Claude Haiku 4.5 pricing for rag pipeline

Quick start

Call Claude Haiku 4.5 with the Anthropic Python SDK:

from anthropic import Anthropic

client = Anthropic()
response = client.messages.create(
    model="claude-haiku-4-5",
    max_tokens=1500,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0135 per call at standard rates
# Input:  $1.00/MTok
# Output: $5.00/MTok

How Claude Haiku 4.5 compares on cost

Per-call cost for all models scoring 50+ on rag pipeline benchmarks. Hover for details.

Cheapest viable option: GPT 5.6 Luna at $0.003000/call (78% less, 85/100 quality).

What drives rag pipeline cost

Retrieval-augmented calls are dominated by the retrieved passages, not the question. Retrieving eight chunks instead of three roughly triples input cost for an answer that is often no better, so retrieval tuning is cost tuning. The system prompt and instructions are identical on every call, which makes cache reads the first thing to enable.

For Claude Haiku 4.5 specifically, that means output tokens cost 5.0x more than input, at $5.00 vs $1.00 per MTok. At this use case’s 6,000/1,500 token split, output accounts for 56% of the $0.0135 per-call cost.

Claude Haiku 4.5 quality benchmarks for rag pipeline

Performance across all task types

Claude Haiku 4.5 scores by task type. RAG Pipeline highlighted.

Confidence scores are a third-party benchmark snapshot from week 29 of 2026. This snapshot is 8 weeks old, so treat the scores as directional and validate against your own evals.

About Claude Haiku 4.5

Other models from Claude

You can compare Claude Haiku 4.5 head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.

Frequently asked questions