All plans/Calculator/Claude Opus 5.5

Claude Opus 5.5 Calculator — requests per $1

Every monthly plan that includes Claude Opus 5.5, converted to requests per $1 at the model's typical request shape. Same engine as the main calculator — proxy estimates carry a ~ marker; coarse estimates carry ≈.

Claude Opus 5.5 (API claude-opus-5-5) is Anthropic's newest Opus-line flagship for long-running agentic coding and knowledge work — released 2026-09-22 at $4/$20 per 1M tokens, roughly 40% cheaper to run than Claude Opus 5 and at Claude Fable 5.1's performance level on most work.

At Claude Opus 5.5’s typical shape

122req / $1

on Cursor Ultra · 17 plans priced · exact

Agent Arena benchmark

n/anot on the current leaderboard

Agent Arena leaderboard · fetched 2026-09-21

Per-request shape · tokens

Throttling, off-peak, rollover, and cache writes are not modeled. Where a provider publishes no cached-read price, cached tokens bill at the input rate — those req / $1 figures are floors.

Price–$
17 / 17 plans
Plan detailsProvider and subscription tier. Sorts by provider name.Standard monthly price in USD, before first-month promotions.Estimated cost per request for the selected model and token shape.Requests fitting in the rolling 5-hour budget. '—' means no published 5-hour limit.Requests fitting in the rolling 7-day budget. '—' means no published weekly limit.Requests fitting in 30 days. Weekly budgets are extrapolated; unused credits do not roll over.Requests per $1 of plan price over 30 days. Higher is better.Requests per $1 available in one 5-hour burst. Uncapped plans match Req / $1.SubscribeOpen provider pricing. Referral links may support TokenPlans at no extra cost.
LLM Gateway DevPassPro$237/mo usage at provider rates · weekly frontier fair-use 15%$79.00$0.0164——14,451~183~183Subscribe ↗
LLM Gateway DevPassMax$537/mo usage at provider rates · weekly frontier fair-use 18%$179.00$0.0164——32,743~183~183Subscribe ↗
LLM Gateway DevPassLite$87/mo usage at provider rates · weekly frontier fair-use 12%$29.00$0.0164——5,304~183~183Subscribe ↗
CursorUltra$400/mo API pool + Cursor Models pool$200.00$0.0164——24,390122122Subscribe ↗
CursorPro+$70/mo API pool + Cursor Models pool$60.00$0.0164——4,2687171Subscribe ↗
Nous PortalSuper$110 credits/mo · $50 rollover$100.00$0.0149——6,707~67~67Subscribe ↗
Nous PortalUltra$220 credits/mo · $100 rollover$200.00$0.0149——13,414~67~67Subscribe ↗
Nous PortalPlus$22 credits/mo · $10 rollover$20.00$0.0149——1,341~67~67Subscribe ↗
ClaudeMax 20x20× Pro$200.00$0.0164——12,195≈61≈61Subscribe ↗
CommandCodeMax 20×$300 credits · ~370K reqs/mo · $90/5h · $180/7d$200.00$0.01643,6587,31712,195~61~18Subscribe ↗
ClaudeMax 5x5× Pro$100.00$0.0164——6,097≈61≈61Subscribe ↗
CommandCodeMax 10×$150 credits · ~230K reqs/mo · $45/5h · $90/7d$100.00$0.01641,8293,6586,097~61~18Subscribe ↗
ClaudePro≥5× Free · 5h rolling window + weekly cap$20.00$0.0164——1,219≈61≈61Subscribe ↗
CursorPro$20/mo API pool + Cursor Models pool$20.00$0.0164——1,2196161Subscribe ↗
CommandCodeProviderPAYG · top-ups roll over, never expire · zero markup$15.00$0.0164——914~61~61Subscribe ↗
OzorePro$70 in credits/mo · + Smart Compression, Analytics Pro, Privacy Pack, 10 extra API keys, Custom Router, Fusion$35.00$0.1317——531~≥15~≥15Subscribe ↗
OzoreBasic$20 in credits/mo · spend on any model at discounted rates · cancel anytime$10.00$0.1317——151~≥15~≥15Subscribe ↗

Some Subscribe buttons carry referral or affiliate codes — using them may give you a signup bonus or support this project at no extra cost to you.

Markers: ~ proxy estimate, ≈ coarse estimate, and ≥ cache floor. A floor means the plan publishes no cached-read rate, so cached tokens bill at the input rate and the real figure is this or higher. Borrowed cap means the budget is a published API cap at list price, so Req / $1 is a value comparison rather than a measured allowance.

