@anthropic-ai/sdk
Advanced tools
This library provides convenient access to the Anthropic REST API from server-side TypeScript or JavaScript.
The REST API documentation can be found on docs.anthropic.com. The full API of this library can be found in api.md.
npm install @anthropic-ai/sdk
The full API of this library can be found in api.md.
import Anthropic from '@anthropic-ai/sdk';
const client = new Anthropic({
apiKey: process.env['ANTHROPIC_API_KEY'], // This is the default and can be omitted
});
async function main() {
const message = await client.messages.create({
max_tokens: 1024,
messages: [{ role: 'user', content: 'Hello, Claude' }],
model: 'claude-3-5-sonnet-latest',
});
console.log(message.content);
}
main();
We provide support for streaming responses using Server Sent Events (SSE).
import Anthropic from '@anthropic-ai/sdk';
const client = new Anthropic();
const stream = await client.messages.create({
max_tokens: 1024,
messages: [{ role: 'user', content: 'Hello, Claude' }],
model: 'claude-3-5-sonnet-latest',
stream: true,
});
for await (const messageStreamEvent of stream) {
console.log(messageStreamEvent.type);
}
If you need to cancel a stream, you can break from the loop
or call stream.controller.abort().
This library includes TypeScript definitions for all request params and response fields. You may import and use them like so:
import Anthropic from '@anthropic-ai/sdk';
const client = new Anthropic({
apiKey: process.env['ANTHROPIC_API_KEY'], // This is the default and can be omitted
});
async function main() {
const params: Anthropic.MessageCreateParams = {
max_tokens: 1024,
messages: [{ role: 'user', content: 'Hello, Claude' }],
model: 'claude-3-5-sonnet-latest',
};
const message: Anthropic.Message = await client.messages.create(params);
}
main();
Documentation for each method, request param, and response field are available in docstrings and will appear on hover in most modern editors.
You can see the exact usage for a given request through the usage response property, e.g.
const message = await client.messages.create(...)
console.log(message.usage)
// { input_tokens: 25, output_tokens: 13 }
This library provides several conveniences for streaming messages, for example:
import Anthropic from '@anthropic-ai/sdk';
const anthropic = new Anthropic();
async function main() {
const stream = anthropic.messages
.stream({
model: 'claude-3-5-sonnet-latest',
max_tokens: 1024,
messages: [
{
role: 'user',
content: 'Say hello there!',
},
],
})
.on('text', (text) => {
console.log(text);
});
const message = await stream.finalMessage();
console.log(message);
}
main();
Streaming with client.messages.stream(...) exposes various helpers for your convenience including event handlers and accumulation.
Alternatively, you can use client.messages.create({ ..., stream: true }) which only returns an async iterable of the events in the stream and thus uses less memory (it does not build up a final message object for you).
This SDK provides beta support for the Message Batches API under the client.beta.messages.batches namespace.
Message Batches takes an array of requests, where each object has a custom_id identifier, and the exact same request params as the standard Messages API:
await anthropic.beta.messages.batches.create({
requests: [
{
custom_id: 'my-first-request',
params: {
model: 'claude-3-5-sonnet-latest',
max_tokens: 1024,
messages: [{ role: 'user', content: 'Hello, world' }],
},
},
{
custom_id: 'my-second-request',
params: {
model: 'claude-3-5-sonnet-latest',
max_tokens: 1024,
messages: [{ role: 'user', content: 'Hi again, friend' }],
},
},
],
});
Once a Message Batch has been processed, indicated by .processing_status === 'ended', you can access the results with .batches.results()
const results = await anthropic.beta.messages.batches.results(batch_id);
for await (const entry of results) {
if (entry.result.type === 'succeeded') {
console.log(entry.result.message.content)
}
}
This SDK provides beta support for tool use, aka function calling. More details can be found in the documentation.
We provide support for the Anthropic Bedrock API through a separate package.
