scriptoriumadmin/Roo-Code
1
0
Fork 0
mirror of https://github.com/RooVetGit/Roo-Code.git synced 2026-08-28 05:27:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
Roo-Code/src/shared/api.ts
Chris Estreich a08461a655
Gemini prompt caching (#2827)
2025-04-23 11:35:50 -07:00

1398 lines
37 KiB
TypeScript
Raw Blame History

import { ModelInfo, ProviderName, ProviderSettings } from "../schemas"
import { REASONING_MODELS } from "../api/providers/constants"
export { REASONING_MODELS }
export type { ModelInfo, ProviderName as ApiProvider }
export type ApiHandlerOptions = Omit<ProviderSettings, "apiProvider" | "id">
export type ApiConfiguration = ProviderSettings
// Anthropic
// https://docs.anthropic.com/en/docs/about-claude/models
export type AnthropicModelId = keyof typeof anthropicModels
export const anthropicDefaultModelId: AnthropicModelId = "claude-3-7-sonnet-20250219"
export const anthropicModels = {
"claude-3-7-sonnet-20250219:thinking": {
maxTokens: 128_000,
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
thinking: true,
},
"claude-3-7-sonnet-20250219": {
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
thinking: false,
},
"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: 1.0,
outputPrice: 5.0,
cacheWritesPrice: 1.25,
cacheReadsPrice: 0.1,
},
"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
// Amazon Bedrock
// https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html
export interface MessageContent {
type: "text" | "image" | "video" | "tool_use" | "tool_result"
text?: string
source?: {
type: "base64"
data: string | Uint8Array // string for Anthropic, Uint8Array for Bedrock
media_type: "image/jpeg" | "image/png" | "image/gif" | "image/webp"
}
// Video specific fields
format?: string
s3Location?: {
uri: string
bucketOwner?: string
}
// Tool use and result fields
toolUseId?: string
name?: string
input?: any
output?: any // Used for tool_result type
}
export type BedrockModelId = keyof typeof bedrockModels
export const bedrockDefaultModelId: BedrockModelId = "anthropic.claude-3-7-sonnet-20250219-v1:0"
export const bedrockDefaultPromptRouterModelId: BedrockModelId = "anthropic.claude-3-sonnet-20240229-v1:0"
// March, 12 2025 - updated prices to match US-West-2 list price shown at https://aws.amazon.com/bedrock/pricing/
// including older models that are part of the default prompt routers AWS enabled for GA of the promot router feature
export const bedrockModels = {
"amazon.nova-pro-v1:0": {
maxTokens: 5000,
contextWindow: 300_000,
supportsImages: true,
supportsComputerUse: false,
supportsPromptCache: true,
inputPrice: 0.8,
outputPrice: 3.2,
cacheWritesPrice: 0.8, // per million tokens
cacheReadsPrice: 0.2, // per million tokens
minTokensPerCachePoint: 1,
maxCachePoints: 1,
cachableFields: ["system"],
},
"amazon.nova-pro-latency-optimized-v1:0": {
maxTokens: 5000,
contextWindow: 300_000,
supportsImages: true,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 1.0,
outputPrice: 4.0,
cacheWritesPrice: 1.0, // per million tokens
cacheReadsPrice: 0.25, // per million tokens
description: "Amazon Nova Pro with latency optimized inference",
},
"amazon.nova-lite-v1:0": {
maxTokens: 5000,
contextWindow: 300_000,
supportsImages: true,
supportsComputerUse: false,
supportsPromptCache: true,
inputPrice: 0.06,
outputPrice: 0.24,
cacheWritesPrice: 0.06, // per million tokens
cacheReadsPrice: 0.015, // per million tokens
minTokensPerCachePoint: 1,
maxCachePoints: 1,
cachableFields: ["system"],
},
"amazon.nova-micro-v1:0": {
maxTokens: 5000,
contextWindow: 128_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: true,
inputPrice: 0.035,
outputPrice: 0.14,
cacheWritesPrice: 0.035, // per million tokens
cacheReadsPrice: 0.00875, // per million tokens
minTokensPerCachePoint: 1,
maxCachePoints: 1,
cachableFields: ["system"],
},
"anthropic.claude-3-7-sonnet-20250219-v1:0": {
maxTokens: 8192,
contextWindow: 200_000,
supportsImages: true,
supportsComputerUse: true,
supportsPromptCache: true,
inputPrice: 3.0,
outputPrice: 15.0,
cacheWritesPrice: 3.75,
cacheReadsPrice: 0.3,
minTokensPerCachePoint: 1024,
maxCachePoints: 4,
cachableFields: ["system", "messages", "tools"],
},
"anthropic.claude-3-5-sonnet-20241022-v2:0": {
maxTokens: 8192,
contextWindow: 200_000,
supportsImages: true,
supportsComputerUse: true,
supportsPromptCache: true,
inputPrice: 3.0,
outputPrice: 15.0,
cacheWritesPrice: 3.75,
cacheReadsPrice: 0.3,
minTokensPerCachePoint: 1024,
maxCachePoints: 4,
cachableFields: ["system", "messages", "tools"],
},
"anthropic.claude-3-5-haiku-20241022-v1:0": {
maxTokens: 8192,
