Skip to content
models / Anthropic / Claude Haiku 5.5

Claude Haiku 5.5

textanthropic/claude-haiku-5.5

Claude Haiku 5.5 is a fast, cost-efficient model for high-volume, latency-sensitive tasks such as classification, extraction, routing, and subagent work.

$0.50list priceper 1M output tokens (short context)
pricing
unitlist price
per 1M cache write tokens (long context)$0.625
per 1M cache write tokens (short context)$0.125
per 1M cached input tokens (long context)$0.05
per 1M cached input tokens (short context)$0.01
per 1M input tokens (long context)$0.50
per 1M input tokens (short context)$0.10
per 1M output tokens (long context)$2.50
per 1M output tokens (short context)$0.50

Everyone pays the list price. What comes back grows with your Reward Status: Noob 0.5% of every spend buys back $INFX, Pro (hold 1,337 $INFX) 2%, Elite (also hold 1,337 $XAVA) 5%. How it works

openai sdk (python)
from openai import OpenAI

client = OpenAI(
    base_url="https://xavainf.com/v1",
    api_key="xk_live_...",  # your Xava Inference key
)

r = client.chat.completions.create(
    model="anthropic/claude-haiku-5.5",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)
curl
curl https://xavainf.com/v1/chat/completions \
  -H "Authorization: Bearer $XINF_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/claude-haiku-5.5","messages":[{"role":"user","content":"Hello!"}]}'
limits
providerAnthropic
typetext
context window1,000,000 tokens
max output—
prompt storagenone
provider retentionthe model provider's policy
livesoon
requests 24h—
p50 latency—
uptime 7d—