When the library is unable to connect to the API,
or if the API returns a non-success status code (i.e., 4xx or 5xx response),
a subclass of APIError will be thrown:
async function main() {
const message = await client.messages
.create({
max_tokens: 1024,
messages: [{ role: 'user', content: 'Hello, Claude' }],
model: 'claude-3-5-sonnet-latest',
})
.catch(async (err) => {
if (err instanceof Anthropic.APIError) {
console.log(err.status); // 400
console.log(err.name); // BadRequestError
console.log(err.headers); // {server: 'nginx', ...}
} else {
throw err;
}
});
}
main();
Error codes are as followed:
| Status Code | Error Type |
|---|---|
| 400 | BadRequestError |
| 401 | AuthenticationError |
| 403 | PermissionDeniedError |
| 404 | NotFoundError |
| 422 | UnprocessableEntityError |
| 429 | RateLimitError |
| >=500 | InternalServerError |
| N/A | APIConnectionError |
For more information on debugging requests, see these docs
All object responses in the SDK provide a _request_id property which is added from the request-id response header so that you can quickly log failing requests and report them back to Anthropic.
const message = await client.messages.create({ max_tokens: 1024, messages: [{ role: 'user', content: 'Hello, Claude' }], model: 'claude-3-5-sonnet-latest' });
console.log(completion._request_id) // req_018EeWyXxfu5pfWkrYcMdjWG
Certain errors will be automatically retried 2 times by default, with a short exponential backoff. Connection errors (for example, due to a network connectivity problem), 408 Request Timeout, 409 Conflict, 429 Rate Limit, and >=500 Internal errors will all be retried by default.
You can use the maxRetries option to configure or disable this:
// Configure the default for all requests:
const client = new Anthropic({
maxRetries: 0, // default is 2
});
// Or, configure per-request:
await client.messages.create({ max_tokens: 1024, messages: [{ role: 'user', content: 'Hello, Claude' }], model: 'claude-3-5-sonnet-latest' }, {
maxRetries: 5,
});
Requests time out after 10 minutes by default. You can configure this with a timeout option:
// Configure the default for all requests:
const client = new Anthropic({
timeout: 20 * 1000, // 20 seconds (default is 10 minutes)
});
// Override per-request:
await client.messages.create({ max_tokens: 1024, messages: [{ role: 'user', content: 'Hello, Claude' }], model: 'claude-3-5-sonnet-latest' }, {
timeout: 5 * 1000,
});
On timeout, an APIConnectionTimeoutError is thrown.
Note that requests which time out will be retried twice by default.
List methods in the Anthropic API are paginated.
You can use the for await … of syntax to iterate through items across all pages:
async function fetchAllBetaMessagesBatches(params) {
const allBetaMessagesBatches = [];
// Automatically fetches more pages as needed.
for await (const betaMessageBatch of client.beta.messages.batches.list({ limit: 20 })) {
allBetaMessagesBatches.push(betaMessageBatch);
}
return allBetaMessagesBatches;
}
Alternatively, you can request a single page at a time:
let page = await client.beta.messages.batches.list({ limit: 20 });
for (const betaMessageBatch of page.data) {
console.log(betaMessageBatch);
}
// Convenience methods are provided for manually paginating:
while (page.hasNextPage()) {
page = await page.getNextPage();
// ...
}
We automatically send the anthropic-version header set to 2023-06-01.
If you need to, you can override it by setting default headers on a per-request basis.
Be aware that doing so may result in incorrect types and other unexpected or undefined behavior in the SDK.
import Anthropic from '@anthropic-ai/sdk';
const client = new Anthropic();
const message = await client.messages.create(
{
max_tokens: 1024,
messages: [{ role: 'user', content: 'Hello, Claude' }],
model: 'claude-3-5-sonnet-latest',
},
{ headers: { 'anthropic-version': 'My-Custom-Value' } },
);
The "raw" Response returned by fetch() can be accessed through the .asResponse() method on the APIPromise type that all methods return.
You can also use the .withResponse() method to get the raw Response along with the parsed data.
const client = new Anthropic();
const response = await client.messages
.create({
max_tokens: 1024,
messages: [{ role: 'user', content: 'Hello, Claude' }],
model: 'claude-3-5-sonnet-latest',
})
.asResponse();
console.log(response.headers.get('X-My-Header'));
console.log(response.statusText); // access the underlying Response object
const { data: message, response: raw } = await client.messages
.create({
max_tokens: 1024,
messages: [{ role: 'user', content: 'Hello, Claude' }],
model: 'claude-3-5-sonnet-latest',
})
.withResponse();
console.log(raw.headers.get('X-My-Header'));
console.log(message.content);
This library is typed for convenient access to the documented API. If you need to access undocumented endpoints, params, or response properties, the library can still be used.
To make requests to undocumented endpoints, you can use client.get, client.post, and other HTTP verbs.
