Novità Registrati gratis, 10 chiamate le offriamo noi. Fino a $1, senza carta.

Claude Opus 5 vs Claude Sonnet 5

vs

Quale scegliere e quando

La classica alternativa verso l'alto o verso il basso, ora con un divario di prezzo di 2.5× ($5/$25 contro $2/$10) e contesti identici da 1M. Sonnet 5 è stato posizionato come un aggiornamento di capacità drop-in da 4.6 - per la maggior parte del traffico di prodotto è sufficiente; riserva Opus 5 per la coda agentica a lungo orizzonte in cui la sua profondità è ciò che conta.

Benchmark

In testaSopra la mediaNessuno miglioreClaude Opus 51738 / 469 / 46Claude Sonnet 504 / 221 / 22

17 misurati su entrambi.

Claude Opus 5 Claude Sonnet 5 altri modelli misurati media dei modelli confrontati ★ nessun altro modello ha fatto meglio
DeepSWE 1.1
68.8%
53.8%
BioMysteryBench hard
49.4%
34.1%
OSWorld 2.0 Partial score, batch tool enabled
nessun altro modello ha fatto meglio 75.4%
42.6%
ExploitBench (Cap%)
70%
N/A
HealthBench Professional
59.8%
N/A
Finance Agent v2
58.6%
53.9%
Legal Agent Benchmark
6.7%
5%
HLE-Verified
54.4%
31%
AutomationBench
26.9%
10.7%
LVBench
75.4%
68.5%

Dati pubblicati dai provider: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai

Prezzi

Claude Opus 5 Claude Sonnet 5 Δ
Input / 1M token $5 $2 2.5×
Output / 1M token $25 $10 2.5×
Lettura cache / 1M token $0.5 $0.2 2.5×
Scrittura in cache 1.25x (5m) / 2x (1h) 1.25x (5m) / 2x (1h) -

Tariffe lette dal catalogo live al momento della build; il listino aggiornato è sulla pagina di ciascun modello.

Dove si collocano: prezzo di input per 1M di token tra tutti i modelli di chat con questa unità di fatturazione (76, scala logaritmica)

Funzionalità

Claude Opus 5 Claude Sonnet 5
Tool use sì sì
Controllo del ragionamento configurabile configurabile
Output strutturato sì sì
Prompt caching esplicito (contrassegni tu il prefisso) esplicito (contrassegni tu il prefisso)
Durata della cache 5m default, 1h option 5m default, 1h option
Prefisso minimo in cache 1024 token 1024 token

Specifiche

Claude Opus 5 Claude Sonnet 5
Modalità di input testo immagine testo immagine
Modalità di output testo testo
Rilascio 2026-07-24 2026-06-30
Knowledge cutoff 2026-05 2026-01
Finestra di contesto 1M 1M
Output massimo 128K 128K
Parametro di ragionamento
  • thinking.type
  • output_config.effort
  • thinking.type "adaptive"
  • output_config.effort
Valori accettati
thinking.type
  • adaptive
  • disabled
effort
  • low
  • medium
  • high
  • xhigh
  • max
thinking.type
  • adaptive
  • disabled
effort
  • low
  • medium
  • high
  • xhigh
  • max

"enabled" returns 400

Valore di default

thinking on

effort
  • high (Claude API and Claude Code)

thinking on (adaptive)

effort
  • high

Le specifiche sono riprese dalla documentazione di ciascun provider; se un provider non pubblica un dato, la riga viene omessa e non dedotta. Fonti complete: Claude Opus 5 · Claude Sonnet 5

Un solo prompt, entrambi i modelli, misurati attraverso il gateway

PROMPT Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. VERIFICA esattamente 3 frasi

