Claude 3 Haiku — Anthropic | Modeldex

Claude 3 Haiku

Active

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku) #multimodal

Updated 4 days agoStructured data from Modeldex catalog

VisionLong context

Knowledge cutoff

Aug 31, 2023(2.6 years ago)

API release

Mar 13, 2024(2.1 years ago)

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

Overview

History

Claude 3 Haiku became available via the Anthropic API on 2024-03-13.

Training & availability

Training data has a knowledge cutoff of 2023-08-31 — information about events after that date is unlikely to appear in the model's responses. Anthropic has not released the underlying model weights — access is via their hosted API only.

Capabilities

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

Recommended for: vision, long-context.

Limitations

The knowledge cutoff is 32 months old — this model will not know about recent events, releases, or API changes.

Pricing

Input: $0.2500 per 1M tokens
Output: $1.2500 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-3-haiku",
    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

@ $0.25/1M

Output tokens / month2.0M

@ $1.25/1M

Input cost

$1.25

5.0M × $0.25/1M

Output cost

$2.5

2.0M × $1.25/1M

Total / month

$3.75

$45 / year

Providers & performance

3 providers

Multi-provider inference routes for this model — sorted by throughput. Latency is time-to-first-token; throughput is output tokens per second. Data from OpenRouter, measured over the last 30 minutes.

Provider	Throughput	Latency (TTFT)	Input $ / 1M	Output $ / 1M	Context	Quant	Supports
Amazon Bedrock	79tok/s	451ms	$0.25	$1.25	200K	—	tools
Anthropic	78tok/s	464ms	$0.25	$1.25	200K	—	tools
Google	—	—

Integrations & tooling support

Tool calling: Not supported
Structured outputs: Not supported

Price vs quality

Budget pricing

Priced low — good for high-volume tasks. Quality tier pending more benchmark coverage.