How much does Claude Opus 4.5 cost?

On the Respan gateway, Claude Opus 4.5 costs from $2.50 per 1M input tokens and $12.50 per 1M output tokens on OpenRouter, after gateway discounts. Averaged across its 5 routes from 4 providers, it costs $4.50 per 1M input tokens and $22.50 per 1M output tokens.

Which providers serve Claude Opus 4.5 on Respan?

Claude Opus 4.5 is available through 5 routes from 4 providers: OpenRouter, Anthropic, Perplexity, and Google Vertex AI. Google Vertex AI requires your own provider API key (BYOK).

What is Claude Opus 4.5's context window?

Claude Opus 4.5 accepts up to 200K tokens of context on its largest provider route.

How do I use Claude Opus 4.5 with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "anthropic/claude-opus-4-5". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How fast is Claude Opus 4.5?

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 35 tokens per second, and the lowest response latency was 1.6 seconds on Perplexity. Speed varies with request size and provider.

Where does Claude Opus 4.5 rank on the Respan Index?

Claude Opus 4.5 scores 37.4 out of 100 on the Respan Index v1.1, ranking #54 of 143 models. By category: Coding 19.2, Agents 53.8, Reasoning 27.0, Knowledge & language 45.5, and Human preference 52.6. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

How does Claude Opus 4.5 score on benchmarks?

Claude Opus 4.5 has 39 published benchmark scores, including SWE-bench Verified 80.9%, τ2-bench (Telecom) 98.2%, and GPQA Diamond 87%. Each score links to where it was published; the data is collected by llmmetric.com.

Claude Opus 4.5

Q: What is Claude Opus 4.5?

Claude Opus 4.5 is a model from Anthropic, released on Nov 24, 2025. Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. $5 per million input tokens, $25 per million output tokens. 200,000 token context window, maximum output of 64,000 tokens. Higher uptime with 4 providers. Includes independent benchmarks from Artificial Analysis.

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. $5 per million input tokens, $25 per million output tokens. 200,000 token context window, maximum output of 64,000 tokens. Higher uptime with 4 providers. Includes independent benchmarks from Artificial Analysis.

Input / output, from: $2.50 / $12.50 per 1M
Context: 200K tokens
Released: Nov 24, 2025

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "anthropic/claude-opus-4-5".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="anthropic/claude-opus-4-5",

    messages=[{"role": "user", "content": "Hello!"}],

)

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

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "anthropic/claude-opus-4-5",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "anthropic/claude-opus-4-5",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

5 routes from 4 providers, cheapest first, priced per 1M tokens after gateway discounts. BYOK routes use your own key.

Provider	Context	Input	Output	Cache read	Capabilities
OpenRouter`openrouter/anthropic/claude-opus-4.5:batch`	200K	$2.50/M	$12.50/M	$0.25/M	+2
Anthropic`anthropic/claude-opus-4-5`	200K	$5.00/M	$25.00/M	$0.50/M	+2
OpenRouter`openrouter/anthropic/claude-opus-4.5`	200K	$5.00/M	$25.00/M	$0.50/M	+2
Perplexity`perplexity/anthropic/claude-opus-4-5`	200K	$5.00/M	$25.00/M	$0.50/M
Google Vertex AIBYOK only`vertex_ai/claude-opus-4-5@20251101`	200K	$5.00/M	$25.00/M	$0.50/M	+2

Is a provider down? OpenRouter status, Anthropic status, Perplexity status, Google AI status

Pricing

Averaged across 5 routes from 4 providers, in USD per 1M tokens after gateway discounts.

Average input: $4.50 per 1M
Average output: $22.50 per 1M
Average cache read: $0.45 per 1M
Average cache write: $5.63 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$5.00/MAnthropic, OpenRouter, Perplexity, and Google Vertex AILowest$2.50/MOpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway, 3 of 5 routes had traffic in that window. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

35tokens/sbest, on OpenRouter

Faster than 22% of the other 485 models on the gateway

OpenRouter35 tok/s
Anthropic11 tok/s
Perplexity3.1 tok/s

Response latency

Lower is better

1.6sbest, on Perplexity

Faster than 49% of the other 501 models on the gateway

Perplexity1.6 s
Anthropic1.8 s
OpenRouter4.2 s

No traffic in the last 30 days on OpenRouter and Google Vertex AI.

