How much does Claude Sonnet 5.5 cost?

On the Respan gateway, Claude Sonnet 5.5 costs from $1.00 per 1M input tokens and $5.00 per 1M output tokens on OpenRouter, after gateway discounts. Averaged across its 8 routes from 6 providers, it costs $1.90 per 1M input tokens and $9.50 per 1M output tokens.

Which providers serve Claude Sonnet 5.5 on Respan?

Claude Sonnet 5.5 is available through 8 routes from 6 providers: OpenRouter, Anthropic, Bedrock, DeepInfra, Perplexity, and Google Vertex AI. Bedrock and Google Vertex AI require your own provider API key (BYOK).

What is Claude Sonnet 5.5's context window?

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

How do I use Claude Sonnet 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-sonnet-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 Sonnet 5.5?

Over the last 30 days of requests through the Respan gateway, the fastest provider was Anthropic at 36 tokens per second, and the lowest response latency was 0.9 seconds on Bedrock. Speed varies with request size and provider.

Where does Claude Sonnet 5.5 rank on the Respan Index?

Claude Sonnet 5.5 scores 68.3 out of 100 on the Respan Index v1.1, ranking #6 of 143 models. By category: Coding 69.9, Agents 77.7, Reasoning 70.5, Knowledge & language 48.6, and Human preference 59.3. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

How does Claude Sonnet 5.5 score on benchmarks?

Claude Sonnet 5.5 has 31 published benchmark scores, including LiveBench Coding 91.4%, OSWorld 2.1 (offline subset) 83.9%, and GPQA Diamond 95.6%. Each score links to where it was published; the data is collected by llmmetric.com.

Claude Sonnet 5.5

Q: What is Claude Sonnet 5.5?

Claude Sonnet 5.5 is a model from Anthropic, released on Sep 28, 2026. Claude Sonnet 5.5 is Anthropic's model offering the best combination of speed and intelligence, with a 1M-token context window, 128K max output, and adaptive thinking.

Claude Sonnet 5.5 is Anthropic's model offering the best combination of speed and intelligence, with a 1M-token context window, 128K max output, and adaptive thinking.

Input / output, from: $1.00 / $5.00 per 1M
Weekly tokens / requests: 72.8M / 10.9K
Context: 1M tokens
Released: Sep 28, 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-sonnet-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-sonnet-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-sonnet-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-sonnet-5-5",

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

}'

Read docs

Providers

8 routes from 6 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-sonnet-5.5:batch`	1M	$1.00/M	$5.00/M	$0.05/M	+2
Anthropic`anthropic/claude-sonnet-5-5`	1M	$2.00/M	$10.00/M	$0.20/M	+2
BedrockBYOK only`bedrock/global.anthropic.claude-sonnet-5-5`	1M	$2.00/M	$10.00/M	$0.10/M	+2
DeepInfra`deepinfra/anthropic/claude-sonnet-5-5`	1M	$2.00/M	$10.00/M	$0.00/M	+2
OpenRouter`openrouter/anthropic/claude-sonnet-5.5`	1M	$2.00/M	$10.00/M	$0.10/M	+2
Perplexity`perplexity/anthropic/claude-sonnet-5-5`	1M	$2.00/M	$10.00/M	$0.10/M
Google Vertex AIBYOK only`vertex_ai/claude-sonnet-5-5@default`	1M	$2.00/M	$10.00/M	$0.20/M	+2
BedrockBYOK only`bedrock/us.anthropic.claude-sonnet-5-5`	1M	$2.20/M	$11.00/M	$0.11/M	+2

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

Pricing

Averaged across 8 routes from 6 providers, in USD per 1M tokens after gateway discounts.

