Claude Sonnet 4.5 (latest)

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 improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.

Sonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.

anthropic/claude-sonnet-4-5

Organization: Anthropic
Family: claude-sonnet
Providers: 30
Context: 200,000
Output limit: 64,000
Knowledge: 2025-07-31
Release: 2025-09-29
Updated: —
Weights: Closed
Input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf
Output: text
Capabilities: —

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

41 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
AIHubMix	claude-sonnet-4-5-think	200,000	64,000	— / —	—	—	—	View
AIHubMix	claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
AI/ML API	anthropic/claude-sonnet-4.5	200,000	64,000	— / —	—	—	—	View
Anthropic	claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
AnyAPI	anthropic/claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
Cloudflare AI Gateway	anthropic/claude-sonnet-4.5	200,000	64,000	— / —	—	—	—	View
Cortecs	claude-4-5-sonnet	200,000	64,000	— / —	—	—	—	View
Databricks	databricks-claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
DevPass (LLM Gateway)	claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
DigitalOcean	anthropic-claude-4.5-sonnet	200,000	64,000	— / —	—	—	—	View
Helicone	claude-4.5-sonnet	200,000	64,000	— / —	—	—	—	View
Impossibl	anthropic/claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
Kilo Gateway	anthropic/claude-sonnet-4.5	1,000,000	64,000	— / —	—	—	—	View
LLM Gateway	anthropic/claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
LLM Gateway	aws-bedrock/claude-sonnet-4-5	200,000	8,192	— / —	—	—	—	View
LLM Gateway	vertex-anthropic/claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
NanoGPT	anthropic/claude-sonnet-4.5:thinking	200,000	64,000	— / —	—	—	—	View
NanoGPT	anthropic/claude-sonnet-4.5	200,000	64,000	— / —	—	—	—	View
NEAR AI Cloud	anthropic/claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
Neon	claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
Ofox	anthropic/claude-sonnet-4.5	200,000	64,000	— / —	—	—	—	View
OpenCode	claude-sonnet-4-5	1,000,000	64,000	— / —	—	—	—	View
Amazon Bedrockvia OpenRouter	anthropic/claude-sonnet-4.5 unknown	1,000,000	64,000	$3.30 / $16.50	Yes	Yes	Yes	View
Amazon Bedrockvia OpenRouter	anthropic/claude-sonnet-4.5 unknown	1,000,000	64,000	$3.00 / $15.00	Yes	Yes	Yes	View
Anthropicvia OpenRouter	anthropic/claude-sonnet-4.5 unknown	1,000,000	64,000	$3.00 / $15.00	Yes	Yes	Yes	View
Azurevia OpenRouter	anthropic/claude-sonnet-4.5 unknown	200,000	64,000	$3.00 / $15.00	Yes	Yes	Yes	View
Claude Platform on AWSvia OpenRouter	anthropic/claude-sonnet-4.5 unknown	1,000,000	64,000	$3.00 / $15.00	Yes	Yes	Yes	View
Googlevia OpenRouter	anthropic/claude-sonnet-4.5 unknown	1,000,000	64,000	$3.30 / $16.50	Yes	Yes	Yes	View
Googlevia OpenRouter	anthropic/claude-sonnet-4.5 unknown	1,000,000	64,000	$3.00 / $15.00	Yes	Yes	Yes	View
Opper	claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
OrcaRouter	anthropic/claude-sonnet-4.5	1,000,000	64,000	— / —	—	—	—	View
Perplexity Agent	anthropic/claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
Poe	anthropic/claude-sonnet-4.5	983,040	32,768	— / —	—	—	—	View
Qiniu	claude-4.5-sonnet	200,000	64,000	— / —	—	—	—	View
Requesty	claude-sonnet-4-5@eu	1,000,000	64,000	— / —	—	—	—	View
Requesty	claude-sonnet-4-5	1,000,000	64,000	— / —	—	—	—	View
SAP AI Core	anthropic--claude-4.5-sonnet	200,000	64,000	— / —	—	—	—	View
Snowflake Cortex	claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
Tempr Gateway	anthropic/claude-sonnet-4-5	200,000	64,000	— / —	—	—	—	View
Venice AI	claude-sonnet-4-5	198,000	64,000	— / —	—	—	—	View
ZenMux	anthropic/claude-sonnet-4.5	1,000,000	64,000	— / —	—	—	—	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$3.00Per 1M input tokens

