Claude Haiku 4.5 — Anthropic | Modeldex

Claude Haiku 4.5

Active31.1Limited

Fast, low-cost Claude model for latency-sensitive workloads.

Updated 4 days agoStructured data from Modeldex catalog

VisionAgenticLong context

API release

Oct 15, 2025(6 months ago)

Intelligence Index

31.1/ 100

Limitedweighted across 6 benchmarks

Factual grounding: 63.8
Instruction following: 36.5
Medical: 17.3
Long context: 6.9

Computed as the mean of per-category averages across MMLU, GPQA, SWE-bench, HumanEval, MATH, GSM8K, AIME, Aider Polyglot and more. See each benchmark for methodology.

Overview

Claude Haiku 4.5 is optimized for speed and cost while retaining strong tool-calling and structured-output behavior.

History

Claude Haiku 4.5 became available via the Anthropic API on 2025-10-15.

Training & availability

Anthropic has not released the underlying model weights — access is via their hosted API only.

Capabilities

Context window: 200K tokens.
Max output: 64K tokens.
Input modalities: text, image.

Recommended for: vision, agentic, long-context.

Pricing

Input: $1.0000 per 1M tokens
Output: $5.0000 per 1M tokens

Use the cost calculator above to estimate monthly spend for your workload.

Quick start

Minimal example using the anthropic API. Copy, paste, replace the key.

from anthropic import Anthropic

client = Anthropic(api_key="sk-ant-...")
resp = client.messages.create(
    model="claude-haiku-4-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.content[0].text)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $1/1M

Output tokens / month2.0M

@ $5/1M

Input cost

5.0M × $1/1M

Output cost

$10

2.0M × $5/1M

Total / month

$15

$180 / year

Benchmarks

Benchmark	Score	Source
FACTS GroundingFactual grounding	63.76%	Third-party llm-stats.com
HealthBenchMedical	17.28%	Third-party llm-stats.com
LongBench v2Long context	1.11%	Third-party llm-stats.com

Integrations & tooling support

Tool calling: Supported
Structured outputs: Supported

Price vs quality

Poor value

Below-average benchmark performance for the price.

Quality percentile: 16%
Effective price: $4/1M
Pricing breakdown: $1/1M in
$5/1M out

Community ratings

No ratings yet. Be the first to rate Claude Haiku 4.5.