NEAR AICloud
Sign inStart building
Claude Haiku 4.5 icon
Claude Haiku 4.5
anthropic/claude-haiku-4-5
200K context|$1/M input tokens|$5/M output tokens|$0.1/M cache read

Anthropic's fastest model with near-frontier intelligence for high-throughput, cost-sensitive workloads.

Input / M tokens
$1
Output / M tokens
$5
Cache read
$0.1
Context
200K

Sample code and API for Claude Haiku 4.5

Use the native Messages API (/v1/messages) for Claude models.

const response = await fetch("https://cloud-api.near.ai/v1/messages", {
  method: "POST",
  headers: {
    "x-api-key": "<YOUR-NEAR-AI-CLOUD-API-KEY>",
    "anthropic-version": "2023-06-01",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "anthropic/claude-haiku-4-5",
    max_tokens: 1024,
    messages: [{ role: "user", content: "What is the meaning of life?" }],
  }),
})

console.log(await response.json())

You can also use NEAR AI Cloud with Anthropic's client API:

import Anthropic from "@anthropic-ai/sdk"

const client = new Anthropic({
  baseURL: "https://cloud-api.near.ai",
  apiKey: "<YOUR-NEAR-AI-CLOUD-API-KEY>",
})

const message = await client.messages.create({
  model: "anthropic/claude-haiku-4-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "What is the meaning of life?" }],
})

console.log(message.content)

Privacy & Execution

This is an Incognito model: it runs on a partner provider rather than inside a NEAR AI GPU TEE. Requests are routed through a shared NEAR AI API key, so your identity is not disclosed to the provider.

Your prompt content, however, is transmitted to and processed by Anthropic in accordance with their terms of service and privacy policy. Data is encrypted in transit, but execution happens outside of trusted hardware — there is no hardware-level privacy, attestation, or cryptographic proof of execution for this model.