Output from$15.00Per 1M output tokens

Available offers41Across 30 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 7 lowest-priced configurations

InputOutput

Amazon Bedrockamazon-bedrock

$3.00$15.00

Anthropicanthropic

$3.00$15.00

Azureazure/global

$3.00$15.00

Claude Platform on AWSclaude-on-aws

$3.00$15.00

Googlegoogle-vertex/global

$3.00$15.00

Amazon Bedrockamazon-bedrock/eu-west-1

$3.30$16.50

Googlegoogle-vertex/us-east5

$3.30$16.50

anthropic/claude-sonnet-4.5Observed Oct 10, 2026, 11:31 AM UTC

Input: $3.00
Output: $15.00
Cache read: $0.30
Cache write: $3.75
Cache write · 1 hour: $6.00

Additional fees and pricing conditions

web search: $0.01 / search

overrides · USD per token for token prices; time windows use UTC.

[
  {
    "prompt": "0.000006",
    "completion": "0.0000225",
    "input_cache_read": "0.0000006",
    "input_cache_write": "0.0000075",
    "min_prompt_tokens": 200000,
    "input_cache_write_1h": "0.000012"
  }
]

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Amazon Bedrockamazon-bedrock/eu-west-1	$3.30	$16.50	$0.33	$4.125
Amazon Bedrockamazon-bedrock	$3.00	$15.00	$0.30	$3.75
Anthropicanthropic	$3.00	$15.00	$0.30	$3.75
Azureazure/global	$3.00	$15.00	$0.30	$3.75
Claude Platform on AWSclaude-on-aws	$3.00	$15.00	$0.30	$3.75
Googlegoogle-vertex/us-east5	$3.30	$16.50	$0.33	$4.125
Googlegoogle-vertex/global	$3.00	$15.00	$0.30	$3.75

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Amazon Bedrockamazon-bedrock/eu-west-1

1,419–2,680.2 ms

Amazon Bedrockamazon-bedrock

1,655–6,049.81 ms

Anthropicanthropic

795–3,134.72 ms

Azureazure/global

1,261–2,467.04 ms

Claude Platform on AWSclaude-on-aws

1,271–9,882.08 ms

Googlegoogle-vertex/global

989–3,889.72 ms

All latency percentiles 6 endpoints

Endpoint	P50	P75	P90	P99
Amazon Bedrockamazon-bedrock/eu-west-1	1,419 ms	1,538 ms	1,663.4 ms	2,680.2 ms
Amazon Bedrockamazon-bedrock	1,655 ms	2,018 ms	2,662.9 ms	6,049.81 ms
Anthropicanthropic	795 ms	949 ms	1,273.8 ms	3,134.72 ms
Azureazure/global	1,261 ms	1,457 ms	1,663.6 ms	2,467.04 ms
Claude Platform on AWSclaude-on-aws	1,271 ms	1,463 ms	1,811 ms	9,882.08 ms
Googlegoogle-vertex/global	989 ms	1,272 ms	1,648.4 ms	3,889.72 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Amazon Bedrockamazon-bedrock/eu-west-1

