Home/Models
Models/Anthropic

Claude Opus 4.5 (latest)

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high.

Opus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.

anthropic/claude-opus-4-5
Organization
Anthropic
Family
claude-opus
Providers
21
Context
200,000
Output limit
64,000
Knowledge
2025-05
Release
2025-11-24
Updated
2025-11-24
Weights
Closed
Input
text, image, pdf
Output
text
Capabilities
Tools, Reasoning, Temperature

Providers

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

28 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
AIHubMix
claude-opus-4-5
200,00064,000$5.00 / $25.00YesYes—
View
Anthropic
claude-opus-4-5
200,00064,000$5.00 / $25.00YesYesYes
View
Cloudflare AI Gateway
anthropic/claude-opus-4.5
200,00064,000$5.00 / $25.00YesYesYes
View
Cortecs
claude-opus4-5
200,00064,000$5.313 / $26.568YesYesYes
View
Databricks
databricks-claude-opus-4-5
200,00064,000$5.00 / $25.00YesYes—
View
Eden AI
anthropic/claude-opus-4-5
200,00064,000$5.00 / $25.00YesYesYes
View
Impossibl
anthropic/claude-opus-4-5
200,00064,000$5.00 / $25.00YesYes—
View
Kilo Gateway
anthropic/claude-opus-4.5
200,00064,000$5.00 / $25.00YesYesYes
View
NanoGPT
anthropic/claude-opus-4.5
200,00064,000$5.00 / $25.00YesYesYes
View
NanoGPT
anthropic/claude-opus-4.5:thinking
200,00064,000$5.00 / $25.00YesYesYes
View
Neon
claude-opus-4-5
200,00064,000$5.00 / $25.00YesYesYes
View
Ofox
anthropic/claude-opus-4.5
200,00064,000$5.00 / $25.00YesYes—
View
Amazon Bedrockvia OpenRouter
anthropic/claude-opus-4.5
unknown		200,00064,000$5.50 / $27.50YesYesYes
View
Amazon Bedrockvia OpenRouter
anthropic/claude-opus-4.5
unknown		200,00064,000$5.00 / $25.00YesYesYes
View
Anthropicvia OpenRouter
anthropic/claude-opus-4.5
unknown		200,00064,000$5.00 / $25.00YesYesYes
View
Azurevia OpenRouter
anthropic/claude-opus-4.5
unknown		200,00064,000$5.00 / $25.00YesYesYes
View
Claude Platform on AWSvia OpenRouter
anthropic/claude-opus-4.5
unknown		200,00064,000$5.00 / $25.00YesYesYes
View
Googlevia OpenRouter
anthropic/claude-opus-4.5
unknown		200,00064,000$5.00 / $25.00YesYesYes
View
Opper
claude-opus-4-5
200,00064,000$5.00 / $25.00YesYesYes
View
OrcaRouter
anthropic/claude-opus-4.5
200,00064,000$5.00 / $25.00YesYes—
View
Pioneer
claude-opus-4-5
200,00064,000$5.00 / $25.00YesYes—
View
Requesty
claude-opus-4-5@eu
200,00064,000$5.50 / $27.50YesYesYes
View
Requesty
claude-opus-4-5
200,00064,000$5.00 / $25.00YesYesYes
View
SAP AI Core
anthropic--claude-4.5-opus
200,00064,000$5.00 / $25.00YesYes—
View
Snowflake Cortex
claude-opus-4-5
200,00064,000— / —YesYes—
View
Tempr Gateway
anthropic/claude-opus-4-5
200,00064,000$5.00 / $25.00YesYesYes
View
Venice AI
claude-opus-4-5
198,00032,768$6.00 / $30.00YesYesYes
View
Vercel AI Gateway
anthropic/claude-opus-4.5
200,00064,000$5.00 / $25.00YesYes—
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$5.00Per 1M input tokens
Output from$25.00Per 1M output tokens
Available offers28Across 21 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 · 6 lowest-priced configurations
InputOutput
Amazon Bedrockamazon-bedrock
$5.00$25.00
Anthropicanthropic
$5.00$25.00
Azureazure/global
$5.00$25.00
Claude Platform on AWSclaude-on-aws
$5.00$25.00
Googlegoogle-vertex/global
$5.00$25.00
Amazon Bedrockamazon-bedrock/eu-west-1
$5.50$27.50
anthropic/claude-opus-4.5Observed
Input
$5.00
Output
$25.00
Cache read
$0.50
Cache write
$6.25
Cache write · 1 hour
$10.00
Additional fees and pricing conditions
web search
$0.01 / search
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
Amazon Bedrockamazon-bedrock/eu-west-1$5.50$27.50$0.55$6.875
Amazon Bedrockamazon-bedrock$5.00$25.00$0.50$6.25
Anthropicanthropic$5.00$25.00$0.50$6.25
Azureazure/global$5.00$25.00$0.50$6.25
Claude Platform on AWSclaude-on-aws$5.00$25.00$0.50$6.25
Googlegoogle-vertex/global$5.00$25.00$0.50$6.25

