Atlas / Models / Anthropic / Anthropic: Claude Sonnet 4.5

Anthropic: Claude Sonnet 4.5✓ Catalog verified

anthropic/claude-sonnet-4.5

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

Input price
$3.00 /1M
Output price
$15.00 /1M
Context
1M
Modalities
textimagefile
Released
Sep 29, 2025
Tool calling
✓ Yes
Atlas signal
90/100
01

Overview

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

Access: available through the official Anthropic API. Context window: 1M.

ModelsAtlas catalog, merged with official vendor documentation.Last refreshed Oct 29, 2026
02

Specifications

API identifieranthropic/claude-sonnet-4.5
ProviderAnthropic
Model typeMultimodal LLM
Context window1M catalog
Input modalitiestext · image · file
Output modalitiestext
ReleasedSep 29, 2025
TokenizerClaude
ModeratedYes
Architecture modalitytext+image+file->text
Supported parameters
include_reasoningmax_completion_tokensmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Source: provider documentation + catalog feedMethodology →

API defaults

Default parameters
{
  "top_k": null,
  "top_p": 1,
  "temperature": 1,
  "presence_penalty": null,
  "frequency_penalty": null,
  "repetition_penalty": null
}
Advertisement
03

Pricing

Live pricing components for anthropic/claude-sonnet-4.5 as published in the catalog.

$3.00
Input /1M
$15.00
Output /1M
—
Per request
—
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$0.000003$3.00 / 1MPer input token
Completion tokens$0.000015$15.00 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search fee$0.01$0.010000Per search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$4.5Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual Understanding✓ SupportedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Anthropic: Claude Sonnet 4.5
MMLU Signal (Reasoning)
95signal
Coding Signal (HumanEval proxy)
92signal
Math Signal (GSM8K proxy)
87signal
Science Signal (GPQA proxy)
87signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
Advertisement
07

Quick start

Call Anthropic: Claude Sonnet 4.5 through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4.5",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

Head-to-head comparisons

Side-by-side breakdowns of Anthropic: Claude Sonnet 4.5 against other frontier models.

vs Anthropic: Claude Fable 5vs Anthropic: Claude Fable 5.1vs Anthropic: Claude Haiku 5.5vs Anthropic: Claude Opus 4.6vs Anthropic: Claude Opus 4.7vs Anthropic: Claude Opus 4.7 (Fast)vs Anthropic: Claude Opus 4.8vs Anthropic: Claude Opus 4.8 (Fast)vs Anthropic: Claude Opus 5vs Anthropic: Claude Opus 5.5vs Anthropic: Claude Sonnet 4.6vs Anthropic: Claude Sonnet 5vs Anthropic: Claude Sonnet 5.5vs Claude Opus 5 (Fast)vs Google: Gemini 2.5 Flashvs Google: Gemini 2.5 Flash Litevs Google: Gemini 2.5 Flash Lite Preview 09-2025vs Google: Gemini 2.5 Provs Google: Gemini 2.5 Pro Preview 05-06vs Google: Gemini 2.5 Pro Preview 06-05vs Google: Gemini 3 Flash Previewvs Google: Gemini 3 Pro Previewvs Google: Gemini 3.1 Flash Lite Previewvs Google: Gemini 3.1 Pro Previewvs Google: Gemini 3.1 Pro Preview Custom Toolsvs Google: Gemini 3.5 Flashvs Google: Gemini 3.6 Flashvs Google: Gemini 4 Argonvs OpenAI: GPT-5.4vs OpenAI: GPT-5.4 Provs OpenAI: GPT-5.5vs OpenAI: GPT-5.5 Provs OpenAI: GPT-5.6 Lunavs OpenAI: GPT-5.6 Luna Provs OpenAI: GPT-5.6 Solvs OpenAI: GPT-5.6 Sol Provs OpenAI: GPT-5.6 Terravs OpenAI: GPT-5.6 Terra Provs xAI: Grok 4 Fastvs Anthropic: Claude Haiku 4.5vs Anthropic: Claude Opus 4.1vs Anthropic: Claude Opus 4.5vs OpenAI: GPT-5vs OpenAI: GPT-5 Codexvs OpenAI: GPT-5 Imagevs OpenAI: GPT-5 Image Minivs OpenAI: GPT-5 Minivs OpenAI: GPT-5 Nanovs OpenAI: GPT-5 Provs OpenAI: GPT-5.1vs OpenAI: GPT-5.1-Codexvs OpenAI: GPT-5.1-Codex-Maxvs OpenAI: GPT-5.1-Codex-Minivs OpenAI: GPT-5.2vs OpenAI: GPT-5.2-Codexvs OpenAI: GPT-5.2 Provs OpenAI: GPT-5.3-Codexvs OpenAI: GPT-5.4 Minivs OpenAI: GPT-5.4 Nanovs OpenAI: o1
09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Anthropic: Claude Sonnet 4.5 cost?

$3.00 per 1M input tokens and $15.00 per 1M output tokens on the official Anthropic API.

What is the context window of Anthropic: Claude Sonnet 4.5?

Anthropic: Claude Sonnet 4.5 supports up to 1M tokens of context.

Does Anthropic: Claude Sonnet 4.5 support tool / function calling?

Yes, Anthropic: Claude Sonnet 4.5 supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access Anthropic: Claude Sonnet 4.5?

Use the official Anthropic API with the model id `anthropic/claude-sonnet-4.5`. See the Quick start section above for code examples.

Advertisement