feat(vertex): Add prompt caching support for Claude on Vertex AI (#1885)

* feat(vertex): Add prompt caching support for Claude on Vertex AI

* Remove countTokens update claude 3.7

* claude-3-7-sonnet@20250219 support in Vertex AI as default model
This commit is contained in:
Doug Daniels 2025-02-27 00:28:02 -06:00 committed by GitHub
parent d58c947c41
commit a229b8ce9d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 166 additions and 430 deletions

View file

@ -0,0 +1,5 @@
---
"claude-dev": minor
---
feat(vertex): Add prompt caching support for Claude on Vertex AI

443
package-lock.json generated
View file

@ -11,7 +11,7 @@
"dependencies": {
"@anthropic-ai/bedrock-sdk": "^0.10.2",
"@anthropic-ai/sdk": "^0.26.0",
"@anthropic-ai/vertex-sdk": "^0.4.1",
"@anthropic-ai/vertex-sdk": "^0.6.4",
"@google/generative-ai": "^0.18.0",
"@mistralai/mistralai": "^1.5.0",
"@modelcontextprotocol/sdk": "^1.0.1",
@ -118,14 +118,39 @@
}
},
"node_modules/@anthropic-ai/vertex-sdk": {
"version": "0.4.1",
"resolved": "https://registry.npmjs.org/@anthropic-ai/vertex-sdk/-/vertex-sdk-0.4.1.tgz",
"integrity": "sha512-RT/2CWzqyAcJDZWxnNc1mXa7XiiHDaQ9aknfW4mIDw6zE+Zj/R2vCKpTb0dIwrmHYNOyKQNaD7Z1ynDt9oXFWA==",
"version": "0.6.4",
"resolved": "https://registry.npmjs.org/@anthropic-ai/vertex-sdk/-/vertex-sdk-0.6.4.tgz",
"integrity": "sha512-rMBlO2jF53TfMRmsQMm1bPO2JRUh4jYddjq/OJLj8DSAkfbCrNWhc0yhDed6oLYJg5s+VpDbvlPzMggqHhTfMw==",
"license": "MIT",
"dependencies": {
"@anthropic-ai/sdk": ">=0.14 <1",
"@anthropic-ai/sdk": ">=0.35 <1",
"google-auth-library": "^9.4.2"
}
},
"node_modules/@anthropic-ai/vertex-sdk/node_modules/@anthropic-ai/sdk": {
"version": "0.36.3",
"resolved": "https://registry.npmjs.org/@anthropic-ai/sdk/-/sdk-0.36.3.tgz",
"integrity": "sha512-+c0mMLxL/17yFZ4P5+U6bTWiCSFZUKJddrv01ud2aFBWnTPLdRncYV76D3q1tqfnL7aCnhRtykFnoCFzvr4U3Q==",
"license": "MIT",
"dependencies": {
"@types/node": "^18.11.18",
"@types/node-fetch": "^2.6.4",
"abort-controller": "^3.0.0",
"agentkeepalive": "^4.2.1",
"form-data-encoder": "1.7.2",
"formdata-node": "^4.3.2",
"node-fetch": "^2.6.7"
}
},
"node_modules/@anthropic-ai/vertex-sdk/node_modules/@types/node": {
"version": "18.19.76",
"resolved": "https://registry.npmjs.org/@types/node/-/node-18.19.76.tgz",
"integrity": "sha512-yvR7Q9LdPz2vGpmpJX5LolrgRdWvB67MJKDPSgIIzpFbaf9a1j/f5DnLp5VDyHGMR0QZHlTr1afsD87QCXFHKw==",
"license": "MIT",
"dependencies": {
"undici-types": "~5.26.4"
}
},
"node_modules/@aws-crypto/crc32": {
"version": "5.2.0",
"resolved": "https://registry.npmjs.org/@aws-crypto/crc32/-/crc32-5.2.0.tgz",
@ -2534,74 +2559,6 @@
"url": "https://github.com/prettier/prettier?sponsor=1"
}
},
"node_modules/@esbuild/aix-ppc64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.25.0.tgz",
"integrity": "sha512-O7vun9Sf8DFjH2UtqK8Ku3LkquL9SZL8OLY1T5NZkA34+wG3OQF7cl4Ql8vdNzM6fzBbYfLaiRLIOZ+2FOCgBQ==",
"cpu": [
"ppc64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"aix"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/android-arm": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.25.0.tgz",
"integrity": "sha512-PTyWCYYiU0+1eJKmw21lWtC+d08JDZPQ5g+kFyxP0V+es6VPPSUhM6zk8iImp2jbV6GwjX4pap0JFbUQN65X1g==",
"cpu": [
"arm"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"android"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/android-arm64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.25.0.tgz",
