Claude Haiku 5.5 API at $0.06 / $0.30 per 1M tokens

Anthropic's fastest model for high-volume, latency-sensitive tasks like classification, extraction and routing. On Qora API you call claude-haiku-5-5 through one OpenAI-compatible endpoint at least 40% below Anthropic's official price.

Claude Haiku 5.5 pricing vs official

Official prices from Anthropic; Qora prices from qoraapi.com/pricing, both checked November 2, 2026. This model is served in the Stable Claude group (0.6x of official price). Prices shown are for prompts up to 100K tokens; like Anthropic's own pricing, longer prompts use a higher tier.

What it costs in practice

A workload of 10M input tokens and 2M output tokens costs $2.00 at Anthropic's official price and $1.20 on Qora API, a saving of $0.80.

Quick start

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(base_url="https://qoraapi.com/v1", api_key="YOUR_QORA_KEY")
resp = client.chat.completions.create(
    model="claude-haiku-5-5",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

cURL

curl https://qoraapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_QORA_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-haiku-5-5", "messages": [{"role": "user", "content": "Hello!"}]}'

Claude Code

export ANTHROPIC_BASE_URL=https://qoraapi.com
export ANTHROPIC_AUTH_TOKEN=YOUR_QORA_KEY
export ANTHROPIC_MODEL=claude-haiku-5-5
claude

Full walkthrough: Claude Code with a cheaper API.

The same key works in Cursor, Cline, Continue, SillyTavern and any tool that accepts a custom OpenAI base URL. See the docs or this setup guide.

FAQ

Other Anthropic model prices