Claude Sonnet 4.6 · Anthropic

What does Claude Sonnet 4.6 cost to run in a coding agent?

Claude Sonnet 4.6 costs about $0.097 per average coding-agent request on our measured traffic, at list prices of $3 per million input and $15 per million output tokens. It scores 30 on the Artificial Analysis Intelligence Index, 28th of the 48 models we track. Source: Artificial Analysis (artificialanalysis.ai)

List prices: Anthropic pricing, checked 2026-10-13. Request costs: Standard Compute gateway data, 79,301 coding-agent requests from 75 users, Sep 13 to Oct 12, 2026. How we compute this

A newer version is out. Claude Sonnet 5.5 →

Run Claude Sonnet 5.5 in your agent

Or let the router send each step to the cheapest model that can do it, on providers we vet for price, uptime and speed. Plans from $19 a month.

See plans

What Sonnet 4.6 costs per coding-agent request

Cost at list price	Sonnet 4.6
Prompt under 100K tokens50% of requests, 87% of input cached	$0.047
Prompt of 100K to 272K39% of requests, 88% of input cached	$0.12
Prompt over 272K tokens11% of requests, 86% of input cached	$0.26
Average request	$0.097
100 requests	$9.74
Median session16 requests; a session ends after 10 idle minutes	$1.35
A month of regular usemedian of 20 users active on 5+ days	$149

Each logged request priced at the vendor’s list rates for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request.

Sonnet 4.6 benchmarks, speed and latency

Artificial Analysis	Value	Rank
Intelligence Index10 evaluations, 0 to 100	30	28 of 48
Terminal-Bench 4.0agentic coding in a terminal	3.0%	26 of 39
Output speedmedian	57 tokens/s	37 of 44
Time to first answer tokenincludes thinking time	101 s	28 of 44

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: Claude Sonnet 4.6 (Max), speed on Anthropic. Fetched October 13, 2026. Rank is among the models on this site, older versions included. Artificial Analysis runs Terminal-Bench 4.0 in its own setup, so its scores differ from the tbench.ai leaderboard.

About Claude Sonnet 4.6

Claude Sonnet 4.6 was the mid-tier Claude from February 17, 2026 and a common default in coding agents until Sonnet 5.5 replaced it in September. It has a 1M-token context and costs $3/$15 per million tokens. Current models have moved well past it: it scores 30 on the Artificial Analysis Intelligence Index and 3.0% in Artificial Analysis's Terminal-Bench 4.0 run, against 56 and 63.6% for Sonnet 5.5, and runs at about 57 output tokens per second. Sonnet 5.5 is also cheaper, at $0.053 per request against $0.097 in our measurements.

Sources: Artificial Analysis

Claude Sonnet 4.6 FAQ

How much does Claude Sonnet 4.6 cost per coding-agent request?

$0.097 on average at list price, $9.74 per 100 requests, and $1.35 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at Anthropic's list rates; the median request sent 99,534 input tokens, 87% of input was read from cache, and requests returned 698 output tokens on average.

Does Claude Sonnet 4.6 charge more for long prompts?

No. Claude Sonnet 4.6 bills the same rate per token up to its 1M-token context window.

How fast is Claude Sonnet 4.6?

Artificial Analysis measures Claude Sonnet 4.6 (Max) at 57 output tokens per second, with 101 seconds to the first answer token, thinking time included, on Anthropic's API. Source: Artificial Analysis (artificialanalysis.ai).

Is Claude Sonnet 4.6 good for AI agents?

Existing Sonnet 4.6 setups until they move to Sonnet 5.5. On our scoring, which is calibrated to public benchmarks, it rates 5.1/10 for agentic ability and 6.4/10 for output quality. 1M-token context.

What is Claude Sonnet 4.6's context window?

Claude Sonnet 4.6 has a 1M-token context window, large enough to hold sizeable codebases or document sets in a single run. Anthropic is the maker.

Can I self-host Claude Sonnet 4.6?

No. Claude Sonnet 4.6 is a proprietary, hosted-only model from Anthropic. You access it through an API, such as OpenRouter, rather than running the weights yourself.

What are the downsides of Claude Sonnet 4.6?

The main trade-offs: Superseded by Claude Sonnet 5.5, which costs less ($2/$10 vs $3/$15) and scores far higher; About 57 output tokens/s at max effort, per Artificial Analysis. It's strongest for existing Sonnet 4.6 setups until they move to Sonnet 5.5.