contextWindow: 200_000,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 0.8,
outputPrice: 4.0,
cacheWritesPrice: 1.0,
cacheReadsPrice: 0.08,
minTokensPerCachePoint: 2048,
maxCachePoints: 4,
cachableFields: ["system", "messages", "tools"],
},
"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,
},
"anthropic.claude-2-1-v1:0": {
maxTokens: 4096,
contextWindow: 100_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 8.0,
outputPrice: 24.0,
description: "Claude 2.1",
},
"anthropic.claude-2-0-v1:0": {
maxTokens: 4096,
contextWindow: 100_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 8.0,
outputPrice: 24.0,
description: "Claude 2.0",
},
"anthropic.claude-instant-v1:0": {
maxTokens: 4096,
contextWindow: 100_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.8,
outputPrice: 2.4,
description: "Claude Instant",
},
"deepseek.r1-v1:0": {
maxTokens: 32_768,
contextWindow: 128_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 1.35,
outputPrice: 5.4,
},
"meta.llama3-3-70b-instruct-v1:0": {
maxTokens: 8192,
contextWindow: 128_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.72,
outputPrice: 0.72,
description: "Llama 3.3 Instruct (70B)",
},
"meta.llama3-2-90b-instruct-v1:0": {
maxTokens: 8192,
contextWindow: 128_000,
supportsImages: true,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.72,
outputPrice: 0.72,
description: "Llama 3.2 Instruct (90B)",
},
"meta.llama3-2-11b-instruct-v1:0": {
maxTokens: 8192,
contextWindow: 128_000,
supportsImages: true,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.16,
outputPrice: 0.16,
description: "Llama 3.2 Instruct (11B)",
},
"meta.llama3-2-3b-instruct-v1:0": {
maxTokens: 8192,
contextWindow: 128_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.15,
outputPrice: 0.15,
description: "Llama 3.2 Instruct (3B)",
},
"meta.llama3-2-1b-instruct-v1:0": {
maxTokens: 8192,
contextWindow: 128_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.1,
outputPrice: 0.1,
description: "Llama 3.2 Instruct (1B)",
},
"meta.llama3-1-405b-instruct-v1:0": {
maxTokens: 8192,
contextWindow: 128_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 2.4,
outputPrice: 2.4,
description: "Llama 3.1 Instruct (405B)",
},
"meta.llama3-1-70b-instruct-v1:0": {
maxTokens: 8192,
contextWindow: 128_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.72,
outputPrice: 0.72,
description: "Llama 3.1 Instruct (70B)",
},
"meta.llama3-1-70b-instruct-latency-optimized-v1:0": {
maxTokens: 8192,
contextWindow: 128_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.9,
outputPrice: 0.9,
description: "Llama 3.1 Instruct (70B) (w/ latency optimized inference)",
},
"meta.llama3-1-8b-instruct-v1:0": {
maxTokens: 8192,
contextWindow: 8_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.22,
outputPrice: 0.22,
description: "Llama 3.1 Instruct (8B)",
},
"meta.llama3-70b-instruct-v1:0": {
maxTokens: 2048,
contextWindow: 8_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 2.65,
outputPrice: 3.5,
},
"meta.llama3-8b-instruct-v1:0": {
maxTokens: 2048,
contextWindow: 4_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.3,
outputPrice: 0.6,
},
"amazon.titan-text-lite-v1:0": {
maxTokens: 4096,
contextWindow: 8_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.15,
outputPrice: 0.2,
description: "Amazon Titan Text Lite",
},
"amazon.titan-text-express-v1:0": {
maxTokens: 4096,
contextWindow: 8_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.2,
outputPrice: 0.6,
description: "Amazon Titan Text Express",
},
"amazon.titan-text-embeddings-v1:0": {
maxTokens: 8192,
contextWindow: 8_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.1,
description: "Amazon Titan Text Embeddings",
},
"amazon.titan-text-embeddings-v2:0": {
maxTokens: 8192,
contextWindow: 8_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.02,
description: "Amazon Titan Text Embeddings V2",
},
} as const satisfies Record<string, ModelInfo>
// Glama
// https://glama.ai/models
export const glamaDefaultModelId = "anthropic/claude-3-7-sonnet"
export const glamaDefaultModelInfo: 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:
"Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. Claude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks. Read more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)",
}
// Requesty
// https://requesty.ai/router-2
export const requestyDefaultModelId = "anthropic/claude-3-7-sonnet-latest"
export const requestyDefaultModelInfo: 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:
"Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. Claude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks. Read more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)",
}
// OpenRouter
// https://openrouter.ai/models?order=newest&supported_parameters=tools
export const openRouterDefaultModelId = "anthropic/claude-3.7-sonnet"
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:
"Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. Claude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks. Read more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)",
}
// 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-3-7-sonnet@20250219"
export const vertexModels = {
"gemini-2.5-flash-preview-04-17:thinking": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0.15,
outputPrice: 3.5,
thinking: true,
maxThinkingTokens: 24_576,
},
"gemini-2.5-flash-preview-04-17": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0.15,
outputPrice: 0.6,
thinking: false,
},
"gemini-2.5-pro-preview-03-25": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 2.5,
outputPrice: 15,
},
"gemini-2.5-pro-exp-03-25": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
"gemini-2.0-pro-exp-02-05": {
maxTokens: 8192,
contextWindow: 2_097_152,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
"gemini-2.0-flash-001": {
maxTokens: 8192,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0.15,
outputPrice: 0.6,
},
"gemini-2.0-flash-lite-001": {
maxTokens: 8192,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0.075,
outputPrice: 0.3,
},
"gemini-2.0-flash-thinking-exp-01-21": {
maxTokens: 8192,
contextWindow: 32_768,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
"gemini-1.5-flash-002": {
maxTokens: 8192,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0.075,
outputPrice: 0.3,
},
"gemini-1.5-pro-002": {
maxTokens: 8192,
contextWindow: 2_097_152,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 1.25,
outputPrice: 5,
},
"claude-3-7-sonnet@20250219:thinking": {
maxTokens: 64_000,
contextWindow: 200_000,
supportsImages: true,
supportsComputerUse: true,
supportsPromptCache: true,
inputPrice: 3.0,
outputPrice: 15.0,
cacheWritesPrice: 3.75,
cacheReadsPrice: 0.3,
thinking: true,
},
"claude-3-7-sonnet@20250219": {
maxTokens: 8192,
contextWindow: 200_000,
supportsImages: true,
supportsComputerUse: true,
supportsPromptCache: true,
inputPrice: 3.0,
outputPrice: 15.0,
cacheWritesPrice: 3.75,
cacheReadsPrice: 0.3,
thinking: false,
},
"claude-3-5-sonnet-v2@20241022": {
maxTokens: 8192,
contextWindow: 200_000,
supportsImages: true,
supportsComputerUse: true,
supportsPromptCache: true,
inputPrice: 3.0,
outputPrice: 15.0,
cacheWritesPrice: 3.75,
cacheReadsPrice: 0.3,
},
"claude-3-5-sonnet@20240620": {
maxTokens: 8192,
contextWindow: 200_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 3.0,
outputPrice: 15.0,
cacheWritesPrice: 3.75,
cacheReadsPrice: 0.3,
},
"claude-3-5-haiku@20241022": {
maxTokens: 8192,
contextWindow: 200_000,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 1.0,
outputPrice: 5.0,
cacheWritesPrice: 1.25,
cacheReadsPrice: 0.1,
},
"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>
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-001"
export const geminiModels = {
"gemini-2.5-flash-preview-04-17:thinking": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0.15,
outputPrice: 3.5,
thinking: true,
maxThinkingTokens: 24_576,
},
"gemini-2.5-flash-preview-04-17": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0.15,
outputPrice: 0.6,
thinking: false,
},
"gemini-2.5-pro-exp-03-25": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
"gemini-2.5-pro-preview-03-25": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
outputPrice: 15,
cacheReadsPrice: 0.625,
cacheWritesPrice: 4.5,
tiers: [
{
contextWindow: 200_000,
inputPrice: 1.25,
outputPrice: 10,
cacheReadsPrice: 0.31,
},
{
contextWindow: Infinity,
inputPrice: 2.5,
outputPrice: 15,
cacheReadsPrice: 0.625,
},
],
},
"gemini-2.0-flash-001": {
maxTokens: 8192,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.1,
outputPrice: 0.4,
cacheReadsPrice: 0.025,
cacheWritesPrice: 1.0,
},
"gemini-2.0-flash-lite-preview-02-05": {
maxTokens: 8192,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
"gemini-2.0-pro-exp-02-05": {
maxTokens: 8192,
contextWindow: 2_097_152,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
"gemini-2.0-flash-thinking-exp-01-21": {
maxTokens: 65_536,
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-1.5-flash-002": {
maxTokens: 8192,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.15, // This is the pricing for prompts above 128k tokens.