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
3,943–7,237.76 ms
Amazon Bedrockamazon-bedrock
1,484–4,479.68 ms
Anthropicanthropic
1,126–8,818.28 ms
Azureazure/global
3,503.5–5,580.61 ms
Claude Platform on AWSclaude-on-aws
1,523–4,047.47 ms
Googlegoogle-vertex/global
7,165.5–10,389.85 ms
All latency percentiles 6 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock/eu-west-13,943 ms5,624 ms6,632.6 ms7,237.76 ms
Amazon Bedrockamazon-bedrock1,484 ms1,846 ms2,373.8 ms4,479.68 ms
Anthropicanthropic1,126 ms1,445 ms1,965.6 ms8,818.28 ms
Azureazure/global3,503.5 ms4,563.25 ms5,199.1 ms5,580.61 ms
Claude Platform on AWSclaude-on-aws1,523 ms3,066.25 ms3,647.2 ms4,047.47 ms
Googlegoogle-vertex/global7,165.5 ms7,416.5 ms7,641 ms10,389.85 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Amazon Bedrockamazon-bedrock/eu-west-1
84–109.48 t/s
Amazon Bedrockamazon-bedrock
45–102.85 t/s
Anthropicanthropic
39–101.2 t/s
Azureazure/global
16.5–23.85 t/s
Claude Platform on AWSclaude-on-aws
41–53.34 t/s
Googlegoogle-vertex/global
59–79 t/s
All throughput percentiles 6 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock/eu-west-184 t/s97 t/s104.8 t/s109.48 t/s
Amazon Bedrockamazon-bedrock45 t/s52 t/s55 t/s102.85 t/s
Anthropicanthropic39 t/s46 t/s69 t/s101.2 t/s
Azureazure/global16.5 t/s20.25 t/s22.5 t/s23.85 t/s
Claude Platform on AWSclaude-on-aws41 t/s46.25 t/s47.9 t/s53.34 t/s
Googlegoogle-vertex/global59 t/s66 t/s70 t/s79 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 · 6 endpoints
Endpoint5 minutes30 minutes24 hours
Amazon Bedrockamazon-bedrock/eu-west-1
Amazon Bedrockamazon-bedrock
Anthropicanthropic
Azureazure/global
Claude Platform on AWSclaude-on-aws
Googlegoogle-vertex/global

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-opus-4.5Observed
Design ArenaCategoryEloWin rateRank
models3d1,22958.5%36
modelsasciiart1,20154.8%25
modelscodecategories1,24859.5%36
modelsdataviz1,25158.5%30
modelsgamedev1,24259.3%35
modelssvg1,18058.7%32
modelsuicomponent1,24558.1%38
modelswebsite1,25359.7%37
agentsandroidnative1,19165.5%17
agentsfullstack1,15560.2%24
agentsmobileapps1,18660.7%19
agentswebapps1,15255.1%26

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 Opus 4.5
77.111%
gpqa diamondAnthropic: Claude Opus 4.5
86.177%
EvaluationConfigurationSourceResultsDetails
tau bench verified airlineAnthropic: Claude Opus 4.5anthropic/claude-4.5-opus-20251124OpenRouter77.111%
Details
models · asciiartClaude Opus 4.5anthropic/claude-4.5-opus-20251124Design Arena1,201 Elo
Details
models · uicomponentClaude Opus 4.5anthropic/claude-4.5-opus-20251124Design Arena1,245 Elo
Details
gpqa diamondAnthropic: Claude Opus 4.5anthropic/claude-4.5-opus-20251124OpenRouter86.177%
Details
models · 3dClaude Opus 4.5anthropic/claude-4.5-opus-20251124Design Arena1,229 Elo
Details
models · svgClaude Opus 4.5anthropic/claude-4.5-opus-20251124Design Arena1,180 Elo
Details
models · gamedevClaude Opus 4.5anthropic/claude-4.5-opus-20251124Design Arena1,242 Elo
Details
models · datavizClaude Opus 4.5anthropic/claude-4.5-opus-20251124Design Arena1,251 Elo
Details
models · codecategoriesClaude Opus 4.5anthropic/claude-4.5-opus-20251124Design Arena1,248 Elo
Details
models · websiteClaude Opus 4.5anthropic/claude-4.5-opus-20251124Design Arena1,253 Elo
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Technical details & API

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

Current route specifications
anthropic/claude-opus-4.5Observed
Context
200,000
Maximum output
64,000
Tokenizer
Claude
Input
file, image, text
Output
text
Moderation
Yes
Added to OpenRouter
2025-11-24
Base URLhttps://openrouter.ai/api/v1
Model IDanthropic/claude-opus-4.5
Version IDanthropic/claude-4.5-opus-20251124

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
  • verbosity

Frequently asked questions

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

How much does Claude Opus 4.5 (latest) cost?

Listed rates start at $5.00 per million input tokens and $25.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Claude Opus 4.5 (latest)?

There are 28 cataloged offers across 21 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: Yes. Structured output: Not reported. Support can vary by endpoint.

Catalog history · 2 recorded revisions

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

  • · cbc9b1e9d521
  • · c18931f6a3aa