Claude Haiku 4.5: API pricing, context window and capabilities

Prices from official vendor price lists · October 2026

Claude Haiku 4.5 costs $1 per 1M input tokens and $5 per 1M output tokens, with a 200K context window. Mid-priced: dearer than 74% of this rating. Recorded for vision, reasoning, adjustable thinking.

Visit Anthropic All Anthropic models

Capabilities

API $/1M (in / out)

$1 / $5

Context window

200K tokens

Price / mo

API only

Overview Reviews

Claude Haiku 4.5 is an AI model from Anthropic, priced at $1 input and $5 output per 1M tokens. That places it in the mid tier of this rating — dearer than 74% of the 205 priced models listed.

It holds 200K tokens in a single conversation. Capabilities recorded in this rating: text & chat, vision, reasoning, adjustable thinking, tool calling. Access is through the API rather than a consumer subscription.

API price$1 / $5per 1M tokens, in / out

Context200K tokenstokens per conversation

VendorAnthropicall models from this vendor

TierMiddearer than 74% of models

Cost calculator

1M tokens/mo10M tokens/mo50M tokens/mo200M tokens/mo

Standard$4.00~~AED 15 per month~~

With batch −50%$2.00~~AED 7 per month~~

With caching on input$3.77~~AED 14 per month~~

Standard$40.00~~AED 147 per month~~

With batch −50%$20.00~~AED 73 per month~~

With caching on input$37.75~~AED 139 per month~~

Standard$200~~AED 735 per month~~

With batch −50%$100~~AED 367 per month~~

With caching on input$189~~AED 693 per month~~

Standard$800~~AED 2,938 per month~~

With batch −50%$400~~AED 1,469 per month~~

With caching on input$755~~AED 2,773 per month~~

Assumes a 1:3 input-to-output ratio, which is typical for chat and generation. Dirham figures use 3.6725 per dollar. Batch and caching discounts apply where the vendor offers them.

Compared with alternatives

How Claude Haiku 4.5 sits against its neighbours in this rating. Tap a card to open that model.

GPT-5.4 Mini

Cheaper

OpenAI

$0.75 / $4.5400K tokens

Qwen3.7 Max

Closest match

Alibaba (Qwen)

$1.475 / $4.4251M tokens

ERNIE 5.0

Step up

Baidu

$1.4 / $5.6119K tokens

Good and poor fit

Good fit

Multi-step analysis, planning and code review, where the first plausible answer is often wrong.
Reading screenshots, charts, scanned documents and photos.
High-volume routing, classification and autocomplete.

Poor fit

Long multi-step reasoning, where a larger model finishes in fewer attempts.

Related filters

Text & chat234 models for text generation and chat

Vision159 models that read images

Reasoning175 models that think before answering

Adjustable thinking85 models with a reasoning depth dial

Tool calling172 models that call your functions

Anthropic13 models from this vendor

All 245 modelsThe full rating with filters and prices

Frequently asked questions

How much does Claude Haiku 4.5 cost?

$1 / $5 per 1M tokens, input and output. In dirhams that is roughly AED 3.67 per 1M input tokens. Batch processing halves it where the vendor offers it.

What is the context window of Claude Haiku 4.5?

200K tokens in a single conversation.

What can Claude Haiku 4.5 do?

In this rating it is recorded with: text & chat, vision, reasoning, adjustable thinking, tool calling, structured JSON output, code execution, prompt caching, batch API, priority / fast tier, low latency, multilingual, proprietary API.

Is Claude Haiku 4.5 a good choice?

It depends on the job. See the good-fit and poor-fit lists above, and compare against the neighbouring models before committing.

Ratings 0

Avg. score 0

Rate this page

Help us improve