Anthropic Claude Sonnet 4.5 — what it is, when to use it and what to use instead

Summary

Claude Sonnet 4.5 is a legacy Sonnet release from September 2025, at $3 per million input tokens and $15 per million output tokens with a 200K-token context window. Anthropic's availability commitment for it runs only to 29 September 2026, the shortest runway of any active Claude model.

Sonnet 4.5 was released on 29 September 2025 and has been superseded twice, by Claude Sonnet 4.6 and then by Claude Sonnet 5. Sonnet 5 is cheaper ($2 / $10 against $3 / $15), has five times the context window and moves the reliable knowledge cutoff from January 2025 to January 2026.

It accepts text and image input and returns text, with manual extended thinking; the effort parameter is not supported. Max output is 64K tokens.

No retirement date has been announced, but Anthropic's commitment is to keep it available until at least 29 September 2026. Treat that as the point from which a retirement notice becomes possible, not as a shutdown date; Anthropic gives at least 60 days' notice before retiring a publicly released model.

Modality

• Text
• Vision

Use case

• Chat
• Coding
• Reasoning
• Agents & tool use
• Long context

Tier

• Mid-tier

Access

• Hosted API

Languages

• Multilingual

Specifications

Input price

$3.00 / M tokens

Output price

$15.00 / M tokens

Price band

Premium

Context window

200K tokens

Max output

64K tokens

Input

Text, image

Output

Text

Knowledge cutoff

January 2025

Tool use

Yes

Structured output

Yes

Weights licence

not published

Model maker

Anthropic

“unknown” means the figure has not been published, or we have not verified it yet — never that the answer is no. “not published” under the weights licence means this model is not offered with downloadable weights. The price band is ours: it bands the blended price (three parts input to one part output) as budget (≤ $0.50), standard (≤ $3), premium (≤ $12) or flagship.

Lifecycle

Anthropic has not announced a deprecation or shutdown date for this model. That is a statement about what has been published, not a guarantee — providers typically announce a shutdown months ahead, and this page updates when they do.

1. Released 29 September 2025
2. Deprecated not announced
3. Retired not announced

Use it for

• Keep an existing Sonnet 4.5 integration running while you migrate, and schedule that migration now rather than later.
• Reproduce earlier results on a pinned snapshot where output has to stay comparable.

Avoid it when

• You are starting a new integration; Anthropic's availability commitment for this model runs only to 29 September 2026.
• You are choosing on price; Claude Sonnet 5 costs $2 / $10 against $3 / $15 here and adds a 1M-token window.
• You need more than 64K output tokens or more than a 200K-token context window.
• Your prompts depend on facts after January 2025, which is this model's reliable knowledge cutoff.

Alternatives to consider

• Claude Sonnet 5 Curated

  Anthropic ● Active

  The current Sonnet model and the direct migration path: cheaper at $2 / $10, a 1M-token window against 200K and 128K max output against 64K.

  $2.00 in · $10.00 out / M tokens · 1M context

• Claude Haiku 4.5 Curated

  Anthropic ● Active

  A third of the price at $1 / $5 with the same 200K-token window, if your workload is high volume.

  $1.00 in · $5.00 out / M tokens · 200K context

• GPT-5.6 Terra Curated

  OpenAI ● Active

  OpenAI's balanced tier at $2 / $12 with a 1.05M-token context window, if the migration is also a chance to compare providers.

  $2.00 in · $12.00 out / M tokens · 1.1M context

• Claude Sonnet 4.6 Derived

  Anthropic ● Active

  Same provider, same tier (mid-tier), similar price; shares chat, coding, reasoning, agents and long-context.

  $3.00 in · $15.00 out / M tokens · 1M context

• Claude Sonnet 4.5 Derived

  Amazon Bedrock ● Active

  Alternative from Amazon Bedrock, same tier (mid-tier), similar price; shares chat, coding, reasoning, agents and long-context.

  $3.00 in · $15.00 out / M tokens · 200K context

Curated suggestions were picked by a reviewer, with the reason written by hand. Derived suggestions are ranked from the data — shared tags, the same tier and a comparable price band — not from benchmark scores. Check the capability fit yourself: we track lifecycle, price and specifications.

Sources

• platform.claude.com ↗ https://platform.claude.com/docs/en/models/sonnet-4-5/overview
• platform.claude.com ↗ https://platform.claude.com/docs/en/about-claude/pricing
• platform.claude.com ↗ https://platform.claude.com/docs/en/about-claude/models/overview
• platform.claude.com ↗ https://platform.claude.com/docs/en/about-claude/model-deprecations

Verified against the source on 10 September 2026. Dataset snapshot 10 September 2026. Providers can change a date without notice — the link above is always the final word.

About this profile

The specifications and dates above are facts from Anthropic, with the sources listed. The summary, the use-for and avoid-when lists and the curated alternatives are our assessment: editorial profile reviewed on 21 September 2026 by llm-researcher.