Claude Haiku 4.5

Text Generation • Anthropic • Proxied

Claude Haiku 4.5 delivers similar levels of coding performance at one-third the cost and more than twice the speed of larger models.

Model Info
Context Window ↗	200,000 tokens
Terms and License	link ↗
More information	link ↗

Usage

const response = await env.AI.run(
  'anthropic/claude-haiku-4.5',
  {
    messages: [
      {
        role: 'user',
        content: 'What are the three laws of thermodynamics?',
      },
    ],
    max_tokens: 1024,
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Examples

With System Message — Using a system message to set context

const response = await env.AI.run(
  'anthropic/claude-haiku-4.5',
  {
    system: 'You are a helpful coding assistant specializing in Python.',
    messages: [
      {
        role: 'user',
        content: 'How do I read a JSON file in Python?',
      },
    ],
    max_tokens: 1024,
    temperature: 0.3,
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Multi-turn Conversation — Continuing a conversation with context

const response = await env.AI.run(
  'anthropic/claude-haiku-4.5',
  {
    messages: [
      {
        role: 'user',
        content:
          'I need help planning a road trip from San Francisco to Los Angeles.',
      },
      {
        role: 'assistant',
        content:
          "I'd be happy to help! The drive is about 380 miles and takes roughly 5-6 hours. Would you like suggestions for scenic routes or interesting stops along the way?",
      },
      {
        role: 'user',
        content: 'Yes, what are some good places to stop?',
      },
    ],
    max_tokens: 1024,
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Creative Writing — Higher temperature for creative output

const response = await env.AI.run(
  'anthropic/claude-haiku-4.5',
  {
    messages: [
      {
        role: 'user',
        content:
          'Write a short story opening about a detective finding an unusual clue.',
      },
    ],
    max_tokens: 512,
    temperature: 0.8,
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Streaming Response — Enable streaming for real-time output

const response = await env.AI.run(
  'anthropic/claude-haiku-4.5',
  {
    messages: [
      {
        role: 'user',
        content: 'Explain the concept of recursion with a simple example.',
      },
    ],
    max_tokens: 1024,
    stream: true,
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

▶messages[]

arrayrequired

max_tokens

numberrequiredexclusiveMinimum: 0

system

string

temperature

numberminimum: 0maximum: 1

top_p

numberminimum: 0maximum: 1

top_k

numberexclusiveMinimum: 0

stream

boolean

▶metadata{}

object

string

type

stringconst: message

role

stringconst: assistant

▶content[]

array

model

string

stop_reason

string | null

▶usage{}

object

API Schemas

Input
Output

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "messages": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "role": {
            "type": "string",
            "enum": [
              "user",
              "assistant"
            ]
          },
          "content": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "array",
                "items": {
                  "type": "object",
                  "properties": {
                    "type": {
                      "type": "string"
                    },
                    "text": {
                      "type": "string"
                    },
                    "source": {}
                  },
                  "required": [
                    "type"
                  ],
                  "additionalProperties": false
                }
              }
            ]
          }
        },
        "required": [
          "role",
          "content"
        ],
        "additionalProperties": false
      }
    },
    "max_tokens": {
      "type": "number",
      "exclusiveMinimum": 0
    },
    "system": {
      "type": "string"
    },
    "temperature": {
      "type": "number",
      "minimum": 0,
      "maximum": 1
    },
    "top_p": {
      "type": "number",
      "minimum": 0,
      "maximum": 1
    },
    "top_k": {
      "type": "number",
      "exclusiveMinimum": 0
    },
    "stream": {
      "type": "boolean"
    },
    "metadata": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    }
  },
  "required": [
    "messages",
    "max_tokens"
  ],
  "additionalProperties": {}
}

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "type": {
      "type": "string",
      "const": "message"
    },
    "role": {
      "type": "string",
      "const": "assistant"
    },
    "content": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "type": {
            "type": "string"
          },
          "text": {
            "type": "string"
          }
        },
        "required": [
          "type"
        ],
        "additionalProperties": {}
      }
    },
    "model": {
      "type": "string"
    },
    "stop_reason": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ]
    },
    "usage": {
      "type": "object",
      "properties": {
        "input_tokens": {
          "type": "number"
        },
        "output_tokens": {
          "type": "number"
        }
      },
      "required": [
        "input_tokens",
        "output_tokens"
      ],
      "additionalProperties": false
    }
  },
  "required": [
    "id",
    "type",
    "role",
    "content",
    "model",
    "stop_reason",
    "usage"
  ],
  "additionalProperties": {}
}