Claude Haiku 5.5

by October 7, 20261M context128K output

Claude Haiku 5.5 is the fastest and lowest-cost model in Anthropic’s Claude 5.5 family, built for high-volume and latency-sensitive work such as classification, extraction, routing, and customer support. It reads text and images, calls tools, and offers configurable effort, so a request can trade response time against depth. Its 1M-token context window and 128K-token maximum output also make it a practical sub-agent inside larger coding and research workflows.

Claude Haiku 5.5 is served through Runware's compatible endpoints, which take another provider's request format. Point the SDK you already use at Runware by changing the base URL and the API key, and set model to anthropic:claude@haiku-5.5.

Requests and responses keep the provider's format, so its reference documents every parameter.

Endpoint	Format
`/v1/chat/completions`	OpenAI Chat Completions
`/v1/messages`	Anthropic Messages

Chat Completions

cURL

curl -X POST https://api.runware.ai/v1/chat/completions \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic:claude@haiku-5.5",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="your_runware_api_key",
    base_url="https://api.runware.ai/v1",
)

response = client.chat.completions.create(
    model="anthropic:claude@haiku-5.5",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
)

print(response.choices[0].message.content)

TypeScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'your_runware_api_key',
  baseURL: 'https://api.runware.ai/v1',
});

const response = await client.chat.completions.create({
  model: 'anthropic:claude@haiku-5.5',
  messages: [{ role: 'user', content: 'What is the capital of France?' }],
});

console.log(response.choices[0].message.content);

Compatible APIs covers streaming, tool calling and how the endpoint differs from OpenAI, and the OpenAI API reference lists every parameter.

Messages

cURL

curl -X POST https://api.runware.ai/v1/messages \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic:claude@haiku-5.5",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

Python

from anthropic import Anthropic

client = Anthropic(
    auth_token="your_runware_api_key",
    base_url="https://api.runware.ai",
)

message = client.messages.create(
    model="anthropic:claude@haiku-5.5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "What is the capital of France?"}],
)

print(message.content[0].text)

TypeScript

import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  authToken: 'your_runware_api_key',
  baseURL: 'https://api.runware.ai',
});

const message = await client.messages.create({
  model: 'anthropic:claude@haiku-5.5',
  max_tokens: 1024,
  messages: [{ role: 'user', content: 'What is the capital of France?' }],
});

console.log(message.content[0].text);

Compatible APIs covers how the Anthropic SDKs authenticate against Runware, and the Claude API reference lists every parameter.