPrice: 0,
|
|
}
|
|
|
|
// Gemini
|
|
// https://ai.google.dev/gemini-api/docs/models/gemini
|
|
export type GeminiModelId = keyof typeof geminiModels
|
|
export const geminiDefaultModelId: GeminiModelId = "gemini-2.0-flash-thinking-exp-1219"
|
|
export const geminiModels = {
|
|
"gemini-2.0-flash-thinking-exp-01-21": {
|
|
maxTokens: 65536,
|
|
contextWindow: 1_048_576,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0,
|
|
outputPrice: 0,
|
|
},
|
|
"gemini-2.0-flash-thinking-exp-1219": {
|
|
maxTokens: 8192,
|
|
contextWindow: 32_767,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0,
|
|
outputPrice: 0,
|
|
},
|
|
"gemini-2.0-flash-exp": {
|
|
maxTokens: 8192,
|
|
contextWindow: 1_048_576,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0,
|
|
outputPrice: 0,
|
|
},
|
|
"gemini-exp-1206": {
|
|
maxTokens: 8192,
|
|
contextWindow: 2_097_152,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0,
|
|
outputPrice: 0,
|
|
},
|
|
"gemini-1.5-flash-002": {
|
|
maxTokens: 8192,
|
|
contextWindow: 1_048_576,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0,
|
|
outputPrice: 0,
|
|
},
|
|
"gemini-1.5-flash-exp-0827": {
|
|
maxTokens: 8192,
|
|
contextWindow: 1_048_576,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0,
|
|
outputPrice: 0,
|
|
},
|
|
"gemini-1.5-flash-8b-exp-0827": {
|
|
maxTokens: 8192,
|
|
contextWindow: 1_048_576,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0,
|
|
outputPrice: 0,
|
|
},
|
|
"gemini-1.5-pro-002": {
|
|
maxTokens: 8192,
|
|
contextWindow: 2_097_152,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0,
|
|
outputPrice: 0,
|
|
},
|
|
"gemini-1.5-pro-exp-0827": {
|
|
maxTokens: 8192,
|
|
contextWindow: 2_097_152,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0,
|
|
outputPrice: 0,
|
|
},
|
|
} as const satisfies Record<string, ModelInfo>
|
|
|
|
// OpenAI Native
|
|
// https://openai.com/api/pricing/
|
|
export type OpenAiNativeModelId = keyof typeof openAiNativeModels
|
|
export const openAiNativeDefaultModelId: OpenAiNativeModelId = "gpt-4o"
|
|
export const openAiNativeModels = {
|
|
"o3-mini": {
|
|
maxTokens: 100_000,
|
|
contextWindow: 200_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: false,
|
|
inputPrice: 1.1,
|
|
outputPrice: 4.4,
|
|
},
|
|
// don't support tool use yet
|
|
o1: {
|
|
maxTokens: 100_000,
|
|
contextWindow: 200_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 15,
|
|
outputPrice: 60,
|
|
},
|
|
"o1-preview": {
|
|
maxTokens: 32_768,
|
|
contextWindow: 128_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 15,
|
|
outputPrice: 60,
|
|
},
|
|
"o1-mini": {
|
|
maxTokens: 65_536,
|
|
contextWindow: 128_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 1.1,
|
|
outputPrice: 4.4,
|
|
},
|
|
"gpt-4o": {
|
|
maxTokens: 4_096,
|
|
contextWindow: 128_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 2.5,
|
|
outputPrice: 10,
|
|
},
|
|
"gpt-4o-mini": {
|
|
maxTokens: 16_384,
|
|
contextWindow: 128_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0.15,
|
|
outputPrice: 0.6,
|
|
},
|
|
} as const satisfies Record<string, ModelInfo>
|
|
|
|
// Azure OpenAI
|
|
// https://learn.microsoft.com/en-us/azure/ai-services/openai/api-version-deprecation
|
|
// https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#api-specs
|
|
export const azureOpenAiDefaultApiVersion = "2024-08-01-preview"
|
|
|
|
// DeepSeek
|
|
// https://api-docs.deepseek.com/quick_start/pricing
|
|
export type DeepSeekModelId = keyof typeof deepSeekModels
|
|
export const deepSeekDefaultModelId: DeepSeekModelId = "deepseek-chat"
|
|
export const deepSeekModels = {
|
|
"deepseek-chat": {
|
|
maxTokens: 8_000,
