Textby Anthropic

Claude Sonnet 4.6

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...

  • By price it is among the most expensive of the 348 text models GenMagic runs (315th cheapest).
  • It scores 30.5 on the Artificial Analysis Intelligence Index, 39th of the 121 text models with a score.
  • Among the models GenMagic runs, it places in the top 10 on 2 of its 50 benchmarks: 2nd of 19 on DeepResearchBench (FutureSearch), 10th of 34 on Design Arena: Godot Game Dev (agentic).
  • It was listed on Feb 17, 2026.

Data last changed Nov 12, 2026 · tracked since Oct 29, 2026 · Every model change

Try Claude Sonnet 4.6

Generate with Claude Sonnet 4.6 right here. Verify your email to start with free credits.

~$0.027
Try

Specifications

Context window

1M tokens

Max output

128K tokens

Input price

$4.50 / 1M tokens

Output price

$22.50 / 1M tokens

Cached input

$0.45 / 1M tokens

Benchmarks

How Claude Sonnet 4.6 scores on public benchmarks. Each card links to the benchmark explainer and to the original source.

31.8

source date 2026-11-11
Source: openrouter

63

source date 2026-11-11
Source: openrouter

30.5

source date 2026-09-18
Source: openrouter
AIMEMathematics

71.1%± 6.8

maxsource date 2026-08-06
Source: epoch
APEX-AgentsAgentic & Tool Use

43%

high
Source: epoch
ARC-AGI-1Reasoning & Knowledge

86.5%

high
Source: epoch
ARC-AGI-2Reasoning & Knowledge

60.4%

high
Source: epoch
Chess PuzzlesReasoning & Knowledge

23%± 4.2

maxsource date 2026-10-13
Source: epoch
Design Arena: 3DDesign & Generation

1219 Elo

Source: designarena
Design Arena: CodeDesign & Generation

1270 Elo

Source: designarena
Design Arena: SVGDesign & Generation

1188 Elo

Source: designarena
DeepSWECoding

29.9%

high; Reasoning effort: high; Harness: mini-swe-agent
Source: epoch
DTBenchReasoning & Knowledge

89.9%

max
Source: epoch

24.3

unknown; Reasoning effort: max; Harness: claude-code
Source: epoch
FrontierMathMathematics

32.4%± 2.8

budget:16ksource date 2026-02-20
Source: epoch

8.3%± 4.0

budget:16ksource date 2026-02-21
Source: epoch

73%

budget:32k; Tools: None
Source: epoch
GPQA DiamondReasoning & Knowledge

70.6%± 13.7

source date 2026-10-31
Source: openrouter
LMArena (Coding)Instruction & Preference

1504 Elo

source date 2026-11-09
Source: lmarena
LMArena: Creative WritingInstruction & Preference

1434 Elo

source date 2026-11-09
Source: lmarena
LMArena: Hard PromptsInstruction & Preference

1484 Elo

source date 2026-11-09
Source: lmarena

1479 Elo

source date 2026-11-09
Source: lmarena
LMArena: MathMathematics

1482 Elo

source date 2026-11-09
Source: lmarena
LMArena: Multi-TurnInstruction & Preference

1463 Elo

source date 2026-11-09
Source: lmarena
LMArena (Overall)Instruction & Preference

1458 Elo

source date 2026-11-09
Source: lmarena
LMCAReasoning & Knowledge

46.5

max
Source: epoch
Mystery Game PuzzlesReasoning & Knowledge

14%± 3.5

source date 2026-08-06
Source: epoch
OSWorldAgentic & Tool Use

9.3%

medium
Source: epoch
OSWorld (original)Agentic & Tool Use

72.1%

Source: epoch
ProofBenchMathematics

45%± 5.0

max; Reasoning effort: max
Source: epoch
SciCodeCoding

46.8%

max
Source: epoch
SimpleQA VerifiedReasoning & Knowledge

32.8%± 1.5

maxsource date 2026-08-27
Source: epoch

75.2%± 2.0

source date 2026-02-21
Source: epoch
tau-bench (Airline)Agentic & Tool Use

74.1%± 2.6

source date 2026-10-31
Source: openrouter

53.4%± 2.8

unknown
Source: epoch
WebDev ArenaAgentic & Tool Use

1521 Elo

Source: epoch
WeirdMLCoding

66.1%± 0.0

medium
Source: epoch

Compare against every model in the full benchmark matrix.