49–86 t/s

Amazon Bedrockamazon-bedrock

39–95 t/s

Anthropicanthropic

47–83.51 t/s

Azureazure/global

36–102.32 t/s

Claude Platform on AWSclaude-on-aws

38–49 t/s

Googlegoogle-vertex/global

35–72.22 t/s

All throughput percentiles 6 endpoints

Endpoint	P50	P75	P90	P99
Amazon Bedrockamazon-bedrock/eu-west-1	49 t/s	58 t/s	66 t/s	86 t/s
Amazon Bedrockamazon-bedrock	39 t/s	46 t/s	56 t/s	95 t/s
Anthropicanthropic	47 t/s	55 t/s	63 t/s	83.51 t/s
Azureazure/global	36 t/s	56 t/s	77.2 t/s	102.32 t/s
Claude Platform on AWSclaude-on-aws	38 t/s	41 t/s	43 t/s	49 t/s
Googlegoogle-vertex/global	35 t/s	37 t/s	41.2 t/s	72.22 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 7 endpoints

Endpoint5 minutes30 minutes24 hours

Amazon Bedrockamazon-bedrock/eu-west-1Observed Oct 10, 2026, 11:31 AM UTC

100%

Amazon Bedrockamazon-bedrockObserved Oct 10, 2026, 11:31 AM UTC

100%

AnthropicanthropicObserved Oct 10, 2026, 11:31 AM UTC

100%

Azureazure/globalObserved Oct 10, 2026, 11:31 AM UTC

—

100%

Claude Platform on AWSclaude-on-awsObserved Oct 10, 2026, 11:31 AM UTC

100%

Googlegoogle-vertex/us-east5Observed Oct 10, 2026, 11:31 AM UTC

—

100%

Googlegoogle-vertex/globalObserved Oct 10, 2026, 11:31 AM UTC

—

100%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

anthropic/claude-sonnet-4.5Observed Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 60

Coding

52.1

Agentic

15.8

Intelligence

20.7

Design Arena	Category	Elo	Win rate	Rank
models	3d	1,163	51%	60
models	asciiart	1,210	56.1%	21
models	codecategories	1,187	51.5%	57
models	dataviz	1,170	47.4%	67
models	gamedev	1,173	51.1%	62
models	svg	1,114	52.2%	55
models	uicomponent	1,176	49.5%	62
models	website	1,194	51.8%	63
agents	fullstack	1,049	43.7%	36
agents	mobileapps	1,134	52.9%	31
agents	webapps	1,053	43.2%	37

