Anthropic

Chat completions using Anthropic models can be created with:

the chat completion methods in @preternatural-js/client-sdk
the official Anthropic SDK, configured with the Client SDK’s gateway settings

Using the Client SDK


import { ServiceProvider } from '@preternatural-js/client-sdk'

Non-streaming completion

Set streamMode to false for a non-streaming chat completion.


const result = await client.streamChat({
  scope: {
    provider: ServiceProvider.anthropic,
    modelIdentifier: 'claude-sonnet-4-5-20250929',
    productId: 'your-product-id',
  },
  messages: [
    {
      role: 'user',
      content: 'Explain quantum computing in one paragraph.',
    },
  ],
  maxTokens: 500,
  temperature: 0.7,
  streamMode: false,
})
 
if (typeof result === 'string') {
  throw new Error('Expected a non-streaming chat completion')
}
 
const message = result.choices[0]?.message.content

When streamMode is false, streamChat() returns an OpenAI-compatible ChatCompletion object.

Anthropic requires a maximum output-token value, so include maxTokens in the request.

Streaming completion

Set streamMode to true and provide a callback to process generated text as it arrives.


const text = await client.streamChat(
  {
    scope: {
      provider: ServiceProvider.anthropic,
      modelIdentifier: 'claude-sonnet-4-5-20250929',
      productId: 'your-product-id',
    },
    messages: [
      {
        role: 'user',
        content: 'Write a short story about a lunar gardener.',
      },
    ],
    maxTokens: 500,
    temperature: 0.7,
    streamMode: true,
  },
  (chunk) => {
    console.log(chunk)
  },
)

The callback receives each generated text chunk. The returned promise resolves to the complete generated text after the stream finishes.

More info

Check chat completions using the Client SDK

Using the Anthropic SDK


import Anthropic from '@anthropic-ai/sdk'
import { ServiceProvider } from '@preternatural-js/client-sdk'
 
const model = 'claude-sonnet-4-5-20250929'
const gateway = await client.gateway.providerConfiguration({
  provider: ServiceProvider.anthropic,
  modelIdentifier: model,
  productId: 'your-product-id',
})
 
const anthropic = new Anthropic({
  apiKey: null,
  authToken: 'PRETERNATURAL_GATEWAY_AUTHENTICATES_REQUESTS',
  baseURL: gateway.baseURL,
  defaultHeaders: gateway.headers,
  fetch: gateway.fetchImpl,
  maxRetries: 0,
})
 
const message = await anthropic.messages.create({
  model,
  max_tokens: 500,
  messages: [
    {
      role: 'user',
      content: 'Explain quantum computing in one paragraph.',
    },
  ],
})
 
const text = message.content
  .filter((block) => block.type === 'text')
  .map((block) => block.text)
  .join('')

The Client SDK’s gateway headers authenticate the request. The authToken value satisfies the Anthropic SDK’s authentication requirement; it is not an Anthropic API key.