Average input: $1.90 per 1M
Average output: $9.50 per 1M
Average cache read: $0.11 per 1M
Average cache write: $2.06 per 1M

Cost by volume

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

Highest$2.20/MBedrockLowest$1.00/MOpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway, 3 of 8 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

36tokens/sbest, on Anthropic

Faster than 51% of the other 484 models on the gateway

Anthropic36 tok/s
Bedrock4.3 tok/s
Perplexity3.1 tok/s

Time to first token

Lower is better

0.7son Anthropic

Faster than 85% of the other 63 models on the gateway

Response latency

Lower is better

0.9sbest, on Bedrock

Faster than 43% of the other 499 models on the gateway

Bedrock0.9 s
Perplexity1.3 s
Anthropic2.8 s

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

Benchmarks

The Respan Index plus 31 published scores from 8 sources, each linked to where it was published.

68.3/ 100

Respan Index#6 of 143

143 ranked models. The shaded band is this model's 95% interval, 63.1 to 72.8. Claude Fable 5.1 and Muse Wonder fall inside it, so the gap is within the margin of error.

6Claude Sonnet 5.568.3
5Claude Fable 5.169.2
7Muse Wonder66.9

Published scores

Benchmark	Score	Source	Published
LiveBench CodingLiveBench	91.4%	LiveBench	Oct 5, 2026
Terminal-Bench 4.0Anthropic	70.6%	Anthropic	Sep 28, 2026
Terminal-Bench 4.0Vals AI	64.1%	Vals AI	Oct 5, 2026
FrontierSWE V2Proximal Labs	61.9%	Proximal Labs	Oct 5, 2026
CursorBench 4.0Anthropic	55.5%	Anthropic	Sep 28, 2026
FrontierCode v1.1 (Main)Anthropic	46.2%	Anthropic	Sep 28, 2026

Benchmark	Score	Source	Published
OSWorld 2.1 (offline subset)Anthropic	83.9%	Anthropic	Oct 7, 2026
OSWorld 2.1 (partial)Anthropic	80.1%	Anthropic	Sep 28, 2026
APEX-AgentsMercor	75.5%	Mercor	Oct 5, 2026
LiveBench Agentic CodingLiveBench	56.3%	LiveBench	Oct 5, 2026

Benchmark	Score	Source	Published
GPQA DiamondEpoch AI	95.6%	Epoch AI	Oct 5, 2026
LiveBench ReasoningLiveBench	91.6%	LiveBench	Oct 5, 2026
LiveBench Data AnalysisLiveBench	78.6%	LiveBench	Oct 5, 2026
SimpleBenchSimpleBench	75.9%	SimpleBench	Oct 1, 2026
Mystery Game PuzzlesEpoch AI	65%	Epoch AI	Oct 5, 2026
Humanity's Last Exam (with tools)Anthropic	64.5%	Anthropic	Sep 28, 2026
Humanity's Last Exam (no tools)Anthropic	56.9%	Anthropic	Oct 7, 2026

Benchmark	Score	Source	Published
OTIS Mock AIME 2024-2025Epoch AI	100%	Epoch AI	Oct 5, 2026
LiveBench MathematicsLiveBench	96.7%	LiveBench	Oct 5, 2026
FrontierMath Tiers 1-3 v2Epoch AI	88.8%	Epoch AI	Oct 5, 2026
FrontierMath Tier 4 v2Epoch AI	80.5%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
LiveBench LanguageLiveBench	83.4%	LiveBench	Oct 5, 2026
LiveBench Instruction FollowingLiveBench	70.5%	LiveBench	Oct 5, 2026
SimpleQA VerifiedEpoch AI	46.5%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
Furniture AssemblyEpoch AI	75%	Epoch AI	Oct 5, 2026
Chartography (no tools)Anthropic	61.6%	Anthropic	Sep 28, 2026

Benchmark	Score	Source	Published
LMArena WebDevLMArena	1774 Elo · #3 of 99	LMArena	Oct 8, 2026
LMArena EloLMArena	1476 Elo · #26 of 147	LMArena	Oct 8, 2026
LMArena VisionLMArena	1266 Elo · #30 of 85	LMArena	Oct 9, 2026
LMArena AgentLMArena	0.1075 · #7 of 51	LMArena	Oct 12, 2026