How much does Claude Opus 5.5 cost?

On the Respan gateway, Claude Opus 5.5 costs from $2.00 per 1M input tokens and $10.00 per 1M output tokens on OpenRouter, after gateway discounts. Averaged across its 9 routes from 7 providers, it costs $3.82 per 1M input tokens and $19.11 per 1M output tokens.

Which providers serve Claude Opus 5.5 on Respan?

Claude Opus 5.5 is available through 9 routes from 7 providers: OpenRouter, Anthropic, Bedrock, DeepInfra, Inference.net, Perplexity, and 1 more. Bedrock and Google Vertex AI require your own provider API key (BYOK).

What is Claude Opus 5.5's context window?

Claude Opus 5.5 accepts up to 1M tokens of context on its largest provider route.

How do I use Claude Opus 5.5 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-5-5". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How fast is Claude Opus 5.5?

Over the last 30 days of requests through the Respan gateway, the fastest provider was Bedrock at 1206 tokens per second, and the lowest response latency was 2.3 seconds on Perplexity. Speed varies with request size and provider.

Where does Claude Opus 5.5 rank on the Respan Index?

Claude Opus 5.5 scores 72.7 out of 100 on the Respan Index v1.1, ranking #1 of 143 models. By category: Coding 72.5, Agents 78.7, Reasoning 75.3, Knowledge & language 70.4, and Human preference 60.4. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

How does Claude Opus 5.5 score on benchmarks?

Claude Opus 5.5 has 35 published benchmark scores, including LiveBench Coding 89.3%, OSWorld 2.0 (partial) 81.8%, and LiveBench Reasoning 92.2%. Each score links to where it was published; the data is collected by llmmetric.com.

Claude Opus 5.5

Q: What is Claude Opus 5.5?

Claude Opus 5.5 is a model from Anthropic, released on Sep 22, 2026. Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.

Input / output, from: $2.00 / $10.00 per 1M
Weekly tokens / requests: 126.2M / 4K
Context: 1M tokens
Released: Sep 22, 2026

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-5-5".

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-5-5",

    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-5-5",

  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-5-5",

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

}'

Read docs

Providers

9 routes from 7 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-5.5:batch`	1M	$2.00/M	$10.00/M	$0.10/M	+2
Anthropic`anthropic/claude-opus-5-5`	1M	$4.00/M	$20.00/M	$0.20/M	+2
BedrockBYOK only`bedrock/global.anthropic.claude-opus-5-5`	1M	$4.00/M	$20.00/M	$0.20/M	+2
DeepInfra`deepinfra/anthropic/claude-opus-5-5`	1M	$4.00/M	$20.00/M	$0.20/M	+2
Inference.net`inference_net/claude-opus-5-5`	1M	$4.00/M	$20.00/M	$0.20/M
OpenRouter`openrouter/anthropic/claude-opus-5.5`	1M	$4.00/M	$20.00/M	$0.20/M	+2
Perplexity`perplexity/anthropic/claude-opus-5-5`	1M	$4.00/M	$20.00/M	$0.20/M
Google Vertex AIBYOK only`vertex_ai/claude-opus-5-5@default`	1M	$4.00/M	$20.00/M	$0.20/M	+2
BedrockBYOK only`bedrock/us.anthropic.claude-opus-5-5`	1M	$4.40/M	$22.00/M	$0.22/M	+2

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

Pricing

Averaged across 9 routes from 7 providers, in USD per 1M tokens after gateway discounts.

Average input: $3.82 per 1M
Average output: $19.11 per 1M
Average cache read: $0.19 per 1M
Average cache write: $3.67 per 1M

Cost by volume

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

Highest$4.40/MBedrockLowest$2.00/MOpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway, 3 of 9 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

1206tokens/sbest, on Bedrock

Faster than 96% of the other 484 models on the gateway

Bedrock1206 tok/s
Anthropic348 tok/s
Perplexity1.7 tok/s

Time to first token

Lower is better

5.1sbest, on Bedrock

Faster than 12% of the other 63 models on the gateway

Bedrock5.1 s
Anthropic8.2 s

Response latency

Lower is better

2.3sbest, on Perplexity

Faster than 5% of the other 499 models on the gateway

Perplexity2.3 s
Bedrock5.5 s
Anthropic22 s

No traffic in the last 30 days on OpenRouter, Bedrock, DeepInfra, Inference.net, and Google Vertex AI.

Benchmarks

The Respan Index plus 35 published scores from 10 sources, each linked to where it was published.

72.7/ 100

Respan Index#1 of 143

143 ranked models. The shaded band is this model's 95% interval, 68.8 to 76.2. Gemini 4 Argon and GPT-6 Astra fall inside it, so the gap is within the margin of error.

Published scores

Benchmark	Score	Source	Published
LiveBench CodingLiveBench	89.3%	LiveBench	Oct 5, 2026
MirrorCodeEpoch AI	77.4%	Epoch AI	Oct 5, 2026
Terminal-Bench 4.0Anthropic	66.4%	Anthropic	Sep 22, 2026
Terminal-Bench 4.0Vals AI	65.2%	Vals AI	Oct 5, 2026
FrontierSWE V2Proximal Labs	62.3%	Proximal Labs	Oct 5, 2026
Terminal-Bench Science 0.1Anthropic	58.7%	Anthropic	Sep 22, 2026
CursorBench 4.0Anthropic	57.8%	Anthropic	Sep 22, 2026
FrontierCode v1.1 (Main)Anthropic	54.4%	Anthropic	Sep 22, 2026

Benchmark	Score	Source	Published
OSWorld 2.0 (partial)Anthropic	81.8%	Anthropic	Sep 22, 2026
APEX-AgentsMercor	73.5%	Mercor	Oct 5, 2026
LiveBench Agentic CodingLiveBench	71.7%	LiveBench	Oct 5, 2026
AutomationBench 1.0.6zapier.com	40%	zapier.com	Sep 22, 2026
Vending-Bench 2Andon Labs	9235.25 · #8 of 59	Andon Labs	Oct 5, 2026
GDPval-AA v2.1Anthropic	1846 Elo	Anthropic	Sep 22, 2026

Benchmark	Score	Source	Published
LiveBench ReasoningLiveBench	92.2%	LiveBench	Oct 5, 2026
GPQA DiamondEpoch AI	90.6%	Epoch AI	Oct 5, 2026
SimpleBenchSimpleBench	88.4%	SimpleBench	Sep 24, 2026
LiveBench Data AnalysisLiveBench	80.3%	LiveBench	Oct 5, 2026
EBR-benchEpoch AI	71.4%	Epoch AI	Oct 5, 2026
Mystery Game PuzzlesEpoch AI	71%	Epoch AI	Oct 5, 2026
Humanity's Last Exam (with tools)Anthropic	67.7%	Anthropic	Sep 22, 2026

Benchmark	Score	Source	Published
OTIS Mock AIME 2024-2025Epoch AI	100%	Epoch AI	Oct 5, 2026
LiveBench MathematicsLiveBench	97.1%	LiveBench	Oct 5, 2026
FrontierMath Tier 4 v2Epoch AI	95%	Epoch AI	Oct 5, 2026
FrontierMath Tiers 1-3 v2Epoch AI	91.2%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
LiveBench LanguageLiveBench	86.3%	LiveBench	Oct 5, 2026
SimpleQA VerifiedEpoch AI	72.2%	Epoch AI	Oct 5, 2026
LiveBench Instruction FollowingLiveBench	67%	LiveBench	Oct 5, 2026

Benchmark	Score	Source	Published
Chartography (with tools)Anthropic	89%	Anthropic	Sep 22, 2026
Furniture AssemblyEpoch AI	83.3%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
LMArena WebDevLMArena	1813 Elo · #1 of 99	LMArena	Oct 8, 2026
LMArena EloLMArena	1507 Elo · #2 of 147	LMArena	Oct 8, 2026
LMArena VisionLMArena	1293 Elo · #9 of 85	LMArena	Oct 9, 2026
LMArena AgentLMArena	0.1789 · #1 of 51	LMArena	Oct 12, 2026