Benchmarks

The Respan Index plus 39 published scores from 11 sources, each linked to where it was published.

37.4/ 100

Respan Index#54 of 143

143 ranked models. The shaded band is this model's 95% interval, 33.6 to 41.7. Qwen3.6-Max-Preview and Gemini 3 Pro Preview fall inside it, so the gap is within the margin of error.

54Claude Opus 4.537.4
53Qwen3.6-Max-Preview38.0
55Gemini 3 Pro Preview37.3

Published scores

Benchmark	Score	Source	Published
SWE-bench VerifiedAnthropic	80.9%	Anthropic	Nov 24, 2025
LiveBench CodingLiveBench	79.7%	LiveBench	Oct 5, 2026
SWE-bench VerifiedEpoch AI	76.7%	Epoch AI	Oct 5, 2026
WeirdMLHåvard Tveit Ihle	63.7%	Håvard Tveit Ihle	Oct 5, 2026
Terminal-Bench 2.0Anthropic	59.3%	Anthropic	Nov 24, 2025
GSO Opt@1GSO	24.5%	GSO	Nov 28, 2025

Benchmark	Score	Source	Published
τ2-bench (Telecom)Anthropic	98.2%	Anthropic	Nov 24, 2025
tau2-bench TelecomSierra	92.3%	Sierra	Feb 26, 2026
τ2-bench (Retail)Anthropic	88.9%	Anthropic	Nov 24, 2025
tau2-bench AirlineSierra	84%	Sierra	Feb 26, 2026
tau2-bench RetailSierra	79.6%	Sierra	Feb 26, 2026
OSWorldAnthropic	66.3%	Anthropic	Nov 24, 2025
MCP AtlasAnthropic	62.3%	Anthropic	Nov 24, 2025
BALROGBALROG	43.5%	BALROG	Feb 24, 2026
LiveBench Agentic CodingLiveBench	39.7%	LiveBench	Oct 5, 2026
tau2-bench Banking KnowledgeSierra	24.7%	Sierra	Feb 26, 2026
Vending-Bench 2Andon Labs	4967.06 · #31 of 59	Andon Labs	Oct 5, 2026

Benchmark	Score	Source	Published
GPQA DiamondAnthropic	87%	Anthropic	Nov 24, 2025
GPQA DiamondEpoch AI	86%	Epoch AI	Oct 5, 2026
LiveBench ReasoningLiveBench	80.1%	LiveBench	Oct 5, 2026
LiveBench Data AnalysisLiveBench	74.4%	LiveBench	Oct 5, 2026
SimpleBenchSimpleBench	62%	SimpleBench	Nov 20, 2025
ARC-AGI-2 (Verified)Anthropic	37.6%	Anthropic	Nov 24, 2025
Mystery Game PuzzlesEpoch AI	22%	Epoch AI	Oct 5, 2026
EBR-benchEpoch AI	14.3%	Epoch AI	Oct 5, 2026
Chess PuzzlesEpoch AI	12%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
LiveBench MathematicsLiveBench	90.4%	LiveBench	Oct 5, 2026
OTIS Mock AIME 2024-2025Epoch AI	86.1%	Epoch AI	Oct 5, 2026
FrontierMath Tiers 1-3 v2Epoch AI	34.4%	Epoch AI	Oct 5, 2026
FrontierMath Tier 4 v2Epoch AI	4.9%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
MMMLUAnthropic	90.8%	Anthropic	Nov 24, 2025
LiveBench LanguageLiveBench	81.3%	LiveBench	Oct 5, 2026
LiveBench Instruction FollowingLiveBench	62.5%	LiveBench	Oct 5, 2026
SimpleQA VerifiedEpoch AI	45.7%	Epoch AI	Oct 5, 2026