outputPrice: 0.6,
cacheReadsPrice: 0.0375,
cacheWritesPrice: 1.0,
tiers: [
{
contextWindow: 128_000,
inputPrice: 0.075,
outputPrice: 0.3,
cacheReadsPrice: 0.01875,
},
{
contextWindow: Infinity,
inputPrice: 0.15,
outputPrice: 0.6,
cacheReadsPrice: 0.0375,
},
],
},
"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,
},
"gemini-exp-1206": {
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-4.1"
export const openAiNativeModels = {
"gpt-4.1": {
maxTokens: 32_768,
contextWindow: 1_047_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2,
outputPrice: 8,
cacheReadsPrice: 0.5,
},
"gpt-4.1-mini": {
maxTokens: 32_768,
contextWindow: 1_047_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.4,
outputPrice: 1.6,
cacheReadsPrice: 0.1,
},
"gpt-4.1-nano": {
maxTokens: 32_768,
contextWindow: 1_047_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.1,
outputPrice: 0.4,
cacheReadsPrice: 0.025,
},
o3: {
maxTokens: 100_000,
contextWindow: 200_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 10.0,
outputPrice: 40.0,
cacheReadsPrice: 2.5,
reasoningEffort: "medium",
},
"o3-high": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 10.0,
outputPrice: 40.0,
cacheReadsPrice: 2.5,
reasoningEffort: "high",
},
"o3-low": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 10.0,
outputPrice: 40.0,
cacheReadsPrice: 2.5,
reasoningEffort: "low",
},
"o4-mini": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 1.1,
outputPrice: 4.4,
cacheReadsPrice: 0.275,
reasoningEffort: "medium",
},
"o4-mini-high": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 1.1,
outputPrice: 4.4,
cacheReadsPrice: 0.275,
reasoningEffort: "high",
},
"o4-mini-low": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 1.1,
outputPrice: 4.4,
cacheReadsPrice: 0.275,
reasoningEffort: "low",
},
"o3-mini": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 1.1,
outputPrice: 4.4,
cacheReadsPrice: 0.55,
reasoningEffort: "medium",
},
"o3-mini-high": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 1.1,
outputPrice: 4.4,
cacheReadsPrice: 0.55,
reasoningEffort: "high",
},
"o3-mini-low": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 1.1,
outputPrice: 4.4,
cacheReadsPrice: 0.55,
reasoningEffort: "low",
},
o1: {
maxTokens: 100_000,
contextWindow: 200_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 15,
outputPrice: 60,
cacheReadsPrice: 7.5,
},
"o1-preview": {
maxTokens: 32_768,
contextWindow: 128_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 15,
outputPrice: 60,
cacheReadsPrice: 7.5,
},
"o1-mini": {
maxTokens: 65_536,
contextWindow: 128_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 1.1,
outputPrice: 4.4,
cacheReadsPrice: 0.55,
},
"gpt-4.5-preview": {
maxTokens: 16_384,
contextWindow: 128_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 75,
outputPrice: 150,
cacheReadsPrice: 37.5,
},
"gpt-4o": {
maxTokens: 16_384,
contextWindow: 128_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.5,
outputPrice: 10,
cacheReadsPrice: 1.25,
},
"gpt-4o-mini": {
maxTokens: 16_384,
contextWindow: 128_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.15,
outputPrice: 0.6,
cacheReadsPrice: 0.075,
},
} as const satisfies Record<string, ModelInfo>
// DeepSeek
// https://platform.deepseek.com/docs/api
export type DeepSeekModelId = keyof typeof deepSeekModels
export const deepSeekDefaultModelId: DeepSeekModelId = "deepseek-chat"
export const deepSeekModels = {
"deepseek-chat": {
maxTokens: 8192,
contextWindow: 64_000,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 0.27, // $0.27 per million tokens (cache miss)
outputPrice: 1.1, // $1.10 per million tokens
cacheWritesPrice: 0.27, // $0.27 per million tokens (cache miss)
cacheReadsPrice: 0.07, // $0.07 per million tokens (cache hit).
