anthropic/claude-haiku-5.5
The successor to Haiku 4.5, built for high-volume, latency-sensitive work such as classification, extraction, routing and sub-agent tasks, with much stronger instruction following. The context window grows to 1M tokens. Pricing depends on prompt length: prompts up to 100K tokens bill at the low rate, and longer prompts (cached tokens included) bill at 5× that rate. Adaptive thinking is on by default and tunable with the effort parameter (default medium). Text and image input with native prompt caching.
Source: official_x0.3 · Verified 2026-10-12
Cache read $0.003/M · Cache write $0.0375/M
| Tier | Input | Cache read | Cache write | Output |
|---|---|---|---|---|
| Standard ≤100K | $0.03 | $0.003 | $0.0375 | $0.15 |
| Standard >100K | $0.15 | $0.015 | $0.1875 | $0.75 |
Use either ID to call this model via the API.
anthropic/claude-haiku-5.5claude-haiku-5-5Replace the ONEHOP_KEY placeholder with your API key. Create one →
from anthropic import Anthropic
client = Anthropic(
base_url="https://api.onehop.ai/anthropic",
api_key="<ONEHOP_KEY>",
)
message = client.messages.create(
model="anthropic/claude-haiku-5.5",
max_tokens=1024,
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(message.content[0].text)