Best-priced plans

Best-priced plans for Claude Opus 5.5

The top 5 plans by computed Req/$1 that include Claude Opus 5.5, plus the lowest-cost plan. Computed at build from the same cost rules the calculator renders · ~ = proxy estimate

“n/a” = the provider publishes no price structure for Claude Opus 5.5 — the calculator renders the same honest n/a. ◆ best value = highest computed Req/$1.

What real work costs

What Claude Opus 5.5 costs on real coding tasks

Illustrative cost of common coding tasks on the best-priced plans above, scaled from each plan's live per-request price to a task-typical token volume. Task token assumptions are shared ~proxy estimates — real tasks vary, and they are never per-provider shapes.

TaskLLM Gateway DevPass ProLLM Gateway DevPass MaxLLM Gateway DevPass LiteCursor UltraCursor Pro+Ozore Basic
Quick lookup / one-liner8,000 in · 1,000 out~1¢~1¢~1¢~1¢~1¢~2¢
Review a 500-line PR60,000 in · 4,000 out~2¢~2¢~2¢~2¢~2¢~17¢
Fix a bug (agent loop)180,000 in · 12,000 out~6¢~6¢~6¢~6¢~6¢~51¢
Refactor a module320,000 in · 20,000 out~11¢~11¢~11¢~11¢~11¢~90¢
Full-repo agent run900,000 in · 45,000 out~31¢~31¢~31¢~31¢~31¢~$2.49

Per-task cost = the plan's effective 50,010-token request price scaled to each task's token volume at the same shape mix. ~ = proxy estimate — shared task-token assumptions, not a quote. “n/a” = Claude Opus 5.5 unpriced on that plan.

Common questions

How many requests per $1 do I get on Claude Opus 5.5?

The best plan pricing Claude Opus 5.5 delivers 122 Req/$1 at the model's typical request shape — on Cursor Ultra. Figures are exact confidence: they are computed from published rates and usage caps, proxy estimates are marked with a ~, and borrowed-cap plans use a published API cap at list price, so their Req/$1 is a value comparison rather than a measured allowance.

What's the cheapest plan with Claude Opus 5.5?

Ozore Basic at $10/mo. The cheapest plan is not always the best value — check Req/$1 above.

Which plans include Claude Opus 5.5?

17 tracked plans across 6 providers price it: Claude (Pro, Max 5x and Max 20x), CommandCode (Max 10×, Max 20× and Provider), Cursor (Pro, Pro+ and Ultra), LLM Gateway DevPass (Lite, Pro and Max), Nous Portal (Plus, Super and Ultra) and Ozore (Basic and Pro). The calculator compares every tracked monthly plan that prices it.

Where does Claude Opus 5.5 rank on the Agent Arena leaderboard?

No verified row yet: Claude Opus 5.5 is not on the Agent Arena agent leaderboard as of 2026-09-21. Ranks are scraped from https://arena.ai/leaderboard/agent, never typed by hand, so this page shows n/a instead of a guessed position.

What is Claude Opus 5.5?

Claude Opus 5.5 (API claude-opus-5-5) is Anthropic's Opus-line text generation model for long-running agentic coding and knowledge work (family: claude, kind: text), released 2026-09-22 as the successor to Claude Opus 5. Anthropic's own docs name it the default starting point for most workloads.

How much does Claude Opus 5.5 cost?

Claude Opus 5.5 lists at $4 per 1M input tokens and $20 per 1M output tokens on Anthropic’s published rate card — about 40% cheaper to run than Claude Opus 5 at $5/$25. Individual providers bill their own resell rate, so the calculator compares each plan at the rate that provider publishes.

How does Claude Opus 5.5 compare to Claude Fable 5.1?

Anthropic positions Claude Opus 5.5 as performing at Claude Fable 5.1’s level on most work while costing less, with Fable 5.1 the pick for demanding reasoning and long-horizon agentic work where Opus 5.5 at higher effort still falls short.

Is Claude Opus 5.5 open-weight?

No — Claude Opus 5.5 is a proprietary Anthropic model, reachable only through provider endpoints, so you cannot self-host it or access the weights. Open-weight agent models we track include GLM-5.3 and Hy4 preview.

Can I use Claude Opus 5.5 with any agent (BYOK)?

Yes — several tracked plans expose Claude Opus 5.5 through OpenAI- or Anthropic-compatible endpoints with no CLI lock, so it works with Claude Code, Cursor, OpenCode or any agent that supports custom model endpoints.

What is Claude Opus 5.5 best used for?

Long-running agentic coding, multi-step tool use and knowledge work — a frontier-quality pick rather than a budget-throughput model like DeepSeek V4 Flash.

Newsletter

The weekly brief — plan churn, dated.

A plain weekly digest of every tracked price move, ceiling change and model-list update — pulled straight from the dated changelog ledger, with a one-line “worth switching?” note on each. Free. No spam, unsubscribe anytime.

Free · weekly · unsubscribe anytime