Anthropic · Claude Sonnet 5
claude-sonnet-5Available from the provider.
- Released
- Deprecatednot announced
- Retirednot announced
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.
Tags
Editorial tags reflect our assessment; documented tags are backed by the sources below.
Specifications
- Input price
- $2.00 / M tok
- Output price
- $10.00 / M tok
- Price class
- Premium
- Context window
- 1M tokens
- Max output
- 128,000 tokens
- Released
- 30 June 2026
- Input modalities
- text, image
- Output modalities
- text
- Knowledge cutoff
- January 2026
- Tool use
- Yes
- Structured output
- Yes
- License
- unknown
- Maker
- Anthropic
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
What to use instead. Curated suggestions are written by our editors for this model; derived ones are ranked automatically from tags, tier and price class.
- Claude Opus 5curated
Anthropic
claude-opus-5Same 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.
In $5.00 / M tokOut $25.00 / M tok
ActiveTextVisionChat+7 - Claude Haiku 4.5curated
Anthropic
claude-haiku-4-5-20251001Half the price at $1 / $5, against a 200K-token context window and a February 2025 knowledge cutoff.
In $1.00 / M tokOut $5.00 / M tok
ActiveTextVisionChat
Change history
Nothing has changed since this model was first recorded — no status change and no price change.
Price history
No price changes recorded yet.
Sources & verification
Facts
Status, dates, pricing and specifications were verified against these pages.
Last verified: (2026-09-23 04:30) · ✓ verified
Editorial profile
The summary, the advice and the curated alternatives are our assessment, not a provider claim.