"integrity": "sha512-grvv8WncGjDSyUBjN9yHXNt+cq0snxXbDxy5pJtzMKGmmpPxeAmAhWxXI+01lU5rwZomDgD3kJwulEnhTRUd6g==",
"cpu": [
"arm64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"android"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/android-x64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.25.0.tgz",
"integrity": "sha512-m/ix7SfKG5buCnxasr52+LI78SQ+wgdENi9CqyCXwjVR2X4Jkz+BpC3le3AoBPYTC9NHklwngVXvbJ9/Akhrfg==",
"cpu": [
"x64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"android"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/darwin-arm64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.25.0.tgz",
@ -2619,346 +2576,6 @@
"node": ">=18"
}
},
"node_modules/@esbuild/darwin-x64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.25.0.tgz",
"integrity": "sha512-DgDaYsPWFTS4S3nWpFcMn/33ZZwAAeAFKNHNa1QN0rI4pUjgqf0f7ONmXf6d22tqTY+H9FNdgeaAa+YIFUn2Rg==",
"cpu": [
"x64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"darwin"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/freebsd-arm64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.25.0.tgz",
"integrity": "sha512-VN4ocxy6dxefN1MepBx/iD1dH5K8qNtNe227I0mnTRjry8tj5MRk4zprLEdG8WPyAPb93/e4pSgi1SoHdgOa4w==",
"cpu": [
"arm64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"freebsd"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/freebsd-x64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.25.0.tgz",
"integrity": "sha512-mrSgt7lCh07FY+hDD1TxiTyIHyttn6vnjesnPoVDNmDfOmggTLXRv8Id5fNZey1gl/V2dyVK1VXXqVsQIiAk+A==",
"cpu": [
"x64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"freebsd"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/linux-arm": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.25.0.tgz",
"integrity": "sha512-vkB3IYj2IDo3g9xX7HqhPYxVkNQe8qTK55fraQyTzTX/fxaDtXiEnavv9geOsonh2Fd2RMB+i5cbhu2zMNWJwg==",
"cpu": [
"arm"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/linux-arm64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.25.0.tgz",
"integrity": "sha512-9QAQjTWNDM/Vk2bgBl17yWuZxZNQIF0OUUuPZRKoDtqF2k4EtYbpyiG5/Dk7nqeK6kIJWPYldkOcBqjXjrUlmg==",
"cpu": [
"arm64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/linux-ia32": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.25.0.tgz",
"integrity": "sha512-43ET5bHbphBegyeqLb7I1eYn2P/JYGNmzzdidq/w0T8E2SsYL1U6un2NFROFRg1JZLTzdCoRomg8Rvf9M6W6Gg==",
"cpu": [
"ia32"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/linux-loong64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.25.0.tgz",
"integrity": "sha512-fC95c/xyNFueMhClxJmeRIj2yrSMdDfmqJnyOY4ZqsALkDrrKJfIg5NTMSzVBr5YW1jf+l7/cndBfP3MSDpoHw==",
"cpu": [
"loong64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/linux-mips64el": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.25.0.tgz",
"integrity": "sha512-nkAMFju7KDW73T1DdH7glcyIptm95a7Le8irTQNO/qtkoyypZAnjchQgooFUDQhNAy4iu08N79W4T4pMBwhPwQ==",
"cpu": [
"mips64el"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/linux-ppc64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.25.0.tgz",
"integrity": "sha512-NhyOejdhRGS8Iwv+KKR2zTq2PpysF9XqY+Zk77vQHqNbo/PwZCzB5/h7VGuREZm1fixhs4Q/qWRSi5zmAiO4Fw==",
"cpu": [
"ppc64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/linux-riscv64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.25.0.tgz",
"integrity": "sha512-5S/rbP5OY+GHLC5qXp1y/Mx//e92L1YDqkiBbO9TQOvuFXM+iDqUNG5XopAnXoRH3FjIUDkeGcY1cgNvnXp/kA==",
"cpu": [
"riscv64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/linux-s390x": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.25.0.tgz",
"integrity": "sha512-XM2BFsEBz0Fw37V0zU4CXfcfuACMrppsMFKdYY2WuTS3yi8O1nFOhil/xhKTmE1nPmVyvQJjJivgDT+xh8pXJA==",
"cpu": [
"s390x"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/linux-x64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.25.0.tgz",
"integrity": "sha512-9yl91rHw/cpwMCNytUDxwj2XjFpxML0y9HAOH9pNVQDpQrBxHy01Dx+vaMu0N1CKa/RzBD2hB4u//nfc+Sd3Cw==",
"cpu": [
"x64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/netbsd-arm64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.25.0.tgz",
"integrity": "sha512-RuG4PSMPFfrkH6UwCAqBzauBWTygTvb1nxWasEJooGSJ/NwRw7b2HOwyRTQIU97Hq37l3npXoZGYMy3b3xYvPw==",
"cpu": [
"arm64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"netbsd"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/netbsd-x64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.25.0.tgz",
"integrity": "sha512-jl+qisSB5jk01N5f7sPCsBENCOlPiS/xptD5yxOx2oqQfyourJwIKLRA2yqWdifj3owQZCL2sn6o08dBzZGQzA==",
"cpu": [
"x64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"netbsd"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/openbsd-arm64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.25.0.tgz",
"integrity": "sha512-21sUNbq2r84YE+SJDfaQRvdgznTD8Xc0oc3p3iW/a1EVWeNj/SdUCbm5U0itZPQYRuRTW20fPMWMpcrciH2EJw==",
"cpu": [
"arm64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"openbsd"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/openbsd-x64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.25.0.tgz",
"integrity": "sha512-2gwwriSMPcCFRlPlKx3zLQhfN/2WjJ2NSlg5TKLQOJdV0mSxIcYNTMhk3H3ulL/cak+Xj0lY1Ym9ysDV1igceg==",
"cpu": [
"x64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"openbsd"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/sunos-x64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.25.0.tgz",
"integrity": "sha512-bxI7ThgLzPrPz484/S9jLlvUAHYMzy6I0XiU1ZMeAEOBcS0VePBFxh1JjTQt3Xiat5b6Oh4x7UC7IwKQKIJRIg==",
"cpu": [
"x64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"sunos"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/win32-arm64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.25.0.tgz",
"integrity": "sha512-ZUAc2YK6JW89xTbXvftxdnYy3m4iHIkDtK3CLce8wg8M2L+YZhIvO1DKpxrd0Yr59AeNNkTiic9YLf6FTtXWMw==",
"cpu": [
"arm64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"win32"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/win32-ia32": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.25.0.tgz",
"integrity": "sha512-eSNxISBu8XweVEWG31/JzjkIGbGIJN/TrRoiSVZwZ6pkC6VX4Im/WV2cz559/TXLcYbcrDN8JtKgd9DJVIo8GA==",
"cpu": [
"ia32"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"win32"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@esbuild/win32-x64": {
"version": "0.25.0",
"resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.25.0.tgz",
"integrity": "sha512-ZENoHJBxA20C2zFzh6AI4fT6RraMzjYw4xKWemRTRmRVtN9c5DcH9r/f2ihEkMjOW5eGgrwCslG/+Y/3bL+DHQ==",
"cpu": [
"x64"
],
"dev": true,
"license": "MIT",
"optional": true,
"os": [
"win32"
],
"engines": {
"node": ">=18"
}
},
"node_modules/@eslint-community/eslint-utils": {
"version": "4.4.0",
"resolved": "https://registry.npmjs.org/@eslint-community/eslint-utils/-/eslint-utils-4.4.0.tgz",

