Anthropic: Claude 3.5 Haiku

Public pricingIntelligence 66/100Large memory视觉工具调用

Anthropic: Claude 3.5 Haiku 是一款多模态模型，适合编码、软件工程和智能体工作流。它结合了多模态输入处理、强大的编码能力、200K tokens上下文和均衡成本定位，可在编码、软件工程和智能体工作流中提供可靠表现。它适合重视质量、速度与成本的团队，能带来稳定输出、灵活部署与扩展空间。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。

Input

$0.80/1M

Output

$4.00/1M

Cached

$0.08/1M

Batch

$0.40/1M

Calculate your Claude 3.5 Haiku bill.

Set your workload — see cost at your exact volume.

What would Claude 3.5 Haiku cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Claude 3.5 Haiku at a glance.

Memory

200,000

tokens

Max reply

8,192

tokens

Memory tier

Large

an entire book or large codebase

Tokenizer

anthropic

Released

Nov 2024

Training cutoff

Jul 2024

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • gpqa_diamond

    41.6

  • humaneval

    88

  • swe_bench_verified

    40.6

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick Claude 3.5 Haiku

  • Screenshot analysis, image understanding, or document OCR.
  • Agentic workflows that call tools or APIs.
  • Long documents, full codebases, or extensive chat histories.
  • High-volume workloads where unit cost matters.

When to look elsewhere

  • Very latency-sensitive, real-time apps where every millisecond counts.

Alternatives

Similar models to compare.

FAQ

Claude 3.5 Haiku — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, Claude 3.5 Haiku costs roughly $220 per month. Input is $0.80 /1M tokens and output is $4.00 /1M tokens.
Claude 3.5 Haiku has a 200,000-token context window (large memory — an entire book or large codebase). That means you can fit about 37,500 words of input and history in a single call.
Beyond text generation, Claude 3.5 Haiku supports understanding images, calling functions / tools, strict JSON output. It streams replies by default.
Claude 3.5 Haiku was released in November 2024, with training data cut off around July 2024.
Models in a similar class include Claude 3 Haiku, Nova Pro 1.0, GPT-5.4 Mini. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Claude 3.5 Haiku against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard