How much does Claude Opus 4.5 cost?

Claude Opus 4.5 costs $5.00/M input tokens and $25.00/M output tokens, with separate rates for Cache Read at $0.50/M tokens, Cache Write at $6.25/M tokens, Cache Write (1h) at $10.00/M tokens, and Web Search at $10.00/1K calls.

What is the context length of Claude Opus 4.5?

Claude Opus 4.5 has a 200,000 token context window. It supports up to 64,000 completion tokens.

Does Claude Opus 4.5 support tool calling and structured outputs?

Yes. Claude Opus 4.5 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does Claude Opus 4.5 support?

Claude Opus 4.5 accepts files such as PDFs, images, and text as input and returns text.

Which providers serve Claude Opus 4.5?

Claude Opus 4.5 is served by 5 providers on OpenRouter: Claude Platform on AWS, Azure, Google Vertex, Amazon Bedrock, and Anthropic. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Claude Opus 4.5 released?

Claude Opus 4.5 was released on November 24, 2025.

Anthropic: Claude Opus 4.5

anthropic/claude-opus-4.5

Compare

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.

Modalities

In / out price

$5 / $25per 1M

Context

200K

Released

Nov 24, 2025

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


	$5.00	$25.00	$0.50	1.01s	40 tok/s	99.58%
	$5.00	$25.00	$0.50	--	--	100.00%
	$5.00	$25.00	$0.50	--	--	100.00%
	$5.00	$25.00	$0.50	1.51s	39 tok/s	99.94%
	$5.00	$25.00	$0.50	1.11s	33 tok/s	96.83%
Not used in Standard routing:Why these endpoints are not used
	$5.50	$27.50	$0.55	1.38s	79 tok/s	100.00%

Input $5.00Output $25.00
40 tok/s99.58% uptime
Input $5.00Output $25.00
-- tok/s100.00% uptime
Input $5.00Output $25.00
-- tok/s100.00% uptime
Input $5.00Output $25.00
39 tok/s99.94% uptime
Input $5.00Output $25.00
33 tok/s96.83% uptime
Not used in Standard routing:Why these endpoints are not used
Input $5.50Output $27.50
79 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$4.478/M tokens

Output

$25.13/M tokens

Claude Opus 4.5 — Price history

Price history

No effective price data for this selection

	$4.17	$25.00	19.7%	40.7%
	$4.51	$25.00	12.5%	2.2%
	$4.56	$25.00	10.7%	26.8%
	$4.82	$25.00	5.2%	29.0%
	$5.00	$25.00	0.0%	0.5%
Not used in Standard routing:Why these endpoints are not used
	$4.55	$27.50	33.0%	0.6%

Effective in $4.17Effective out $25.00
Token share
40.7%
Effective in $4.51Effective out $25.00
Token share
2.2%
Effective in $4.56Effective out $25.00
Token share
26.8%
Effective in $4.82Effective out $25.00
Token share
29.0%
Effective in $5.00Effective out $25.00
Token share
0.5%
Not used in Standard routing:Why these endpoints are not used
Effective in $4.55Effective out $27.50
Token share
0.6%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

79tok/s

P50, best across providers

Latency

1.01s

P50, best provider

Latency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchClaude Platform on AWS86.7%75.8%Anthropic86.2%75.9%Amazon Bedrock (EU)86.7%75.0%auto-routing87.2%74.2%Google Vertex86.0%75.3%Amazon Bedrock85.8%75.0%