description: `DeepSeek-V3 achieves a significant breakthrough in inference speed over previous models. It tops the leaderboard among open-source models and rivals the most advanced closed-source models globally.`,
},
"deepseek-reasoner": {
maxTokens: 8192,
contextWindow: 64_000,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 0.55, // $0.55 per million tokens (cache miss)
outputPrice: 2.19, // $2.19 per million tokens
cacheWritesPrice: 0.55, // $0.55 per million tokens (cache miss)
cacheReadsPrice: 0.14, // $0.14 per million tokens (cache hit)
description: `DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. Supports Chain of Thought reasoning with up to 32K tokens.`,
},
} 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"
// Mistral
// https://docs.mistral.ai/getting-started/models/models_overview/
export type MistralModelId = keyof typeof mistralModels
export const mistralDefaultModelId: MistralModelId = "codestral-latest"
export const mistralModels = {
"codestral-latest": {
maxTokens: 256_000,
contextWindow: 256_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.3,
outputPrice: 0.9,
},
"mistral-large-latest": {
maxTokens: 131_000,
contextWindow: 131_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 2.0,
outputPrice: 6.0,
},
"ministral-8b-latest": {
maxTokens: 131_000,
contextWindow: 131_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.1,
outputPrice: 0.1,
},
"ministral-3b-latest": {
maxTokens: 131_000,
contextWindow: 131_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.04,
outputPrice: 0.04,
},
"mistral-small-latest": {
maxTokens: 32_000,
contextWindow: 32_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.2,
outputPrice: 0.6,
},
"pixtral-large-latest": {
maxTokens: 131_000,
contextWindow: 131_000,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 2.0,
outputPrice: 6.0,
},
} as const satisfies Record<string, ModelInfo>
// Unbound Security
// https://www.unboundsecurity.ai/ai-gateway
export const unboundDefaultModelId = "anthropic/claude-3-5-sonnet-20241022"
export const unboundDefaultModelInfo: ModelInfo = {
maxTokens: 8192,
contextWindow: 200_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 3.0,
outputPrice: 15.0,
cacheWritesPrice: 3.75,
cacheReadsPrice: 0.3,
}
// xAI
// https://docs.x.ai/docs/api-reference
export type XAIModelId = keyof typeof xaiModels
export const xaiDefaultModelId: XAIModelId = "grok-3-beta"
export const xaiModels = {
"grok-3-beta": {
maxTokens: 8192,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 3.0,
outputPrice: 15.0,
description: "xAI's Grok-3 beta model with 131K context window",
},
"grok-3-fast-beta": {
maxTokens: 8192,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 5.0,
outputPrice: 25.0,
description: "xAI's Grok-3 fast beta model with 131K context window",
},
"grok-3-mini-beta": {
maxTokens: 8192,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.3,
outputPrice: 0.5,
description: "xAI's Grok-3 mini beta model with 131K context window",
},
"grok-3-mini-fast-beta": {
maxTokens: 8192,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.6,
outputPrice: 4.0,
description: "xAI's Grok-3 mini fast beta model with 131K context window",
},
"grok-2-latest": {
maxTokens: 8192,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 2.0,
outputPrice: 10.0,
description: "xAI's Grok-2 model - latest version with 131K context window",
},
"grok-2": {
maxTokens: 8192,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 2.0,
outputPrice: 10.0,
description: "xAI's Grok-2 model with 131K context window",
},
"grok-2-1212": {
maxTokens: 8192,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 2.0,
outputPrice: 10.0,
description: "xAI's Grok-2 model (version 1212) with 131K context window",
},
"grok-2-vision-latest": {
maxTokens: 8192,
contextWindow: 32768,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 2.0,
outputPrice: 10.0,
description: "xAI's Grok-2 Vision model - latest version with image support and 32K context window",
},
"grok-2-vision": {
maxTokens: 8192,
contextWindow: 32768,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 2.0,
outputPrice: 10.0,
description: "xAI's Grok-2 Vision model with image support and 32K context window",
