← All models
Claude Sonnet 5.5 · Anthropic

What does Claude Sonnet 5.5 cost to run in a coding agent?

Claude Sonnet 5.5 costs about $0.053 per average coding-agent request on our measured traffic, at list prices of $2 per million input and $10 per million output tokens. It is the everyday coding default, second only to Opus 5.5 on the tbench.ai Terminal-Bench 4.0 leaderboard at 61.8%.

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. Benchmark: tbench.ai Terminal-Bench 4.0 leaderboard. How we compute this

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 5.5 costs per coding-agent request

Cost at list priceSonnet 5.5
Prompt under 100K tokens50% of requests, 87% of input cached$0.026
Prompt of 100K to 272K39% of requests, 88% of input cached$0.064
Prompt over 272K tokens11% of requests, 86% of input cached$0.14
Average request$0.053
100 requests$5.33
Median session16 requests; a session ends after 10 idle minutes$0.74
A month of regular usemedian of 20 users active on 5+ days$77.42

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 5.5 benchmarks, speed and latency

Artificial AnalysisValueRank
Intelligence Index10 evaluations, 0 to 100562 of 48
Terminal-Bench 4.0agentic coding in a terminal63.6%1 of 39
Output speedmedian136 tokens/s9 of 44
Time to first answer tokenincludes thinking time7.3 min43 of 44

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: Claude Sonnet 5.5 (Max, Default Fallback), 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.

What to watch for

These figures assume 87% of input is read from cache at $0.10 per million, as in our traffic. A request that misses the cache (a new task, an edited system prompt, or a long pause) pays $2 per million on every input token, twenty times more, and writing the cache costs 1.25x input.

Where Sonnet 5.5 sits on the Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index bar chart with Claude Sonnet 5.5 (Max, Default Fallback) highlighted, from artificialanalysis.ai, October 13, 2026
Artificial Analysis Intelligence Index v4.3.2, Claude Sonnet 5.5 (Max, Default Fallback) highlighted, downloaded October 13, 2026. Source: Artificial Analysis (artificialanalysis.ai)

Leaderboards

About Claude Sonnet 5.5

Claude Sonnet 5.5 is the mid-tier Claude, released September 28, 2026 as a faster, lower-cost complement to Opus 5.5. It scores close to the flagship: 56 on the Artificial Analysis Intelligence Index against Opus 5.5's 58, and 63.6% in Artificial Analysis's Terminal-Bench 4.0 run, the highest of the models on this hub. On the tbench.ai leaderboard it is #2 at 61.8%, and it is #3 on LMArena's WebDev board. Anthropic reports 70.6% on Terminal-Bench 4.0 against 10.3% for Sonnet 5, and says it runs over 30% faster and costs up to 30% less than its predecessor. It has a 1M-token context window and 128K output; effort defaults to high on the API and medium in Claude Code.

Sources: Anthropic announcement · Artificial Analysis · Terminal-Bench 4.0 · SWE-Bench Pro V2

Agents that support Sonnet 5.5

The everyday default for coding agents, escalating to Opus 5.5 for the hardest tasks.

Not sure which Claude to run? Best Claude model in 2026: Opus vs Sonnet vs Haiku →

Setting it up? Claude Sonnet 5.5: model ID, providers and agent config →

Claude Sonnet 5.5 FAQ

How much does Claude Sonnet 5.5 cost per coding-agent request?
$0.053 on average at list price, $5.33 per 100 requests, and $0.74 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 5.5 charge more for long prompts?
No. Claude Sonnet 5.5 bills the same rate per token up to its 1M-token context window.
How fast is Claude Sonnet 5.5?
Artificial Analysis measures Claude Sonnet 5.5 (Max, Default Fallback) at 136 output tokens per second, with 438 seconds to the first answer token, thinking time included, on Anthropic's API. Source: Artificial Analysis (artificialanalysis.ai).
Is Claude Sonnet 5.5 good for AI agents?
The everyday default for coding agents, escalating to Opus 5.5 for the hardest tasks. On our scoring, which is calibrated to public benchmarks, it rates 9.7/10 for agentic ability and 9.8/10 for output quality. #2 on the tbench.ai Terminal-Bench 4.0 leaderboard (61.8%), behind Opus 5.5.
What is Claude Sonnet 5.5's context window?
Claude Sonnet 5.5 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 5.5?
No. Claude Sonnet 5.5 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 5.5?
The main trade-offs: Artificial Analysis flags it as very verbose, which adds output tokens; A cache miss bills input at $2 per million, 20 times the cache-read rate; Released September 2026, so its long-run track record is still short. It's strongest for the everyday default for coding agents, escalating to Opus 5.5 for the hardest tasks.

Sonnet 5.5 compared

All 51 Sonnet 5.5 comparisons

The agent matters as much as the model. Which agent gets the most out of Sonnet 5.5? →

Every model on this page runs on Standard Compute

Standard Compute

Current frontier models Claude Fable 5.1 · GPT-6 Astra

More intelligence
per dollar.

Each step goes to the cheapest model that can do it, on providers we vet for price, uptime and speed, with automatic fallback when one fails.

Compliance
Opt-in rules keep a company, team or key on European or US providers
Privacy
We don’t train on your prompts or store them

Fixed monthly plans from $19 · cancel anytime

7-day fair refund Free trial, no card Billing by Stripe4,200+ agent users