Claude Haiku 4.5

Anthropic's fastest and most cost-efficient model for low-latency intelligent applications.

FastCost EfficientLow Latency

Context Window

200k tokens

claude-haiku-4-5

Max Output

1M tokens

Input

$0.9$1

10% off

1M tokens

Output

$4.5$5

10% off

1M tokens

Model Codeclaude-haiku-4-5

Playground

Model Code

claude-haiku-4-5

Reference inputs

Reference Images0/5

Click or drag

Enter your prompt here...

Output

No output yet

Pricing

Plan	Context Window	Max Output	Input	Output	Cache Write	Cache Read
claude-haiku-4-5	200k tokens	-	$0.9$110% off 1M tokens	$4.5$510% off 1M tokens	$1.125$1.2510% off 1M tokens	$0.09$0.110% off 1M tokens

1h Cache Write · $1.8 · 1M tokens

Cache read or cached input pricing applies to reused prompt tokens.

README

Claude Haiku 4.5 is Anthropic's smallest current model, designed for near-frontier coding and agent performance with much lower latency and cost, making it a strong fit for high-volume assistant and automation workloads.

Anthropic positions Haiku 4.5 as its fastest and most cost-efficient model, while still delivering near-frontier capability on coding, computer use, and agent tasks.
It is intended for real-time chat assistants, customer service systems, pair programming, and other workloads where latency and cost matter.
Official materials emphasize that Haiku 4.5 can be combined with larger models in multi-model workflows, using Haiku for fast parallel subtasks.

API

Use the API docs for request format, parameters, and integration details.

Anthropic's fastest and most cost-efficient model for low-latency intelligent applications.

Model Code

claude-haiku-4-5

View API Docs

API

Endpoint

POST /v1/messages

Authentication

Authorization: Bearer YOUR_REACH_API_KEY
anthropic-version: 2023-06-01
Content-Type: application/json

Example

curl -X POST "https://direct.reachapi.ai/v1/messages" \
  -H "Authorization: Bearer YOUR_REACH_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [
      {
        "role": "user",
        "content": "Introduce ReachAPI in one sentence."
      }
    ],
    "max_tokens": 512,
    "temperature": 0.2
  }'

Related Models

Other models from the same vendor

Claude Fable 5

Anthropic's most capable widely released model for next-generation intelligence and long-running agents.

Claude Opus 5

Anthropic's flagship model for deep reasoning, complex agentic coding, and long-horizon enterprise work.

Claude Sonnet 5

Anthropic's new Sonnet model for extended-context coding, agents, and enterprise production workflows.

Claude Opus 4.8

Anthropic's newest Opus-tier model for complex reasoning, long-horizon agentic coding, and high-autonomy enterprise work.

Claude Opus 4.7

Anthropic's premium Opus model for advanced coding, vision-heavy review, and long-running enterprise agents.

Claude Opus 4.6

Anthropic's most capable model for coding, agents, and high-stakes enterprise work.