Claude Sonnet 5: Pricing, Context and Features
anthropic/claude-sonnet-5Claude Sonnet 5 is Anthropic's reasoning model for text, images, files, coding, agents, and professional work.
1M tokens of context — about 750,000 words, on a scale that ends at 2M.
What it can do
- Reasoning
- Vision
- Tool use
- Takes text
- Takes image
- Takes file
- Gives text
Released 30 Jun 2026 · checked 3 Oct 2026.
About it
Claude Sonnet 5 is an Anthropic AI model released June 30, 2026. It accepts text, images, and files, returns text, and supports reasoning, vision, and tools. Its context window is 1,000,000 tokens, with up to 128,000 output tokens. Pricing is $2 per million input tokens and $10 per million output tokens.
Review
In a line
Claude Sonnet 5 is Anthropic's Sonnet-class AI model. It accepts text, images, and files, and produces text answers.
What it's good at
The model is aimed at coding, agent tasks, and professional work. It supports reasoning and adaptive thinking, with selectable effort levels such as low, medium, high, and max.
Vision lets it handle image input as well as text and files. Tool support is built in. You can compare it with other reasoning models or vision language models.
Price in plain terms
Input costs $2 per million tokens, while output costs $10 per million tokens. Tokens are the small pieces of text a model reads or writes.
A roughly 500-word page costs about 0.13 cents to read. One chat turn with about 1,000 input tokens and 500 output tokens costs about 0.7 cents. A thousand such turns cost about $7.00.
Context and limits
Claude Sonnet 5 can take up to 1,000,000 tokens in one context, so a single request can include a very large amount of text and other input.
It can write up to 128,000 tokens in one answer. Its output is text, even when the input includes images or files.
Ways to use it
The model reads text, images, and files, then returns text. Its tool support can be used in services that expose those tools alongside the model.
It is identified as anthropic/claude-sonnet-5.
Verdict
Choose Claude Sonnet 5 if you need one model for coding, agent-style tasks, professional work, and image or file input. Its million-token context suits very large documents, while selectable reasoning effort gives some control over how much thinking a task receives.
Look elsewhere if you need output other than text, or if your workload does not benefit from a large context window, reasoning, vision, or tools. Budget for output carefully: output tokens cost five times as much as input tokens.
Verdict
Claude Sonnet 5 fits people who want a single model that can work across coding, agent tasks, professional work, and mixed text, image, or file input. Its very large context can hold substantial material, and its reasoning settings offer adjustable effort. The pricing is low for reading but higher for generated text, so long answers can raise the bill. It is not a fit when you require non-text output or have no use for its large context, vision, reasoning, or tool features.
- Accepts text, images, and files
- One-million-token context window
- Supports reasoning and selectable effort levels
- Tool support is included
- Handles coding, agents, and professional work
- Output costs $10 per million tokens
- Answers are text only
- Maximum output is 128,000 tokens
- Pick it ifCoding and agent tasks; Large documents and mixed text, image, or file input; Professional work needing adjustable reasoning
- Skip it ifYou need non-text output; You do not need a large context, vision, reasoning, or tools; Generated text volume makes the output price too high
Pricing
Input is $2 per million tokens and output is $10 per million tokens. A 500-word page costs about 0.13 cents to read; 1,000 typical chat turns cost about $7.00.
Questions
What is Claude Sonnet 5?
It is Anthropic's Sonnet-class AI model for coding, agent tasks, professional work, and mixed text, image, and file input.
How much does Claude Sonnet 5 cost?
Input costs $2 per million tokens. Output costs $10 per million tokens.
How large is its context window?
It can take up to 1,000,000 tokens in one context.
How much can it write at once?
Its maximum output is 128,000 tokens, and the output format is text.
Can it understand images and files?
Yes. Its inputs include text, images, and files, and it has vision support.
Does Claude Sonnet 5 support reasoning and tools?
Yes. It supports reasoning with selectable effort levels and includes tool support.
What does a typical chat turn cost?
A turn using about 1,000 input tokens and 500 output tokens costs about 0.7 cents.
On these boards
More from Anthropic
- Claude Sonnet 5.5$2 in
- Claude Sonnet 5.5 (batch)$1 in
- Claude Opus 5.5$4 in
- Claude Opus 5.5 (batch)$2 in
- Claude Fable 5.1$10 in
- Claude Fable 5.1 (batch)$5 in
- Claude Opus 5$5 in
- Claude Opus 5 (batch)$2.50 in
- Claude Sonnet 5 (batch)$1 in
- Claude Fable 5$10 in
- Claude Fable 5 (batch)$5 in
- Claude Fable Latest$10 in
- Claude Opus 4.8$5 in
- Claude Opus 4.8 (batch)$2.50 in
- Claude Haiku Latest$1 in
- Claude Sonnet Latest$2 in
- Claude Opus Latest$4 in
- Claude Opus 4.7$5 in