Capabilities

Reasoning

Works through multi-step problems before answering, for harder tasks.

Vision input

Accepts images alongside text, so you can prompt with pictures and screenshots.

Tool use

Can call functions and tools, enabling agentic and structured workflows.

Structured output

Returns validated JSON that conforms to a schema you define.

Use Claude Sonnet 4.6 through the API

The model id is anthropic/claude-sonnet-4.6. Requests bill your GenMagic balance at the price above, and each response reports what it cost.

curl
curl https://genmagic.co/api/v1/chat/completions \
  -H "Authorization: Bearer $GENMAGIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4.6",
    "messages": [{ "role": "user", "content": "Explain vector databases in two sentences." }]
  }'
Python (openai SDK)
from openai import OpenAI

client = OpenAI(base_url="https://genmagic.co/api/v1", api_key="YOUR_GENMAGIC_API_KEY")

resp = client.chat.completions.create(
    model="anthropic/claude-sonnet-4.6",
    messages=[{"role": "user", "content": "Explain vector databases in two sentences."}],
)
print(resp.choices[0].message.content)

From an AI agent, call generate_text with "model": "anthropic/claude-sonnet-4.6" on the GenMagic MCP server. Keys, limits and every endpoint are in the API documentation.

Use Claude Sonnet 4.6 in n8n

  1. In n8n, open the nodes panel, search for GenMagic and install it (a verified community node), then add it to your workflow.
  2. Set Resource to Text and Operation to Generate.
  3. In Model Name or ID, pick Anthropic: Claude Sonnet 4.6, or enter anthropic/claude-sonnet-4.6 as an expression.
  4. Connect your GenMagic API key (get one free). Each run is billed at the price above, and the node returns what it cost.

Ready-to-import workflows that already use the node are on GenMagic for n8n.

Similar-priced text models from other providers

Other text models GenMagic runs at a comparable price, on the same balance and API key.

ModelProviderPriceContext
Anthropic: Claude Sonnet 4.6 (this model)Anthropic$4.50 in / $22.50 out per 1M tokens1M
Fireworks: Ember-1Fireworks$4.50 in / $22.50 out per 1M tokens1M
Perplexity: Sonar Pro SearchPerplexity$4.50 in / $22.50 out per 1M tokens200K
OpenAI: GPT-5.4OpenAI$3.75 in / $22.50 out per 1M tokens1.1M
MoonshotAI: Kimi K3Moonshot AI$0.29 in / $24.00 out per 1M tokens1M
Qwen: Qwen3.8 Max PrimeQwen$6.00 in / $18.00 out per 1M tokens1M

Compare Claude Sonnet 4.6

More from Anthropic

All 20 Anthropic models

Price and listing history

Every change GenMagic has recorded for Claude Sonnet 4.6 since it began tracking the model on Oct 29, 2026. Prices are GenMagic's, the same the studio and the API charge.

DateChangeBeforeAfter
Nov 1, 2026Price up 36%$3.30 in / $16.50 out per 1M tokens$4.50 in / $22.50 out per 1M tokens

Where these figures come from

  • Price: GenMagic's own price, what the studio and the API charge, recomputed from the provider's price list every few minutes and recorded daily. How pricing works.
  • Specs and description: as Anthropic publishes them, checked daily.
  • Benchmarks: 50 scores from Artificial Analysis and OpenRouter, Epoch AI, Design Arena, LMArena, re-read daily. Each score above links to its source.
  • Changes: the data on this page last changed on Nov 12, 2026, tracked since Oct 29, 2026. Every model's new listings, price changes and retirements are in the model changes log, and how every figure on GenMagic is sourced is on our sources page.

Generate with Claude Sonnet 4.6 today

One GenMagic plan unlocks Claude Sonnet 4.6 and every other model across text, image, audio, and video.