View file

@ -239,7 +239,7 @@
"dependencies": {
"@anthropic-ai/bedrock-sdk": "^0.10.2",
"@anthropic-ai/sdk": "^0.26.0",
"@anthropic-ai/vertex-sdk": "^0.4.1",
"@anthropic-ai/vertex-sdk": "^0.6.4",
"@google/generative-ai": "^0.18.0",
"@mistralai/mistralai": "^1.5.0",
"@modelcontextprotocol/sdk": "^1.0.1",

View file

@ -21,14 +21,113 @@ export class VertexHandler implements ApiHandler {
@withRetry()
async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
const stream = await this.client.messages.create({
model: this.getModel().id,
max_tokens: this.getModel().info.maxTokens || 8192,
temperature: 0,
system: systemPrompt,
messages,
stream: true,
})
const model = this.getModel()
const modelId = model.id
let stream
switch (modelId) {
case "claude-3-7-sonnet@20250219":
case "claude-3-5-sonnet-v2@20241022":
case "claude-3-5-sonnet@20240620":
case "claude-3-5-haiku@20241022":
case "claude-3-opus@20240229":
case "claude-3-haiku@20240307": {
// Find indices of user messages for cache control
const userMsgIndices = messages.reduce(
(acc, msg, index) => (msg.role === "user" ? [...acc, index] : acc),
[] as number[],
)
const lastUserMsgIndex = userMsgIndices[userMsgIndices.length - 1] ?? -1
const secondLastMsgUserIndex = userMsgIndices[userMsgIndices.length - 2] ?? -1
stream = await this.client.beta.messages.create(
{
model: modelId,
max_tokens: model.info.maxTokens || 8192,
temperature: 0,
system: [
{
text: systemPrompt,
type: "text",
cache_control: { type: "ephemeral" },
},
],
messages: messages.map((message, index) => {
if (index === lastUserMsgIndex || index === secondLastMsgUserIndex) {
return {
...message,
content:
typeof message.content === "string"
? [
{
type: "text",
text: message.content,
cache_control: {
type: "ephemeral",
},
},
]
: message.content.map((content, contentIndex) =>
contentIndex === message.content.length - 1
? {
...content,
cache_control: {
type: "ephemeral",
},
}
: content,
),
}
}
return {
...message,
content:
typeof message.content === "string"
? [
{
type: "text",
text: message.content,
},
]
: message.content,
}
}),
stream: true,
},
{
headers: {},
},
)
break
}
default: {
stream = await this.client.beta.messages.create({
model: modelId,
max_tokens: model.info.maxTokens || 8192,
temperature: 0,
system: [
{
text: systemPrompt,
type: "text",
},
],
messages: messages.map((message) => ({
...message,
content:
typeof message.content === "string"
? [
{
type: "text",
text: message.content,
},
]
: message.content,
})),
stream: true,
})
break
}
}
for await (const chunk of stream) {
switch (chunk.type) {
case "message_start":
@ -37,6 +136,8 @@ export class VertexHandler implements ApiHandler {
type: "usage",
inputTokens: usage.input_tokens || 0,
outputTokens: usage.output_tokens || 0,
cacheWriteTokens: usage.cache_creation_input_tokens || undefined,
cacheReadTokens: usage.cache_read_input_tokens || undefined,
}
break
case "message_delta":
@ -46,7 +147,8 @@ export class VertexHandler implements ApiHandler {
outputTokens: chunk.usage.output_tokens || 0,
}
break
case "message_stop":
break
case "content_block_start":
switch (chunk.content_block.type) {
case "text":
@ -73,6 +175,8 @@ export class VertexHandler implements ApiHandler {
break
}
break
case "content_block_stop":
break
}
}
}

View file

@ -219,9 +219,9 @@ export const openRouterDefaultModelInfo: ModelInfo = {
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. \n\nClaude 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.\n\nRead 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
// https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models
export type VertexModelId = keyof typeof vertexModels
export const vertexDefaultModelId: VertexModelId = "claude-3-7-sonnet@20250219"
export const vertexModels = {
@ -230,7 +230,7 @@ export const vertexModels = {
contextWindow: 200_000,
supportsImages: true,
supportsComputerUse: true,
supportsPromptCache: false,
supportsPromptCache: true,
inputPrice: 3.0,
outputPrice: 15.0,
},
@ -239,41 +239,51 @@ export const vertexModels = {
contextWindow: 200_000,
supportsImages: true,
supportsComputerUse: true,
supportsPromptCache: false,
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: false,
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: 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: false,
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: false,
supportsPromptCache: true,
inputPrice: 0.25,
outputPrice: 1.25,
cacheWritesPrice: 0.3,
cacheReadsPrice: 0.03,
},
} as const satisfies Record<string, ModelInfo>