+1 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.73%

Availability over the last 3 days

Last 72 hours

Availability 99.73%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.49%

Without Routing

98.47%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Anthropic: Claude Opus 4.5 (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	Claude Opus 4.5 (Reasoning) GPQA Diamond	86.6%
Artificial Analysis	Claude Opus 4.5 (Reasoning) HLE	30.1%
Artificial Analysis	Claude Opus 4.5 (Reasoning) IFBench	58.0%
Artificial Analysis	Claude Opus 4.5 (Reasoning) τ²-Bench Telecom	89.5%
Artificial Analysis	Claude Opus 4.5 (Reasoning) AA-LCR	77.3%
Artificial Analysis	Claude Opus 4.5 (Reasoning) CritPt	4.6%
Artificial Analysis	Claude Opus 4.5 (Reasoning) LiveCodeBench	87.1%
Artificial Analysis	Claude Opus 4.5 (Reasoning) Terminal-Bench Hard	47.0%
Artificial Analysis	Claude Opus 4.5 (Reasoning) MMLU-Pro	89.5%
Artificial Analysis	Claude Opus 4.5 (Reasoning) AIME 2025	91.3%
Artificial Analysis	Claude Opus 4.5 (Non-reasoning) GPQA Diamond	81.0%
Artificial Analysis	Claude Opus 4.5 (Non-reasoning) HLE	13.2%
Artificial Analysis	Claude Opus 4.5 (Non-reasoning) IFBench	43.0%
Artificial Analysis	Claude Opus 4.5 (Non-reasoning) τ²-Bench Telecom	86.3%
Artificial Analysis	Claude Opus 4.5 (Non-reasoning) AA-LCR	70.7%
Artificial Analysis	Claude Opus 4.5 (Non-reasoning) CritPt	0.3%
Artificial Analysis	Claude Opus 4.5 (Non-reasoning) LiveCodeBench	73.8%
Artificial Analysis	Claude Opus 4.5 (Non-reasoning) Terminal-Bench Hard	40.9%
Artificial Analysis	Claude Opus 4.5 (Non-reasoning) MMLU-Pro	88.9%
Artificial Analysis	Claude Opus 4.5 (Non-reasoning) AIME 2025	62.7%
Design Arena	Claude Opus 4.5 Models Arena 3D Elo	1193
Design Arena	Claude Opus 4.5 Models Arena Asciiart Elo	1185
Design Arena	Claude Opus 4.5 Models Arena Code Categories Elo	1232
Design Arena	Claude Opus 4.5 Models Arena Data Visualization Elo	1240
Design Arena	Claude Opus 4.5 Models Arena Game Development Elo	1218
Design Arena	Claude Opus 4.5 Models Arena SVG Elo	1170
Design Arena	Claude Opus 4.5 Models Arena UI Component Elo	1228
Design Arena	Claude Opus 4.5 Models Arena Website Elo	1239
Design Arena	Claude Opus 4.5 Agents Arena Androidnative Elo	1162
Design Arena	Claude Opus 4.5 Agents Arena Full Stack Elo	1128
Design Arena	Claude Opus 4.5 Agents Arena Mobile Apps Elo	1181
Design Arena	Claude Opus 4.5 Agents Arena Webapps Elo	1136
Vals AI	Claude Opus 4.5 (Nonthinking) AIME	76.9%
Vals AI	Claude Opus 4.5 (Nonthinking) CorpFin v2	61.3%
Vals AI	Claude Opus 4.5 (Nonthinking) Finance Agent v1	54.5%
Vals AI	Claude Opus 4.5 (Nonthinking) GPQA Diamond	79.5%
Vals AI	Claude Opus 4.5 (Nonthinking) IOI v1	23.6%
Vals AI	Claude Opus 4.5 (Nonthinking) LiveCodeBench	75.0%
Vals AI	Claude Opus 4.5 (Nonthinking) LegalBench	82.8%
Vals AI	Claude Opus 4.5 (Nonthinking) MedCode	45.2%
Vals AI	Claude Opus 4.5 (Nonthinking) MedQA	93.2%
Vals AI	Claude Opus 4.5 (Nonthinking) MedScribe	83.2%
Vals AI	Claude Opus 4.5 (Nonthinking) MGSM	94.8%
Vals AI	Claude Opus 4.5 (Nonthinking) MMLU Pro	85.6%
Vals AI	Claude Opus 4.5 (Nonthinking) MMMU Pro	81.1%
Vals AI	Claude Opus 4.5 (Nonthinking) MortgageTax	68.7%
Vals AI	Claude Opus 4.5 (Nonthinking) Vals RSI Index	14.8%
Vals AI	Claude Opus 4.5 (Nonthinking) SAGE v1	45.0%
Vals AI	Claude Opus 4.5 (Nonthinking) TaxEval v2	74.3%
Vals AI	Claude Opus 4.5 (Nonthinking) Terminal-Bench 2.0	58.4%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

2.71Btokens

SillyTavern

SillyTavern is the LLM frontend for power users, a chat interface that connects to any model and gives deep control through character creation, roleplay, and prompt customization.

