How much does Claude Sonnet 4.6 cost?

On the Respan gateway, Claude Sonnet 4.6 costs from $1.50 per 1M input tokens and $7.50 per 1M output tokens on OpenRouter, after gateway discounts. Averaged across its 9 routes from 7 providers, it costs $2.87 per 1M input tokens and $14.33 per 1M output tokens.

Which providers serve Claude Sonnet 4.6 on Respan?

Claude Sonnet 4.6 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 Sonnet 4.6's context window?

Claude Sonnet 4.6 accepts up to 1M tokens of context on its largest provider route.

How do I use Claude Sonnet 4.6 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-4-6". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How fast is Claude Sonnet 4.6?

Over the last 30 days of requests through the Respan gateway, the fastest provider was Anthropic at 2077 tokens per second, and the lowest response latency was 0.7 seconds on Bedrock. Speed varies with request size and provider.

Where does Claude Sonnet 4.6 rank on the Respan Index?

Claude Sonnet 4.6 scores 34.4 out of 100 on the Respan Index v1.1, ranking #58 of 143 models. By category: Coding 14.6, Agents 50.8, Reasoning 25.7, Knowledge & language 35.7, and Human preference 53.4. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

How does Claude Sonnet 4.6 score on benchmarks?

Claude Sonnet 4.6 has 36 published benchmark scores, including SWE-bench Verified 79.6%, Tau2-bench Telecom 97.9%, and GPQA Diamond 89.9%. Each score links to where it was published; the data is collected by llmmetric.com.

Claude Sonnet 4.6

Q: What is Claude Sonnet 4.6?

Claude Sonnet 4.6 is a model from Anthropic, released on Feb 17, 2026. Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

Input / output, from: $1.50 / $7.50 per 1M
Weekly tokens / requests: 34.4M / 9.9K
Context: 1M tokens
Released: Feb 17, 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-4-6".

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-4-6",

    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-4-6",

  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-4-6",

    "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-sonnet-4.6:batch`	1M	$1.50/M	$7.50/M	$0.15/M	+2
Anthropic`anthropic/claude-sonnet-4-6`	200K	$3.00/M	$15.00/M	$0.30/M	+2
BedrockBYOK only`bedrock/global.anthropic.claude-sonnet-4-6`	200K	$3.00/M	$15.00/M	$0.30/M	+2
DeepInfra`deepinfra/anthropic/claude-sonnet-4-6`	1M	$3.00/M	$15.00/M	$0.00/M	+2
Inference.net`inference_net/claude-sonnet-4-6`	1M	$3.00/M	$15.00/M	$0.30/M
OpenRouter`openrouter/anthropic/claude-sonnet-4.6`	1M	$3.00/M	$15.00/M	$0.30/M	+2
Perplexity`perplexity/anthropic/claude-sonnet-4-6`	200K	$3.00/M	$15.00/M	$0.30/M
Google Vertex AIBYOK only`vertex_ai/claude-sonnet-4-6@default`	200K	$3.00/M	$15.00/M	$0.30/M	+2
BedrockBYOK only`bedrock/us.anthropic.claude-sonnet-4-6`	200K	$3.30/M	$16.50/M	$0.33/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: $2.87 per 1M
Average output: $14.33 per 1M
Average cache read: $0.25 per 1M
Average cache write: $2.75 per 1M

Cost by volume

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

Highest$3.30/MBedrockLowest$1.50/MOpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway, 4 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

2077tokens/sbest, on Anthropic

Faster than 99% of the other 485 models on the gateway

Anthropic2077 tok/s
Bedrockus.anthropic.claude-sonnet-4-66.7 tok/s
Bedrockglobal.anthropic.claude-sonnet-4-66.6 tok/s

Time to first token

Lower is better

1.0son Anthropic

Faster than 81% of the other 64 models on the gateway

Response latency

Lower is better

0.7sbest, on Bedrock (us.anthropic.claude-sonnet-4-6)

Faster than 12% of the other 501 models on the gateway

Bedrockus.anthropic.claude-sonnet-4-60.7 s
Bedrockglobal.anthropic.claude-sonnet-4-60.8 s
Perplexity1.4 s

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

Benchmarks

The Respan Index plus 36 published scores from 10 sources, each linked to where it was published.

