Claude Opus 5

AnthropicLegacy

Input price: $5.00; Per 1 million tokens (USD)
Output price: $25.00; Per 1 million tokens (USD)
Effort levels: 5total; Default: High
Benchmark results: 35total; Benchmark types: 11

Model information

API model ID: claude-opus-5
release date: Unknown
effort: Low / Med / High (default) / Xhigh / Max
Effort source: Based on Anthropic effort documentation (platform.claude.com/docs/en/build-with-claude/effort).
Claude Code: available
Codex: unavailable
Availability notes: Opus 5 is listed in the Claude Code effort table (model ID specified). Codex's official model list (learn.chatgpt.com/docs/models) contains only OpenAI models, so codex is false (connections via a custom provider are not counted as official options).
Availability source: https://code.claude.com/docs/en/model-config

Price (USD per 1 million tokens)

Prices do not vary by effort; token consumption does.

input	$5.00
output	$25.00
cache read	$0.50
cache write	$6.25

cacheWritePerMTok is for a 5-minute cache write. 1h write $10.

Claude Opus 5 | $5 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | $25 / MTok

Source: https://platform.claude.com/docs/en/about-claude/pricing

Benchmark results

Benchmark	effort	Score	Source cost (metric)	measured/reported by	source	Conditions and extraction method
Terminal-Bench 4.0Low	Low	28.5%	$4.25Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Terminal-Bench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Terminal-Bench 4.0 — Accuracy vs Cost: "Opus 5 · Low: 28.5% $4.25"
Terminal-Bench 4.0Med	Med	41.2%	$7.00Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Terminal-Bench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Terminal-Bench 4.0 — Accuracy vs Cost: "Opus 5 · Med: 41.2% $7"
Terminal-Bench 4.0High (default)	High	47.0%	$10.64Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Terminal-Bench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Terminal-Bench 4.0 — Accuracy vs Cost: "Opus 5 · High: 47.0% $10.64"
Terminal-Bench 4.0Xhigh	Xhigh	50.6%	$13.48Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Terminal-Bench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Terminal-Bench 4.0 — Accuracy vs Cost: "Opus 5 · Xhigh: 50.6% $13.48"
Terminal-Bench 4.0Max	Max	52.3%	$15.83Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Terminal-Bench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Terminal-Bench 4.0 — Accuracy vs Cost: "Opus 5 · Max: 52.3% $15.83"
Terminal-Bench-Science 0.1not stated	not stated	29.0%	—	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. table note: Unless otherwise noted, all Claude Opus 5.5 results use adaptive thinking at max effort. production safeguards enabled. SE ±3.5–5pt. The GPT-6 Astra figure is a reported value from OpenAI.transcribed from table Source excerpt 29.0%Location Table, Terminal-Bench-Science 0.1 row: 29.0
FrontierCode v1.1(main set)Low	Low	42.0%	$2.64Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode v1.1, main set — Accuracy vs Cost: "Opus 5 · Low: 42.0% $2.64"
FrontierCode v1.1(main set)Med	Med	53.4%	$4.61Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode v1.1, main set — Accuracy vs Cost: "Opus 5 · Med: 53.4% $4.61"
FrontierCode v1.1(main set)High (default)	High	48.0%	$7.62Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode v1.1, main set — Accuracy vs Cost: "Opus 5 · High: 48.0% $7.62"
FrontierCode v1.1(main set)Xhigh	Xhigh	43.6%	$8.99Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode v1.1, main set — Accuracy vs Cost: "Opus 5 · Xhigh: 43.6% $8.99"
FrontierCode v1.1(main set)Max	Max	48.0%	$12.28Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode v1.1, main set — Accuracy vs Cost: "Opus 5 · Max: 48.0% $12.28"
CursorBench 4.0Low	Low	40.7%	$4.87Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "CursorBench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt CursorBench 4.0 — Accuracy vs Cost: "Opus 5 · Low: 40.7% $4.87"
CursorBench 4.0Med	Med	43.3%	$6.94Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "CursorBench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt CursorBench 4.0 — Accuracy vs Cost: "Opus 5 · Med: 43.3% $6.94"
CursorBench 4.0High (default)	High	44.7%	$9.00Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "CursorBench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt CursorBench 4.0 — Accuracy vs Cost: "Opus 5 · High: 44.7% $9"
CursorBench 4.0Xhigh	Xhigh	46.1%	$11.43Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "CursorBench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt CursorBench 4.0 — Accuracy vs Cost: "Opus 5 · Xhigh: 46.1% $11.43"
CursorBench 4.0Max	Max	46.6%	$11.95Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "CursorBench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt CursorBench 4.0 — Accuracy vs Cost: "Opus 5 · Max: 46.6% $11.95"
GDPval-AA v2.1Low	Low	1,294	$0.58Estimated cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "GDPval-AA v2.1 / Elo vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt GDPval-AA v2.1 — Elo vs Cost: "Opus 5 · Low: 1294 $0.58"
GDPval-AA v2.1Med	Med	1,476	$1.36Estimated cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "GDPval-AA v2.1 / Elo vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt GDPval-AA v2.1 — Elo vs Cost: "Opus 5 · Med: 1476 $1.36"