|
|
contextWindow: 64_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: true, // supports context caching, but not in the way anthropic does it (deepseek reports input tokens and reads/writes in the same usage report) FIXME: we need to show users cache stats how deepseek does it
|
|
inputPrice: 0, // technically there is no input price, it's all either a cache hit or miss (ApiOptions will not show this)
|
|
outputPrice: 0.28,
|
|
cacheWritesPrice: 0.14,
|
|
cacheReadsPrice: 0.014,
|
|
},
|
|
"deepseek-reasoner": {
|
|
maxTokens: 8_000,
|
|
contextWindow: 64_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: true, // supports context caching, but not in the way anthropic does it (deepseek reports input tokens and reads/writes in the same usage report) FIXME: we need to show users cache stats how deepseek does it
|
|
inputPrice: 0, // technically there is no input price, it's all either a cache hit or miss (ApiOptions will not show this)
|
|
outputPrice: 2.19,
|
|
cacheWritesPrice: 0.55,
|
|
cacheReadsPrice: 0.14,
|
|
},
|
|
} as const satisfies Record<string, ModelInfo>
|
|
|
|
// Mistral
|
|
// https://docs.mistral.ai/getting-started/models/models_overview/
|
|
export type MistralModelId = keyof typeof mistralModels
|
|
export const mistralDefaultModelId: MistralModelId = "codestral-2501"
|
|
export const mistralModels = {
|
|
"mistral-large-2411": {
|
|
maxTokens: 131_000,
|
|
contextWindow: 131_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: false,
|
|
inputPrice: 2.0,
|
|
outputPrice: 6.0,
|
|
},
|
|
"pixtral-large-2411": {
|
|
maxTokens: 131_000,
|
|
contextWindow: 131_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 2.0,
|
|
outputPrice: 6.0,
|
|
},
|
|
"ministral-3b-2410": {
|
|
maxTokens: 131_000,
|
|
contextWindow: 131_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0.04,
|
|
outputPrice: 0.04,
|
|
},
|
|
"ministral-8b-2410": {
|
|
maxTokens: 131_000,
|
|
contextWindow: 131_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0.1,
|
|
outputPrice: 0.1,
|
|
},
|
|
"mistral-embed": {
|
|
maxTokens: 8_000,
|
|
contextWindow: 8_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0.1,
|
|
outputPrice: 0.1,
|
|
},
|
|
"mistral-moderation-2411": {
|
|
maxTokens: 8_000,
|
|
contextWindow: 8_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0.1,
|
|
outputPrice: 0.1,
|
|
},
|
|
"mistral-small-2501": {
|
|
maxTokens: 32_000,
|
|
contextWindow: 32_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0.1,
|
|
outputPrice: 0.3,
|
|
},
|
|
"pixtral-12b-2409": {
|
|
maxTokens: 131_000,
|
|
contextWindow: 131_000,
|
|
supportsImages: true,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0.15,
|
|
outputPrice: 0.15,
|
|
},
|
|
"open-mistral-nemo-2407": {
|
|
maxTokens: 131_000,
|
|
contextWindow: 131_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0.15,
|
|
outputPrice: 0.15,
|
|
},
|
|
"open-codestral-mamba": {
|
|
maxTokens: 256_000,
|
|
contextWindow: 256_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0.15,
|
|
outputPrice: 0.15,
|
|
},
|
|
"codestral-2501": {
|
|
maxTokens: 256_000,
|
|
contextWindow: 256_000,
|
|
supportsImages: false,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0.3,
|
|
outputPrice: 0.9,
|
|
},
|
|
} as const satisfies Record<string, ModelInfo>
|
|
|
|
// LiteLLM
|
|
// https://docs.litellm.ai/docs/
|
|
export type LiteLLMModelId = string
|
|
export const liteLlmDefaultModelId = "gpt-3.5-turbo"
|
|
export const liteLlmModelInfoSaneDefaults: ModelInfo = {
|
|
maxTokens: 4096,
|
|
contextWindow: 8192,
|
|
supportsImages: false,
|
|
supportsPromptCache: false,
|
|
inputPrice: 0,
|
|
outputPrice: 0,
|
|
}
|