Options on the client, such as retries, will be respected when making these requests.
await client.post('/some/path', {
body: { some_prop: 'foo' },
query: { some_query_arg: 'bar' },
});
To make requests using undocumented parameters, you may use // @ts-expect-error on the undocumented
parameter. This library doesn't validate at runtime that the request matches the type, so any extra values you
send will be sent as-is.
client.foo.create({
foo: 'my_param',
bar: 12,
// @ts-expect-error baz is not yet public
baz: 'undocumented option',
});
For requests with the GET verb, any extra params will be in the query, all other requests will send the
extra param in the body.
If you want to explicitly send an extra argument, you can do so with the query, body, and headers request
options.
To access undocumented response properties, you may access the response object with // @ts-expect-error on
the response object, or cast the response object to the requisite type. Like the request params, we do not
validate or strip extra properties from the response from the API.
By default, this library uses node-fetch in Node, and expects a global fetch function in other environments.
If you would prefer to use a global, web-standards-compliant fetch function even in a Node environment,
(for example, if you are running Node with --experimental-fetch or using NextJS which polyfills with undici),
add the following import before your first import from "Anthropic":
// Tell TypeScript and the package to use the global web fetch instead of node-fetch.
// Note, despite the name, this does not add any polyfills, but expects them to be provided if needed.
import '@anthropic-ai/sdk/shims/web';
import Anthropic from '@anthropic-ai/sdk';
To do the inverse, add import "@anthropic-ai/sdk/shims/node" (which does import polyfills).
This can also be useful if you are getting the wrong TypeScript types for Response (more details).
You may also provide a custom fetch function when instantiating the client,
which can be used to inspect or alter the Request or Response before/after each request:
import { fetch } from 'undici'; // as one example
import Anthropic from '@anthropic-ai/sdk';
const client = new Anthropic({
fetch: async (url: RequestInfo, init?: RequestInit): Promise<Response> => {
console.log('About to make a request', url, init);
const response = await fetch(url, init);
console.log('Got response', response);
return response;
},
});
Note that if given a DEBUG=true environment variable, this library will log all requests and responses automatically.
This is intended for debugging purposes only and may change in the future without notice.
By default, this library uses a stable agent for all http/https requests to reuse TCP connections, eliminating many TCP & TLS handshakes and shaving around 100ms off most requests.
If you would like to disable or customize this behavior, for example to use the API behind a proxy, you can pass an httpAgent which is used for all requests (be they http or https), for example:
import http from 'http';
import { HttpsProxyAgent } from 'https-proxy-agent';
// Configure the default for all requests:
const client = new Anthropic({
httpAgent: new HttpsProxyAgent(process.env.PROXY_URL),
});
// Override per-request:
await client.messages.create(
{
max_tokens: 1024,
messages: [{ role: 'user', content: 'Hello, Claude' }],
model: 'claude-3-5-sonnet-latest',
},
{
httpAgent: new http.Agent({ keepAlive: false }),
},
);
This package generally follows SemVer conventions, though certain backwards-incompatible changes may be released as minor versions:
We take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.
We are keen for your feedback; please open an issue with questions, bugs, or suggestions.
TypeScript >= 4.5 is supported.
The following runtimes are supported:
"node" environment ("jsdom" is not supported at this time).dangerouslyAllowBrowser to true.dangerouslyAllowBrowser option can be dangerous because it exposes your secret API credentials in the client-side code. Web browsers are inherently less secure than server environments,
any user with access to the browser can potentially inspect, extract, and misuse these credentials. This could lead to unauthorized access using your credentials and potentially compromise sensitive data or functionality.
Note that React Native is not supported at this time.
If you are interested in other runtime environments, please open or upvote an issue on GitHub.
0.33.0 (2024-12-17)
Full Changelog: sdk-v0.32.1...sdk-v0.33.0
FAQs
The official TypeScript library for the Anthropic API
The npm package @anthropic-ai/sdk receives a total of 644,167 weekly downloads. As such, @anthropic-ai/sdk popularity was classified as popular.
We found that @anthropic-ai/sdk demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 11 open source maintainers collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Research
Security News
Socket researchers uncover a malicious npm package posing as a tool for detecting vulnerabilities in Etherium smart contracts.
Security News
Research
A supply chain attack on Rspack's npm packages injected cryptomining malware, potentially impacting thousands of developers.
Research
Security News
Socket researchers discovered a malware campaign on npm delivering the Skuld infostealer via typosquatted packages, exposing sensitive data.