},
"grok-2-vision-1212": {
maxTokens: 8192,
contextWindow: 32768,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 2.0,
outputPrice: 10.0,
description: "xAI's Grok-2 Vision model (version 1212) with image support and 32K context window",
},
"grok-vision-beta": {
maxTokens: 8192,
contextWindow: 8192,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 5.0,
outputPrice: 15.0,
description: "xAI's Grok Vision Beta model with image support and 8K context window",
},
"grok-beta": {
maxTokens: 8192,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 5.0,
outputPrice: 15.0,
description: "xAI's Grok Beta model (legacy) with 131K context window",
},
} as const satisfies Record<string, ModelInfo>
export type VscodeLlmModelId = keyof typeof vscodeLlmModels
export const vscodeLlmDefaultModelId: VscodeLlmModelId = "claude-3.5-sonnet"
export const vscodeLlmModels = {
"gpt-3.5-turbo": {
contextWindow: 12114,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "gpt-3.5-turbo",
version: "gpt-3.5-turbo-0613",
name: "GPT 3.5 Turbo",
supportsToolCalling: true,
maxInputTokens: 12114,
},
"gpt-4o-mini": {
contextWindow: 12115,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "gpt-4o-mini",
version: "gpt-4o-mini-2024-07-18",
name: "GPT-4o mini",
supportsToolCalling: true,
maxInputTokens: 12115,
},
"gpt-4": {
contextWindow: 28501,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "gpt-4",
version: "gpt-4-0613",
name: "GPT 4",
supportsToolCalling: true,
maxInputTokens: 28501,
},
"gpt-4-0125-preview": {
contextWindow: 63826,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "gpt-4-turbo",
version: "gpt-4-0125-preview",
name: "GPT 4 Turbo",
supportsToolCalling: true,
maxInputTokens: 63826,
},
"gpt-4o": {
contextWindow: 63827,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "gpt-4o",
version: "gpt-4o-2024-11-20",
name: "GPT-4o",
supportsToolCalling: true,
maxInputTokens: 63827,
},
o1: {
contextWindow: 19827,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "o1-ga",
version: "o1-2024-12-17",
name: "o1 (Preview)",
supportsToolCalling: true,
maxInputTokens: 19827,
},
"o3-mini": {
contextWindow: 63827,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "o3-mini",
version: "o3-mini-2025-01-31",
name: "o3-mini",
supportsToolCalling: true,
maxInputTokens: 63827,
},
"claude-3.5-sonnet": {
contextWindow: 81638,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "claude-3.5-sonnet",
version: "claude-3.5-sonnet",
name: "Claude 3.5 Sonnet",
supportsToolCalling: true,
maxInputTokens: 81638,
},
"claude-3.7-sonnet": {
contextWindow: 89827,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "claude-3.7-sonnet",
version: "claude-3.7-sonnet",
name: "Claude 3.7 Sonnet",
supportsToolCalling: true,
maxInputTokens: 89827,
},
"claude-3.7-sonnet-thought": {
contextWindow: 89827,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "claude-3.7-sonnet-thought",
version: "claude-3.7-sonnet-thought",
name: "Claude 3.7 Sonnet Thinking",
supportsToolCalling: false,
maxInputTokens: 89827,
thinking: true,
},
"gemini-2.0-flash-001": {
contextWindow: 127827,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "gemini-2.0-flash",
version: "gemini-2.0-flash-001",
name: "Gemini 2.0 Flash",
supportsToolCalling: false,
maxInputTokens: 127827,
},
"gemini-2.5-pro": {
contextWindow: 63830,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "gemini-2.5-pro",
version: "gemini-2.5-pro-preview-03-25",
name: "Gemini 2.5 Pro (Preview)",
supportsToolCalling: true,
maxInputTokens: 63830,
},
"o4-mini": {
contextWindow: 111446,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "o4-mini",
version: "o4-mini-2025-04-16",
name: "o4-mini (Preview)",
supportsToolCalling: true,
maxInputTokens: 111446,
},
"gpt-4.1": {
contextWindow: 111446,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
family: "gpt-4.1",
version: "gpt-4.1-2025-04-14",
name: "GPT-4.1 (Preview)",
supportsToolCalling: true,
maxInputTokens: 111446,
},
} as const satisfies Record<
string,
ModelInfo & {
family: string
version: string
name: string
supportsToolCalling: boolean
maxInputTokens: number
}
>
Reference in a new issue View git blame Copy permalink