Skip to content
Anthropic

Claude Sonnet 4.5

anthropic/claude-sonnet-4.5
Coding

The default serious coding model, million-token context, dependable agent loops, production temperament.

Model overview

Context window

1M

tokens

Input price

—

quoted on request

Output price

—

quoted on request

Weekly volume

—

tokens / week

Open weights

No

API only

Capabilities

6

of 11 tags

Description

Claude Sonnet 4.5 is a coding model from Anthropic. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. Anthropic’s stated focus is frontier models with a safety-first identity. The weights are not published, so it is API-only.

Capabilities

Tool calling
Calls functions you define and returns their arguments as structured data, the basis of agents.
JSON mode
Constrains the response to valid JSON matching a schema you supply.
Streaming
Emits tokens as they are generated, so answers appear progressively rather than all at once.
Caching
Reuses already-processed prompt prefixes across requests, cutting input cost for repeated context.
Vision input
Accepts images alongside text in the prompt.
Long context
Built for inputs well beyond the mainstream window, whole repositories, archives or corpora.

Strengths & weaknesses

Strengths

  • Best-in-catalogue agentic coding (SWE-bench 77)
  • 1M context fits entire repositories
  • Caching cuts effective input cost sharply

Weaknesses

  • Premium pricing versus open peers
  • Closed weights

Pricing

Pricing for Claude Sonnet 4.5, per 1M tokens
RatePriceUnit
Input— quoted on request—
Output— quoted on request—

Prompt caching is supported, so repeated prefixes bill below the listed input rate. This model is not provisioned yet; the rate is quoted on request.

Context window

1Mtokens

covers prompt and response together, so a long input leaves less room for the answer.

1M tokens against a peer range of 128K to 1M, median 256K. Compared across 4 coding models.

Supported features

Feature support for Claude Sonnet 4.5
FeatureSupport
Tool callingSupported
JSON modeSupported
StreamingSupported
Vision inputSupported
Audio inputNot supported
Long contextSupported
Open weightsNot supported
ReasoningNot supported
Fine-tunableNot supported
BatchNot supported
CachingSupported

Example use cases

  • Coding agents

  • Repository-scale work

  • Production assistants

Example prompt

prompt
Review this diff for correctness and side effects, then propose a safer refactor with tests.

Related models

Comparison

Compare against anything →
Claude Sonnet 4.5 compared with Qwen3 Coder and Claude Opus 4.5
AttributeClaude Sonnet 4.5Qwen3 CoderClaude Opus 4.5
Context window1M256K200K
Input priceR0.00R0.00R0.00
Output price— not charged— not charged— not charged
Tool callingSupportedSupportedSupported
JSON modeSupportedSupportedSupported
Vision inputSupportedNot supportedSupported
Open weightsNot supportedSupportedNot supported
Prompt cachingSupportedNot supportedSupported

Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.

Provider information

View Anthropic →
Anthropic3 models

Anthropic · San Francisco, United States · est. 2021

Founded by former OpenAI researchers, Anthropic pairs frontier capability with an explicit safety research agenda. 5's million-token context a favourite for repository-scale tasks.

Recent releases

    Documentation

    Frequently asked questions

    Input is billed at R0.00 per 1M tokens, and there is no separate output charge. Prompt caching bills repeated prefixes below the listed input rate. Every figure on this page is an illustrative placeholder.