Back to Text & reasoning

Model comparison

Claude Haiku 5.5 vs Claude Haiku 4.5

Provider-published facts for Claude Haiku 5.5 and Claude Haiku 4.5, side by side: price, limits, inputs, access and data policy. No mystery scores and no invented benchmark rankings.

What changed

What changed from Claude Haiku 4.5 to Claude Haiku 5.5

Haiku 5.5 succeeds Haiku 4.5 with a far larger context window and output limit, a later knowledge cutoff and much lower token prices for shorter prompts. Thinking is adaptive and on by default.

SpecClaude Haiku 4.5Claude Haiku 5.5
Context window200K tokens1M tokens
Maximum output64K tokens128K tokens
Knowledge cutoffFebruary 2025June 2026
Input price$1 / 1M$0.10 / 1M up to 100K-token prompts; $0.50 above
Output price$5 / 1M$0.50 / 1M up to 100K-token prompts; $2.50 above

Unchanged: inputs and tools & agents.

Before you switch from Claude Haiku 4.5 to Claude Haiku 5.5

  • Update the model ID; the new ID has no date suffix.
  • Requests that set budget_tokens return an error; use adaptive thinking with an effort level.
  • Remove temperature, top_p and top_k, and replace assistant prefill with structured outputs or tools.
  • The same text produces more tokens than on Haiku 4.5, and images use the high-resolution tier, so re-check cost estimates.
  • Priority Tier is not available for Haiku 5.5.
Source: Anthropic

Estimate your cost

Set your usage. Your estimate updates as you type.

Example: 6,000 input tokens for 10 pages, plus a 500-token summary. Page lengths vary; adjust the numbers below.

One run sends your input to the model once and receives an answer. Tokens are pieces of text: input is what you send, output is the answer you receive.

Advanced options
How this estimate works

Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.

Estimate your cost
ModelEstimated total (USD)
Claude Haiku 5.5Anthropic$0.0009
Claude Haiku 4.5Anthropic$0.0085

Quick take

Claude Haiku 5.5

Anthropic's smallest current Claude model, built for high-volume, latency-sensitive work such as classification, routing, extraction and subagent tasks.

Best for

  • Classification and routing
  • High-volume data extraction
  • Subagent tasks in larger workflows

Watch out for

Check integrations before switching from Haiku 4.5: thinking is adaptive and on by default, and budget_tokens, sampling parameters and assistant prefill now return errors. The same text produces more tokens, and long prompts are billed at a higher tier, so re-baseline costs.

Claude Haiku 4.5

A compact Claude model for quick replies, classification and narrowly scoped assistants.

Best for

  • Data extraction
  • Request routing

Watch out for

Haiku 4.5 uses manual extended thinking, not the adaptive thinking settings of the newer Claude models.

Compare the published facts

Claude Haiku 5.5 vs Claude Haiku 4.5

Values use each provider's own published units and limits. A blank means the provider did not publish a directly comparable value in the sources reviewed.

Text & reasoningClaude Haiku 5.5Claude Haiku 4.5
Context windowMaximum combined prompt and working context documented by the provider.1M tokens200K tokens
Maximum outputProvider-published response limit, where available.128K tokens64K tokens
Knowledge cutoffLatest reliable knowledge date explicitly published by the model provider. Search and connected tools can retrieve newer information but do not change the model's built-in cutoff.June 2026February 2025
Input priceCurrent standard list price per million input tokens unless noted.$0.10 / 1M up to 100K-token prompts; $0.50 above$1 / 1M
Output priceCurrent standard list price per million output tokens unless noted.$0.50 / 1M up to 100K-token prompts; $2.50 above$5 / 1M
InputsMedia types accepted by the listed model endpoint.Text, imageText, image
Tools & agentsSelected native tools and agent-building capabilities, not an exhaustive list.Tool use, agents, vision, coding workflowsTool use, agents, vision, coding workflows

How to choose

Data policy and API access

Start with the job you need to complete, then validate cost, access, and policy details on your exact provider route.

Claude Haiku 5.5

Anthropic does not train on API data without express permission. Retention depends on the API feature, account agreement and cloud provider.

Claude Haiku 4.5

Anthropic does not train on API data without express permission. Retention depends on the API feature, account agreement and cloud provider.

Frequently asked questions

Claude Haiku 5.5 vs Claude Haiku 4.5 FAQ

What is the main difference between Claude Haiku 5.5 and Claude Haiku 4.5?

Claude Haiku 5.5: Anthropic's smallest current Claude model, built for high-volume, latency-sensitive work such as classification, routing, extraction and subagent tasks. Claude Haiku 4.5: A compact Claude model for quick replies, classification and narrowly scoped assistants.

What changed from Claude Haiku 4.5 to Claude Haiku 5.5?

Haiku 5.5 succeeds Haiku 4.5 with a far larger context window and output limit, a later knowledge cutoff and much lower token prices for shorter prompts. Thinking is adaptive and on by default. Changed in the published specs: context window, maximum output, knowledge cutoff, input price and output price. Unchanged: inputs and tools & agents.

Should I choose Claude Haiku 5.5 or Claude Haiku 4.5?

Best fit for Claude Haiku 5.5: Classification and routing. Best fit for Claude Haiku 4.5: Data extraction. Test both with your own data and provider route before committing.

Where do the facts in this Claude Haiku 5.5 vs Claude Haiku 4.5 comparison come from?

From each provider's own documentation, pricing and policy pages for the Text & reasoning category. Cody does not add its own benchmark scores or name a universal winner.