34.4/ 100

Respan Index#58 of 143

143 ranked models. The shaded band is this model's 95% interval, 29.5 to 40.2. Hy3 and GLM-5.1 fall inside it, so the gap is within the margin of error.

58Claude Sonnet 4.634.4
57Hy336.9
58GLM-5.134.4

Published scores

Benchmark	Score	Source	Published
SWE-bench VerifiedAnthropic	79.6%	Anthropic	Feb 17, 2026
LiveBench CodingLiveBench	79.3%	LiveBench	Oct 5, 2026
SWE-bench VerifiedEpoch AI	75.2%	Epoch AI	Oct 5, 2026
WeirdMLHåvard Tveit Ihle	66.1%	Håvard Tveit Ihle	Oct 5, 2026
Terminal-Bench 2.0Anthropic	59.1%	Anthropic	Feb 17, 2026
DeepSWE v1.1Datacurve	29.9%	Datacurve	Oct 5, 2026

Benchmark	Score	Source	Published
Tau2-bench TelecomAnthropic	97.9%	Anthropic	Feb 17, 2026
Tau2-bench RetailAnthropic	91.7%	Anthropic	Feb 17, 2026
OSWorld-VerifiedAnthropic	72.5%	Anthropic	Feb 17, 2026
OSWorld-VerifiedXLANG	72.1%	XLANG	Mar 8, 2026
MCP AtlasAnthropic	61.3%	Anthropic	Feb 17, 2026
APEX-AgentsMercor	43%	Mercor	Oct 5, 2026
LiveBench Agentic CodingLiveBench	42.6%	LiveBench	Oct 5, 2026
Vending-Bench 2Andon Labs	7204.14 · #15 of 59	Andon Labs	Oct 5, 2026
GDPval-AAAnthropic	1633 Elo	Anthropic	Feb 17, 2026

Benchmark	Score	Source	Published
GPQA DiamondAnthropic	89.9%	Anthropic	Feb 17, 2026
GPQA DiamondEpoch AI	87.4%	Epoch AI	Oct 5, 2026
LiveBench ReasoningLiveBench	84.8%	LiveBench	Oct 5, 2026
LiveBench Data AnalysisLiveBench	77.9%	LiveBench	Oct 5, 2026
ARC-AGI-2 (Verified)Anthropic	58.3%	Anthropic	Feb 17, 2026
Humanity's Last Exam (with tools)Anthropic	49%	Anthropic	Feb 17, 2026
Humanity's Last Exam (no tools)Anthropic	33.2%	Anthropic	Feb 17, 2026
Mystery Game PuzzlesEpoch AI	16%	Epoch AI	Oct 5, 2026
Chess PuzzlesEpoch AI	13%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
LiveBench MathematicsLiveBench	87%	LiveBench	Oct 5, 2026
OTIS Mock AIME 2024-2025Epoch AI	85.8%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
MMMLUAnthropic	89.3%	Anthropic	Feb 17, 2026
LiveBench LanguageLiveBench	76.1%	LiveBench	Oct 5, 2026
LiveBench Instruction FollowingLiveBench	63.2%	LiveBench	Oct 5, 2026
SimpleQA VerifiedEpoch AI	35.5%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
MMMU-Pro (with tools)Anthropic	75.6%	Anthropic	Feb 17, 2026
MMMU-Pro (no tools)Anthropic	74.5%	Anthropic	Feb 17, 2026

Benchmark	Score	Source	Published
LMArena WebDevLMArena	1522 Elo · #40 of 99	LMArena	Oct 8, 2026
LMArena EloLMArena	1472 Elo · #34 of 147	LMArena	Oct 8, 2026
LMArena VisionLMArena	1275 Elo · #25 of 85	LMArena	Oct 9, 2026