Anthropic Claude Sonnet 5 — what it is, when to use it and what to use instead

Summary

Claude Sonnet 5 is Anthropic's mid-tier model, at $2 per million input tokens and $10 per million output tokens with a 1M-token context window and 128K max output. Anthropic positions it as the balance between speed and intelligence in the current line-up.

Sonnet sits in the middle of the Claude line: below Claude Opus 5 and Claude Fable 5.1 on capability, above Claude Haiku 4.5 on speed and price. Sonnet 5 was released on 30 June 2026 and succeeds Claude Sonnet 4.6, which it undercuts on price ($2 / $10 against $3 / $15) while keeping the same 1M-token context window.

It accepts text and image input and returns text. Adaptive thinking is on by default and is steered with the effort parameter, which defaults to high. Two things break code written for Sonnet 4.6: manual extended thinking returns a 400 error, and so does setting temperature, top_p or top_k to a non-default value.

No deprecation has been announced. Anthropic commits to keeping Sonnet 5 available until at least 30 June 2027.

Modality

• Text
• Vision

Use case

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

Tier

• Mid-tier

Access

• Hosted API

Languages

• Multilingual

Specifications

Input price

$2.00 / M tokens

Output price

$10.00 / M tokens

Price band

Premium

Context window

1M tokens

Max output

128K tokens

Input

Text, image

Output

Text

Knowledge cutoff

January 2026

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 30 June 2026
2. Deprecated not announced
3. Retired not announced

Use it for

• Build production assistants and chat features where per-token cost matters more than the last few points of capability.
• Process long documents or whole codebases in a single request, up to the 1M-token context window.
• Run tool-calling agent loops that need a fast turnaround per step at a mid-tier price.
• Move workloads off Claude Sonnet 4.6, which costs more per token for the same context window.

Avoid it when

• You need the strongest available reasoning on hard, long-horizon tasks; Claude Opus 5 and Claude Fable 5.1 are the tiers above it.
• You run high-volume classification or extraction where $2 per million input tokens dominates the bill.
• Your input includes audio or video; Sonnet 5 accepts text and images only.
• Your code sets temperature, top_p or top_k; non-default values return a 400 error.

Alternatives to consider

• Claude Opus 5 Curated

  Anthropic ● Active

  Same provider and the same 1M-token window at $5 / $25 instead of $2 / $10; take it when Sonnet 5 falls short on complex agentic or enterprise work.

  $5.00 in · $25.00 out / M tokens · 1M context

• Claude Haiku 4.5 Curated

  Anthropic ● Active

  Half the price at $1 / $5, against a 200K-token context window and a February 2025 knowledge cutoff.

  $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 comparable 1.05M-token context window, so a like-for-like choice between providers.

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

• Gemini 3.6 Flash Curated

  Google (Gemini) ● Active

  Google's balanced tier at $0.75 / $3.75 and it accepts audio, video and PDF input, which Sonnet 5 does not.

  $0.75 in · $3.75 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-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.