AClaude Opus 4.6API

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.

1MContext window · tokens

$5Input price · per M tokens

$25Output price · per M tokens

AnthropicProvider

Prices update automatically — checked daily against provider list prices.

$10 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
cheaper than 14% of the 192 commercial models tracked here
19 of 28 Anthropic models tracked here, from cheapest

See open-source alternatives → Compare all model prices

Benchmarks & performance

Independent benchmark scores for Claude Opus 4.6, measured by Artificial Analysis. Higher is better. Measurement mode: Non-reasoning, High Effort.

Intelligence index38.8

GPQA84%

Humanity's Last Exam19.1%

Long Context Reasoning62.3%

SciCode45.7%

IFBench44.6%

τ²-Bench84.8%

Terminal-Bench Hard48.5%

💰 Blended price$10 / 1M tokens

📈 Value3.9 intelligence points per $

vs. models measured heretop 29%

Scores higher than 71% of the 273 models measured by Artificial Analysis and tracked here.
Models at this level cost $1.13 per 1M tokens (median of 25) — this one costs $10.
Cheaper and better on this index: Claude Opus 5 (batch) · GPT-5.6 Sol · Grok 4.6 and 61 more

Benchmark data by Artificial Analysis

About this model

Claude Opus 4.6 is a commercial AI model by Anthropic. The specifications below are tracked automatically: pricing is refreshed daily from public list prices, so the numbers on this page reflect the current cost of using the model through its API.

Frequently asked questions

What is Claude Opus 4.6?

Claude Opus 4.6 is an AI language model from Anthropic. It is a proprietary model, available through an API. It scores 38.8 on the Artificial Analysis intelligence index.

Is Claude Opus 4.6 free?

Claude Opus 4.6 is not free: it costs $5 per million input tokens and $25 per million output tokens. Open-weight alternatives can be self-hosted at no per-token cost.

What is Claude Opus 4.6 good at?

Independent benchmarks from Artificial Analysis give it GPQA 84%, Humanity's Last Exam 19.1%, Long Context Reasoning 62.3%, SciCode 45.7%, IFBench 44.6%, τ²-Bench 84.8%, Terminal-Bench Hard 48.5%.