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.
Model comparison
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
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.
| Spec | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| Context window | 200K tokens | 1M tokens |
| Maximum output | 64K tokens | 128K tokens |
| Knowledge cutoff | February 2025 | June 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.
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.
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.
| Model | Access | Estimated total (USD) |
|---|---|---|
| Claude Haiku 5.5Anthropic | Anthropic | $0.0009 |
| Claude Haiku 4.5Anthropic | Anthropic | $0.0085 |
Quick take
Anthropic's smallest current Claude model, built for high-volume, latency-sensitive work such as classification, routing, extraction and subagent tasks.
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.
A compact Claude model for quick replies, classification and narrowly scoped assistants.
Haiku 4.5 uses manual extended thinking, not the adaptive thinking settings of the newer Claude models.
Compare the published facts
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 & reasoning | Claude Haiku 5.5 | Claude Haiku 4.5 |
|---|---|---|
| Context windowMaximum combined prompt and working context documented by the provider. | 1M tokens | 200K tokens |
| Maximum outputProvider-published response limit, where available. | 128K tokens | 64K 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 2026 | February 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, image | Text, image |
| Tools & agentsSelected native tools and agent-building capabilities, not an exhaustive list. | Tool use, agents, vision, coding workflows | Tool use, agents, vision, coding workflows |
How to choose
Start with the job you need to complete, then validate cost, access, and policy details on your exact provider route.
Anthropic does not train on API data without express permission. Retention depends on the API feature, account agreement and cloud provider.
Provider and API links
Anthropic does not train on API data without express permission. Retention depends on the API feature, account agreement and cloud provider.
Provider and API links
Frequently asked questions
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.
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.
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.
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.