Claude Opus 5 superato · 3 sentences

When reasoning is enabled, the model generates a hidden chain of "thinking" tokens before it writes the visible answer, and those internal tokens are billed at the output rate even though no one ever sees them — commonly 3–10x more tokens than the response itself. Because output tokens are priced several times higher than input tokens, that added volume hits us at our most expensive rate, which is why the bill roughly doubled while our request count stayed flat. The spend is controllable: we can cap the reasoning budget per call, route only genuinely hard requests to reasoning mode and cheaper models for the rest, and track cost per successfully completed task rather than cost per token, since a single correct answer usually beats three cheap retries plus human cleanup.

out 529 tok latenza 9.0 s

Claude Sonnet 5 superato · 3 sentences

Reasoning mode works by having the model generate extended internal "thinking" steps before producing its final answer, and since we're billed on total tokens, that hidden reasoning text adds significantly to what we pay for—even though you never see it in the output. This is different from simply getting longer visible responses; the model is essentially "showing its work" behind the scenes, and complex prompts can trigger thousands of extra reasoning tokens per request. The upside is improved accuracy on complex tasks, but if we want to control costs, we should selectively enable reasoning only for queries that truly need it, rather than applying it universally.

out 194 tok latenza 4.3 s

Rispetto delle istruzioni (esattamente tre frasi: si contano), adattamento al destinatario (registro da CFO) e lo scarto di fatturazione dovuto al ragionamento nascosto, che i contatori di token qui sotto mettono in luce.

PROMPT This function is supposed to return the longest run of consecutive equal items, but callers report it is off by one on single-element inputs and misses runs that end at the last index. Fix it and explain the bug in one paragraph. VERIFICA la correzione supera i test

Claude Opus 5 superato · 8/8 cases

## Fixed version ```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 else: cur = 1 if cur > best: best = cur return best ``` ## The bug The counters were tracking the wrong quantity: `cur` counted *matching adjacent pairs* rather than *elements in the current run*, and both counters started at `0` instead of `1`. Since a run of length *n* contains only *n − 1* adjacent equal pairs, every result came back one too small — `[1, 1]` returned 1, `[3, 3, 3]` returned 2 — and a single-element list returned 0 because the loop body never executed and `best` kept its initial value of `0`. […]

out 1094 tok latenza 16.1 s

Claude Sonnet 5 superato · 8/8 cases

## The Bug The function has two related off-by-one issues rooted in the same cause: `cur` and `best` are initialized to `0` instead of `1`, treating run lengths as the number of *matches* between adjacent elements rather than the number of *elements* in the run. This means a single-element input never enters the loop (since `range(1, 1)` is empty) and returns `0` instead of the correct answer of `1`. It also means that for any input, the run length is undercounted by exactly one — a run of 3 equal elements only produces 2 "match" increments, so `best` ends up as 2 instead of 3. The claim that it "misses runs that end at the last index" is actually a symptom of this same undercount: the logic does update `best` correctly on every iteration (including the last), but because it's counting matches instead of elements, the final reported value is always one less than the true longest run. […]

out 536 tok latenza 7.1 s

Se la correzione è davvero giusta (si può eseguire), quanto è densa la spiegazione e quanti token servono per un compito circoscritto.

PROMPT Extract a JSON object with fields {company, quarter, revenue_usd_m, growth_pct, guidance} from this text. Use null for anything not stated; add no other fields. VERIFICA JSON valido, schema esatto

Claude Opus 5 superato · 5/5 fields, guidance "Withheld pending Q4 close"

```json { "company": "Meridian Robotics", "quarter": "Q3", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "Withheld pending Q4 close" } ``` Notes on judgment calls: - **quarter**: "September quarter" is labeled Q3 because the text refers to an upcoming "Q4 close," implying a calendar-aligned fiscal year. No fiscal year is given. - **revenue_usd_m**: 412 is stated as constant-currency and hedged ("call it"), so it's approximate; the currency is not explicitly stated as USD. - **growth_pct**: "up eleven and change" means slightly more than 11, so 11 is a floor rather than an exact figure.

out 539 tok latenza 7.6 s

Claude Sonnet 5 superato · 5/5 fields, guidance null

```json { "company": "Meridian Robotics", "quarter": "Q3", "revenue_usd_m": 412, "growth_pct": 11.5, "guidance": null } ```

out 348 tok latenza 5.3 s

Aderenza allo schema (nessun campo inventato), tentazione di allucinare (il testo dice espressamente che la guidance non viene comunicata) e differenze tra i percorsi di output strutturato.

