Claude Sonnet 4.6

Anthropic's most capable Sonnet-class model of early 2026, now superseded by Sonnet 5.

Context window

Input / 1M tokens

$3.00

Output / 1M tokens

$15.00

Provider

Anthropic

Standard pricing $3/$15 per 1M input/output tokens (same as Sonnet 4.5). Batch API is 50% off at $1.50/$7.50 per 1M. Now listed as a legacy model - consider migrating to Sonnet 5 at the same price for higher capability. · Data verified 2026-07-02

Claude Sonnet 4.6 (February 2026) delivered frontier-class performance across coding, agents, and professional work with a 1M-token context window in beta. It scored 79.6% on SWE-bench Verified and introduced strong agentic and computer-use capabilities. It has since been reclassified as a legacy model, with Sonnet 5 as the same-price successor.

Capability index

Relative estimates (0-100) to place this model against its peers, grounded in published benchmarks.

Coding

Reasoning

Math

Multimodal

Long context

Speed

Cost efficiency

How to access it

Available via the Claude API, Amazon Bedrock, Google Cloud, and Microsoft Foundry. Now categorized as a legacy model since the Sonnet 5 release; still fully usable but Sonnet 5 is the recommended drop-in upgrade.

Get access →Documentation →

Strengths

✓Strong agentic coding for its tier: 79.6% SWE-bench Verified
✓1M-token context window for large inputs
✓Solid computer-use and OS-level task performance (OSWorld ~72.5-78.5%)
✓Fast latency with good cost-efficiency at $3/$15
✓Well-documented, stable, and broadly available across clouds

Best for developers who...

Established mid-tier production workloads pinned to a stable modelLarge-context document and codebase analysisAgentic coding at a moderate price pointComputer-use and tool-driven automationGeneral assistant and knowledge-work tasks

When to choose it (and when not to)

Reach for Claude Sonnet 4.6 when...

→You have an existing integration pinned to Sonnet 4.6 and want stability
→You need a proven mid-tier model with 1M context at $3/$15
→You want predictable behavior without the new-tokenizer/thinking changes in Sonnet 5
→You are cost-sensitive and don't need Sonnet 5's incremental gains

Look elsewhere if...

✕You want the best capability per dollar today - Sonnet 5 upgrades it at the same price
✕You need the strongest agentic/coding performance (Opus 4.8 or Fable 5)
✕You want the latest features and long-term support (it is now legacy)

How to use it

›Manual extended thinking is deprecated on Sonnet 4.6; prefer adaptive thinking patterns
›Use the 1M context deliberately - place key instructions near the top and structure long inputs
›Use batch processing for 50% cost savings on non-interactive workloads
›For agentic tasks, give explicit tool-use guidance and success criteria

Quickstart

Python

import anthropic

client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=4096,
    messages=[
        {"role": "user", "content": "Summarize this pull request and flag risks."}
    ],
)
print(response.content[0].text)

Sonnet 4.6 is now a legacy model; for new projects migrate to claude-sonnet-5 (drop-in, same price).

API model id: claude-sonnet-4-6