This library provides convenient access to the Anthropic REST API from server-side TypeScript or JavaScript.
For the AWS Bedrock API, see @anthropic-ai/bedrock-sdk.
In v0.5.0, we introduced a fully rewritten SDK. The new version offers better error handling, a more robust and intuitive streaming implementation, and more.
Key interface changes:
new Client(apiKey)→new Anthropic({ apiKey })client.complete()→client.completions.create()client.completeStream()→client.completions.create({ stream: true })onUpdatecallback →for await (const x of stream)- full message in stream → delta of message in stream
Example diff
// Import "Anthropic" instead of "Client":
- import { Client, HUMAN_PROMPT, AI_PROMPT } from '@anthropic-ai/sdk';
+ import Anthropic, { HUMAN_PROMPT, AI_PROMPT } from '@anthropic-ai/sdk';
// Instantiate with "apiKey" as an object property:
- const client = new Client(apiKey);
+ const client = new Anthropic({ apiKey });
// or, simply provide an ANTHROPIC_API_KEY environment variable:
+ const client = new Anthropic();
async function main() {
// Request & response types are the same as before, but better-typed.
const params = {
prompt: `${HUMAN_PROMPT} How many toes do dogs have?${AI_PROMPT}`,
max_tokens_to_sample: 200,
model: "claude-1",
};
// Instead of "client.complete()", you now call "client.completions.create()":
- await client.complete(params);
+ await client.completions.create(params);
// Streaming requests now use async iterators instead of callbacks:
- client.completeStream(params, {
- onUpdate: (completion) => {
- console.log(completion.completion); // full text
- },
- });
+ const stream = await client.completions.create({ ...params, stream: true });
+ for await (const completion of stream) {
+ process.stdout.write(completion.completion); // incremental text
+ }
// And, since this library uses `Anthropic-Version: 2023-06-01`,
// completion streams are now incremental diffs of text
// rather than sending the whole message every time:
let text = '';
- await client.completeStream(params, {
- onUpdate: (completion) => {
- const diff = completion.completion.replace(text, "");
- text = completion.completion;
- process.stdout.write(diff);
- },
- });
+ const stream = await client.completions.create({ ...params, stream: true });
+ for await (const completion of stream) {
+ const diff = completion.completion;
+ text += diff;
+ process.stdout.write(diff);
+ }
console.log('Done; final text is:')
console.log(text)
}
main();The API documentation can be found here.
npm install --save @anthropic-ai/sdk
# or
yarn add @anthropic-ai/sdkThe full API of this library can be found in api.md.
import Anthropic from '@anthropic-ai/sdk';
const anthropic = new Anthropic({
apiKey: 'my api key', // defaults to process.env["ANTHROPIC_API_KEY"]
});
async function main() {
const completion = await anthropic.completions.create({
model: 'claude-2.1',
max_tokens_to_sample: 300,
prompt: `${Anthropic.HUMAN_PROMPT} how does a court case get to the Supreme Court?${Anthropic.AI_PROMPT}`,
});
}
main();We provide support for streaming responses using Server Sent Events (SSE).
import Anthropic from '@anthropic-ai/sdk';
const anthropic = new Anthropic();
const stream = await anthropic.completions.create({
prompt: `${Anthropic.HUMAN_PROMPT} Your prompt here${Anthropic.AI_PROMPT}`,
model: 'claude-2.1',
stream: true,
max_tokens_to_sample: 300,
});
for await (const completion of stream) {
console.log(completion.completion);
}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 anthropic = new Anthropic({
apiKey: 'my api key', // defaults to process.env["ANTHROPIC_API_KEY"]
});
async function main() {
const params: Anthropic.CompletionCreateParams = {
prompt: `${Anthropic.HUMAN_PROMPT} how does a court case get to the Supreme Court?${Anthropic.AI_PROMPT}`,
max_tokens_to_sample: 300,
model: 'claude-2.1',
};
const completion: Anthropic.Completion = await anthropic.completions.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.
We provide a separate package for counting how many tokens a given piece of text contains.
See the repository documentation for more details.
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 completion = await anthropic.completions
.create({
prompt: `${Anthropic.HUMAN_PROMPT} Your prompt here${Anthropic.AI_PROMPT}`,
max_tokens_to_sample: 300,
model: 'claude-2.1',
})
.catch((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 |
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 anthropic = new Anthropic({
maxRetries: 0, // default is 2
});
// Or, configure per-request:
await anthropic.completions.create(
{
prompt: `${Anthropic.HUMAN_PROMPT} Can you help me effectively ask for a raise at work?${Anthropic.AI_PROMPT}`,
max_tokens_to_sample: 300,
model: 'claude-2.1',
},
{
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 anthropic = new Anthropic({
timeout: 20 * 1000, // 20 seconds (default is 10 minutes)
});
// Override per-request:
await anthropic.completions.create(
{
prompt: `${Anthropic.HUMAN_PROMPT} Where can I get a good coffee in my neighbourhood?${Anthropic.AI_PROMPT}`,
max_tokens_to_sample: 300,
model: 'claude-2.1',
},
{
timeout: 5 * 1000,
},
);On timeout, an APIConnectionTimeoutError is thrown.
Note that requests which time out will be retried twice by default.
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 anthropic = new Anthropic();
const completion = await anthropic.completions.create(
{
max_tokens_to_sample: 300,
model: 'claude-2.1',
prompt: `${Anthropic.HUMAN_PROMPT} Where can I get a good coffee in my neighbourhood?${Anthropic.AI_PROMPT}`,
},
{ 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 anthropic = new Anthropic();
const response = await anthropic.completions
.create({
prompt: `${Anthropic.HUMAN_PROMPT} Can you help me effectively ask for a raise at work?${Anthropic.AI_PROMPT}`,
max_tokens_to_sample: 300,
model: 'claude-2.1',
})
.asResponse();
console.log(response.headers.get('X-My-Header'));
console.log(response.raw.statusText); // access the underlying Response object
// parses the response body, returning an object if the API responds with JSON
const completion: Completions.Completion = await response.parse();
console.log(completion.completion);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 here.
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: (url: RequestInfo, init?: RequestInfo): Response => {
console.log('About to make 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 Anthropic from '@anthropic-ai/sdk';
import HttpsProxyAgent from 'https-proxy-agent';
// Configure the default for all requests:
const anthropic = new Anthropic({
httpAgent: new HttpsProxyAgent(process.env.PROXY_URL),
});
// Override per-request:
await anthropic.completions.create(
{
prompt: `${Anthropic.HUMAN_PROMPT} How does a court case get to the Supreme Court?${Anthropic.AI_PROMPT}`,
max_tokens_to_sample: 300,
model: 'claude-2.1',
},
{
baseURL: 'http://localhost:8080/test-api',
httpAgent: new http.Agent({ keepAlive: false }),
},
);This package generally follows SemVer conventions, though certain backwards-incompatible changes may be released as minor versions:
- Changes that only affect static types, without breaking runtime behavior.
- Changes to library internals which are technically public but not intended or documented for external use. (Please open a GitHub issue to let us know if you are relying on such internals).
- Changes that we do not expect to impact the vast majority of users in practice.
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.js 18 LTS or later (non-EOL) versions.
- Deno v1.28.0 or higher, using
import Anthropic from "npm:@anthropic-ai/sdk". - Bun 1.0 or later.
- Cloudflare Workers.
- Vercel Edge Runtime.
- Jest 28 or greater with the
"node"environment ("jsdom"is not supported at this time). - Nitro v2.6 or greater.
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.