GDPval-AA v2.1High (default)	High	1,581	$3.03Estimated cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "GDPval-AA v2.1 / Elo vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt GDPval-AA v2.1 — Elo vs Cost: "Opus 5 · High: 1581 $3.03"
GDPval-AA v2.1Xhigh	Xhigh	1,676	$4.96Estimated cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "GDPval-AA v2.1 / Elo vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt GDPval-AA v2.1 — Elo vs Cost: "Opus 5 · Xhigh: 1676 $4.96"
GDPval-AA v2.1Max	Max	1,708	$6.76Estimated cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "GDPval-AA v2.1 / Elo vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt GDPval-AA v2.1 — Elo vs Cost: "Opus 5 · Max: 1708 $6.76"
AutomationBenchLow	Low	20.4%	$0.75Cost per task	Zapier	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "AutomationBench / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; measured by: Zapier (Opus 5.5 is from a Zapier early access evaluation; the others are from the Zapier public leaderboard)transcribed from text Source excerpt AutomationBench — Accuracy vs Cost: "Opus 5 · Low: 20.4% $0.75"
AutomationBenchMed	Med	23.9%	$0.89Cost per task	Zapier	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "AutomationBench / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; measured by: Zapier (Opus 5.5 is from a Zapier early access evaluation; the others are from the Zapier public leaderboard)transcribed from text Source excerpt AutomationBench — Accuracy vs Cost: "Opus 5 · Med: 23.9% $0.89"
AutomationBenchHigh (default)	High	20.6%	$1.03Cost per task	Zapier	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "AutomationBench / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; measured by: Zapier (Opus 5.5 is from a Zapier early access evaluation; the others are from the Zapier public leaderboard)transcribed from text Source excerpt AutomationBench — Accuracy vs Cost: "Opus 5 · High: 20.6% $1.03"
AutomationBenchXhigh	Xhigh	25.3%	$1.15Cost per task	Zapier	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "AutomationBench / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; measured by: Zapier (Opus 5.5 is from a Zapier early access evaluation; the others are from the Zapier public leaderboard)transcribed from text Source excerpt AutomationBench — Accuracy vs Cost: "Opus 5 · Xhigh: 25.3% $1.15"
AutomationBenchMax	Max	26.9%	$1.27Cost per task	Zapier	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "AutomationBench / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; measured by: Zapier (Opus 5.5 is from a Zapier early access evaluation; the others are from the Zapier public leaderboard)transcribed from text Source excerpt AutomationBench — Accuracy vs Cost: "Opus 5 · Max: 26.9% $1.27"
Humanity's Last Exam (with tools)not stated	not stated	63.6%	—	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. table note: Unless otherwise noted, all Claude Opus 5.5 results use adaptive thinking at max effort. production safeguards enabled.transcribed from table Source excerpt 63.6%Location Table, Humanity's Last Exam (with tools) row: 63.6
OSWorld 2.1(partial)not stated	not stated	74.0%	—	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. table note: Unless otherwise noted, all Claude Opus 5.5 results use adaptive thinking at max effort. production safeguards enabled.transcribed from table Source excerpt 74.0%Location Table, OSWorld 2.1 (partial) row: 74.0
Chartography (with tools)not stated	not stated	83.4%	—	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. table note: Unless otherwise noted, all Claude Opus 5.5 results use adaptive thinking at max effort. production safeguards enabled.transcribed from table Source excerpt 83.4%Location Table, Chartography (with tools) row: 83.4
WANDRLow	Low	50.5%	$10.65Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR — Accuracy vs Cost: "Opus 5 · Low: 50.5% $10.65"
WANDRMed	Med	58.1%	$23.97Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR — Accuracy vs Cost: "Opus 5 · Med: 58.1% $23.97"
WANDRHigh (default)	High	64.6%	$43.49Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR — Accuracy vs Cost: "Opus 5 · High: 64.6% $43.49"
WANDRXhigh	Xhigh	67.0%	$53.84Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR — Accuracy vs Cost: "Opus 5 · Xhigh: 67.0% $53.84"
WANDRMax	Max	67.2%	$61.62Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR — Accuracy vs Cost: "Opus 5 · Max: 67.2% $61.62"
τ²-bench banking_knowledge (v1.0.1)Max	Max	48.7%	—	Sierra	τ²-bench leaderboard submission claude-opus-5_sierra_2026-08-04 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13	τ²-bench leaderboard submission claude-opus-5_sierra_2026-08-04 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "Anthropic": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "max". User simulator gpt-5.2 (reasoning_effort low). Search configuration retrieval_config "alltools". Evaluation date 2026-08-03. Notes summary: 4 trial runs; seed 300.transcribed from table Source excerpt banking_knowledge.pass_1=48.71134020618557Location In submissions/claude-opus-5_sierra_2026-08-04/submission.json: results.banking_knowledge.pass_1 (line 17 of file). model_name "Claude Opus 5". methodology.notes (line 36)

Claude Opus 5

Model information

Price (USD per 1 million tokens)

Benchmark results

Related rankings

References