PROMPT Write a 120-word product announcement for an API gateway feature that caches prompts across providers. Forbidden words: "seamless", "unlock", "game-changer", "revolutionize", "empower". Exactly one sentence must be a question. VERIFICA 120 parole, 0 parole vietate

Claude Opus 5 superato · 123 words, 0 banned, 1 question

**Cross-Provider Prompt Caching** We're introducing Cross-Provider Prompt Caching in the API Gateway. Repeated system prompts, long documents, and few-shot examples are stored once at the gateway layer and reused across OpenAI, Anthropic, Google, and self-hosted models. Instead of paying full input token costs on every request, your application sends a cache reference, and the gateway rehydrates the context before forwarding it downstream. Why does that matter? Teams running high-volume agents and retrieval pipelines typically see input token spend fall 40 to 70 percent, with median latency dropping by several hundred milliseconds. Caches are scoped per project, encrypted at rest, and invalidated automatically when a prompt template changes. Enable it with a single header, and see the docs for TTL tuning and per-route controls.

out 1593 tok latenza 19.1 s

Claude Sonnet 5 superato · 123 words, 0 banned, 1 question

## Introducing Cross-Provider Prompt Caching We're rolling out a new caching layer for our API gateway that works across every major LLM provider you connect through it. Instead of resending identical prompts and paying full price each time, the gateway recognizes repeated requests and serves cached responses in milliseconds—regardless of whether you're routing to OpenAI, Anthropic, or Google. What does this mean for your bill and your latency? Both drop, often significantly, especially for teams running high-volume, repetitive workloads like customer support bots or batch content generation. The cache is configurable per route, with adjustable TTLs and invalidation rules, so you stay in control of freshness versus cost. Available now for all Pro and Enterprise plans. Check your dashboard to enable it today.

out 259 tok latenza 4.8 s

Rispetto dei vincoli (budget di parole, elenco di parole vietate, l'unica domanda), impronta stilistica e controllo della lunghezza.

Passa dall'uno all'altro cambiando una sola riga

In ogni scheda qui sotto ci sono entrambi gli id: le due righe evidenziate sono l'unica modifica. Stesso endpoint, stessa chiave, stessa struttura della richiesta.

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="claude-opus-5",
    # model="claude-sonnet-5",  # decommenta questa riga, commenta quella sopra
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

Ottieni la tua chiave API →

FAQ

Qual è il più economico, Claude Opus 5 o Claude Sonnet 5?

Claude Sonnet 5 costa meno alla voce Input / 1M token ($2 contro $5, 2.5× di differenza). Altre voci potrebbero dire il contrario: la tabella qui sopra riporta il listino completo, e il costo reale dipende dal tuo mix di utilizzo.

Posso fare un A/B test di Claude Opus 5 contro Claude Sonnet 5 senza due integrazioni?

Sì. Si chiamano entrambi dallo stesso endpoint compatibile con OpenAI, con una sola chiave API. Per passare dall'uno all'altro basta cambiare la stringa del modello in una riga, quindi puoi mandare una parte del traffico a ciascuno e confrontare direttamente i costi.

Claude Opus 5 e Claude Sonnet 5 supportano il prompt caching?

Sì: entrambi fanno pagare le letture dalla cache meno della tariffa di input, quindi i carichi di lavoro con un prefisso già in cache costano meno di quanto facciano pensare le tariffe di listino. Le voci esatte per la lettura dalla cache sono nella tabella dei prezzi qui sopra.

Confronti correlati

Dai nostri studi con dati misurati