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

tau bench verified airlineAnthropic: Claude Sonnet 4.5

72.97%

gpqa diamondAnthropic: Claude Sonnet 4.5

82.015%

Evaluation	Configuration	Source	Results	Details
models · codecategories	Claude Sonnet 4.5anthropic/claude-4.5-sonnet-20250929	Design Arena	1,183 Elo	Details
models · dataviz	Claude Sonnet 4.5 (Thinking)anthropic/claude-4.5-sonnet-20250929	Design Arena	1,158 Elo	Details
models · asciiart	Claude Sonnet 4.5 (Thinking)anthropic/claude-4.5-sonnet-20250929	Design Arena	1,205 Elo	Details
models · 3d	Claude Sonnet 4.5anthropic/claude-4.5-sonnet-20250929	Design Arena	1,158 Elo	Details
models · svg	Claude Sonnet 4.5anthropic/claude-4.5-sonnet-20250929	Design Arena	1,108 Elo	Details
models · website	Claude Sonnet 4.5anthropic/claude-4.5-sonnet-20250929	Design Arena	1,190 Elo	Details
models · codecategories	Claude Sonnet 4.5 (Thinking)anthropic/claude-4.5-sonnet-20250929	Design Arena	1,182 Elo	Details
models · website	Claude Sonnet 4.5 (Thinking)anthropic/claude-4.5-sonnet-20250929	Design Arena	1,190 Elo	Details
Composite indices	Claude 4.5 Sonnet (Reasoning)anthropic/claude-4.5-sonnet-20250929	Artificial Analysis	Intelligence 20.7 · Coding 52.1 · Agentic 15.8	Details
models · gamedev	Claude Sonnet 4.5anthropic/claude-4.5-sonnet-20250929	Design Arena	1,166 Elo	Details
models · uicomponent	Claude Sonnet 4.5 (Thinking)anthropic/claude-4.5-sonnet-20250929	Design Arena	1,169 Elo	Details
models · uicomponent	Claude Sonnet 4.5anthropic/claude-4.5-sonnet-20250929	Design Arena	1,159 Elo	Details
tau bench verified airline	Anthropic: Claude Sonnet 4.5anthropic/claude-4.5-sonnet-20250929	OpenRouter	72.97%	Details
models · asciiart	Claude Sonnet 4.5anthropic/claude-4.5-sonnet-20250929	Design Arena	1,175 Elo	Details
models · dataviz	Claude Sonnet 4.5anthropic/claude-4.5-sonnet-20250929	Design Arena	1,167 Elo	Details
models · gamedev	Claude Sonnet 4.5 (Thinking)anthropic/claude-4.5-sonnet-20250929	Design Arena	1,163 Elo	Details
models · 3d	Claude Sonnet 4.5 (Thinking)anthropic/claude-4.5-sonnet-20250929	Design Arena	1,153 Elo	Details
gpqa diamond	Anthropic: Claude Sonnet 4.5anthropic/claude-4.5-sonnet-20250929	OpenRouter	82.015%	Details
models · svg	Claude Sonnet 4.5 (Thinking)anthropic/claude-4.5-sonnet-20250929	Design Arena	1,115 Elo	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Oct 18, 2026

Application	Model route	Turns	Median cost / session	Details
Claude Code	anthropic/claude-4.5-sonnet-20250929	10–49 turns	$0.767002	Details
Claude Code	anthropic/claude-4.5-sonnet-20250929	1 turn	$0.001808	Details
Hermes Agent	anthropic/claude-4.5-sonnet-20250929	1 turn	$0.028381	Details
Claude Code	anthropic/claude-4.5-sonnet-20250929	2–9 turns	$0.167969	Details
Hermes Agent	anthropic/claude-4.5-sonnet-20250929	2–9 turns	$0.10141	Details
Hermes Agent	anthropic/claude-4.5-sonnet-20250929	10–49 turns	$0.621308	Details

Source: OpenRouter, as of Oct 20, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days

Daily token usage45,591,095,498 reported tokens · 1 days with observations

46B0

2026-09-11
45,591,095,498 tokens

Jul 26, 2026Oct 23, 2026

Daily observations · 1 days

Date (UTC)	Reported tokens	Reported routes
Sep 11, 2026	45,591,095,498	1

Source: OpenRouter (openrouter.ai/rankings), as of Oct 24, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

anthropic/claude-sonnet-4.5Observed Oct 10, 2026, 11:31 AM UTC

Context: 1,000,000
Maximum output: 64,000
Tokenizer: Claude
Input: text, image, file
Output: text
Moderation: Yes
Knowledge cutoff: 2025-01-31
Added to OpenRouter: 2025-09-29

Base URLhttps://openrouter.ai/api/v1

Model IDanthropic/claude-sonnet-4.5

Version IDanthropic/claude-4.5-sonnet-20250929

Reasoning

Required: No
Enabled by default: Not reported
Default effort: —
Supported efforts: —

Supported parameters

include_reasoning
max_completion_tokens
max_tokens
reasoning
response_format
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_p

Default parameters

top p: 1
temperature: 1

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Claude Sonnet 4.5 (latest) cost?

Listed rates start at $3.00 per million input tokens and $15.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Claude Sonnet 4.5 (latest)?

There are 41 cataloged offers across 30 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 200,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Not reported. Structured output: Not reported. Support can vary by endpoint.

Catalog history · 3 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Oct 19, 2026 · bdd8c76b8972
Sep 14, 2026 · d9cfe955648b
Sep 12, 2026 · a7e9fc15eee2