2.02Btokens

Chub AI

GenAI for everyone

1.88Btokens

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

1.29Btokens

Taste Engine

new

985Mtokens

Rest of OpenRouter

703M

Top 5 Apps

90.1M

Available through EU in-region routing

Anthropic: Claude Opus 4.5 is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).

Providers in Europe

Amazon Bedrock

Prices in Europe

Amazon Bedrock: $5.50/M tokens input, $27.50/M tokens output

Base URL

https://eu.openrouter.ai/api/v1

Plan

Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing

Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs

More models from Anthropic

Claude Fable 5.2

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible software migrations, designed working electronic devices from scratch, and made progress on open problems in physics and mathematics. It communicates more clearly than earlier Fable models and generates output up to 30% faster than Fable 5.1. Adaptive extended thinking is always on, with reasoning effort levels from low to max (default high) and preserved thinking across turns. Anthropic recommends Opus 5.5 as the daily driver for most coding and knowledge work, with Fable 5.2 for the most ambitious, open-ended problems.

Text1M context$8 / $40

Claude Fable 5.2 (batch)

Text1M context$4 / $20

Claude Haiku 5.5

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window.

It is the first Haiku model with adjustable effort. Thinking is adaptive and on by default, with effort as the main lever for trading off depth, latency, and cost; it can be turned off at low, medium, and high effort.

Text1M context$0.10 / $0.50

Claude Haiku 5.5 (batch)

Text1M context$0.05 / $0.25

Claude Sonnet 5.5

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor.

Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.

Text1M context$2 / $10

Claude Sonnet 5.5 (batch)

Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.

Text1M context$1 / $5

Claude Opus 5.5

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.

The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.

Text1M context$4 / $20

Claude Opus 5.5 (batch)

Text1M context$2 / $10

Claude Fable 5.1

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.

Text1M context$10 / $50

Claude Fable 5.1 (batch)

Text1M context$5 / $25

Claude Opus 5

Fast-mode variant of Opus 5 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Note: As of September 1, 2026, this dedicated fast model is deprecated. Fast mode is now served by the fast service tier endpoint on Claude Opus 5 — request it with service_tier: "fast" or speed: "fast". Requests to this model keep working and are served by the same fast tier capacity, so no action is required, but new integrations should target the regular model. Learn more in our service tier docs: https://openrouter.ai/docs/guides/features/service-tiers

Text1M context

Claude Opus 5

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.

The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.

Text1M context$5 / $25

Claude Opus 5 (batch)

The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.

Text1M context$2.50 / $12.50

Claude Sonnet 5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.

Text1M context$2 / $10

Claude Sonnet 5 (batch)

Text1M context$1 / $5

Claude Fable Latest

This model always redirects to the latest model in the Claude Fable family.

Text1M context

Claude Fable 5

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.

It is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.

Text1M context$10 / $50

Claude Fable 5 (batch)

Text1M context$5 / $25

Claude Opus 4.8

Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Note: As of September 1, 2026, this dedicated fast model is deprecated. Fast mode is now served by the fast service tier endpoint on Claude Opus 4.8 — request it with service_tier: "fast" or speed: "fast". Requests to this model keep working and are served by the same fast tier capacity, so no action is required, but new integrations should target the regular model. Learn more in our service tier docs: https://openrouter.ai/docs/guides/features/service-tiers

Text1M context

Claude Opus 4.8

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.

It is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.

Text1M context$5 / $25

Anthropic: Claude Opus 4.5

Providers