Anthropic · Messages

Claude Haiku 5.5 API

The fastest, cheapest Claude. Good for quick questions and high volume. Served through RouterHub at $0.01794 input / $0.08969 output per million tokens (prices as of ).

Claude Haiku 5.5 pricing

−82% vs the official API price of $0.10 input / $0.50 output per 1M tokens (source, checked 2026-10-13).

Input
$0.01794
Cached input
$0.001794
Cache write
$0.02242
Output
$0.08969
Typical message
≈ 0.006¢

USD per 1 million tokens. A typical message is about 1,000 input and 500 output tokens. Cached input uses the cache-read rate when the provider reports a cache hit. Billed from your prepaid balance.

API compatibility and context

Exact model ID
claude-haiku-5-5
Provider
Anthropic
Variant
Standard
Supported API
Anthropic-compatible Messages API (/v1/messages)
Availability
Preview
Context window
1,000,000 tokens
Maximum input
Not published
Maximum output
128,000 tokens

Use Claude Haiku 5.5 through the API

Create a RouterHub account, add prepaid credits and create an API key. Set ROUTERHUB_API_KEY locally, then send a first request with the exact model ID.

cURL
curl --connect-timeout 30 --max-time 600 https://routerhub.si/v1/messages \
  -H "x-api-key: $ROUTERHUB_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-haiku-5-5","max_tokens":256,"messages":[{"role":"user","content":"Write a short noir scene set in a lighthouse."}]}'

Python: install anthropic with pip. The example requests 256 output tokens and disables automatic retries, so check Usage before resending a paid request.

Python
import os
from anthropic import Anthropic

client = Anthropic(
    api_key=os.environ["ROUTERHUB_API_KEY"],
    base_url="https://routerhub.si",
    timeout=600.0,
    max_retries=0,
)
response = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=256,
    messages=[{"role": "user", "content": "Write a short noir scene set in a lighthouse."}],
)
print(response.content)

Coding tools that work with Claude Haiku 5.5

Common questions

What is Claude Haiku 5.5?

Claude Haiku 5.5 is an Anthropic language model served through RouterHub using the Anthropic-compatible Messages API. Its exact API model ID is claude-haiku-5-5.

How much does Claude Haiku 5.5 cost?

RouterHub charges $0.01794 input, $0.001794 cached input and $0.08969 output per million tokens (prices as of 2026-11-08). A typical chat message of about 1,000 input and 500 output tokens costs about 0.006¢. Usage is billed against your prepaid balance.

What is the Claude Haiku 5.5 context window?

Context window: 1,000,000 tokens. Maximum input: Not published. Maximum output: 128,000 tokens.

Which API does Claude Haiku 5.5 support?

Use the Anthropic-compatible Messages API at https://routerhub.si/v1/messages with the exact model ID claude-haiku-5-5 and your RouterHub API key (x-api-key header).

Which coding tools work with Claude Haiku 5.5?

OpenCode, Claude Code, VS Code + Continue, VS Code + Cline, Claude Desktop. Each setup guide lists only compatible model IDs.

Can I try Claude Haiku 5.5 for free?

Claude Haiku 5.5 needs a free RouterHub account with prepaid credits. New accounts get $5 free on their first top-up of $20 or more.

Related models and guides