Claude Opus 5 vs Claude Opus 5.5
Qual usar e quando
Esses dois modelos da Anthropic se igualam nos fatos que geralmente decidem as coisas: ambos aceitam entrada de texto e imagem, emitem texto, possuem um contexto de 1000000 de tokens com saída máxima de 128000, e listam as mesmas capacidades de chat, código, pensamento, ferramentas e raciocínio. O claude-opus-5-5 é o mais novo (lançado em 2026-09-22, corte em 2026-06) e o mais barato a $4 de entrada e $20 de saída contra $5 e $25, com leituras de cache a $0.2 contra $0.5, 2.5 vezes menos. Escolha o claude-opus-5 apenas se precisar desativar o pensamento, já que ele permite isso e o claude-opus-5-5 não; caso contrário, leve o 5.5.
Benchmarks
9 medidos em ambos.
Publicado pelos provedores: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai
Preços
| Claude Opus 5 | Claude Opus 5.5 | Δ | |
|---|---|---|---|
| Entrada / 1M tokens | $5 | $4 | 1.3× |
| Saída / 1M tokens | $25 | $20 | 1.3× |
| Leitura de cache / 1M tokens | $0.5 | $0.2 | 2.5× |
| Escrita de cache | 1.25x (5m) / 2x (1h) | 1.25x (5m) / 2x (1h) | - |
Tarifas do catálogo em tempo real, lidas no momento do build; a página de cada modelo traz a tabela de preços atual.
Onde cada um fica: preço de entrada por 1M tokens entre os 77 modelos de chat com esta unidade de cobrança (escala logarítmica)
Capacidades
| Claude Opus 5 | Claude Opus 5.5 | |
|---|---|---|
| Uso de ferramentas | sim | sim |
| Controle de raciocínio | configurável | sempre ativo |
| Saída estruturada | sim | sim |
| Cache de prompts | explícito (você marca o prefixo) | explícito (você marca o prefixo) |
| Tempo de vida do cache | 5m default, 1h option | 5m default, 1h option |
| Prefixo mínimo em cache | 1024 tokens | 1024 tokens |
Especificações
| Claude Opus 5 | Claude Opus 5.5 | |
|---|---|---|
| Modalidades de entrada | texto imagem | texto imagem |
| Modalidades de saída | texto | texto |
| Lançamento | 2026-07-24 | 2026-09-22 |
| Corte de conhecimento | 2026-05 | 2026-06 |
| Janela de contexto | 1M | 1M |
| Saída máxima | 128K | 128K |
| Parâmetro de raciocínio |
| output_config.effort |
| Valores aceitos | thinking.type
effort
| output_config.effort
|
| Padrão | thinking on effort
| medium |
As especificações são transcritas da documentação de cada provedor; quando um provedor não publica um dado, a linha é omitida, e não inferida. Fontes completas: Claude Opus 5 · Claude Opus 5.5
Um prompt, os dois modelos, medidos pelo gateway
Claude Opus 5 passou · 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.
saída 529 tok latência 9.0 s
Claude Opus 5.5 passou · 3 sentences
When we turned on reasoning, the model began "thinking out loud" before each answer, generating thousands of internal working tokens that users never see but that we are billed for just like the final response. Those hidden tokens are charged at the output rate, typically the most expensive rate, so the same question with the same visible answer now costs roughly twice as much or more. We can bring the bill back down without losing the quality gains by capping the reasoning budget and reserving reasoning mode for the complex tasks that actually benefit from it.
saída 263 tok (+102 raciocínio) latência 5.7 s
Se a instrução é seguida (exatamente três frases, dá para contar), a adequação ao público (tom para um CFO) e a diferença de cobrança causada pelo raciocínio oculto, que os medidores de tokens abaixo deixam à mostra.
Claude Opus 5 passou · 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`. […]
saída 1094 tok latência 16.1 s
Claude Opus 5.5 passou · 8/8 cases
```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 best = max(best, cur) else: cur = 1 return best ``` **Explanation:** The original code counted *matching adjacent pairs* rather than *items in a run*. Both `cur` and `best` started at 0, and `cur` reset to 0 on a mismatch, so a run of length *n* was reported as *n − 1*. For a single-element list the loop never executes, so it returned 0 instead of 1. For `[5, 5]` it returned 1 instead of 2. The fix treats every element as the start of a run of length 1: `best` and `cur` start at 1, and `cur` resets to 1 (not 0) when the value changes. An explicit check returns 0 for an empty list. The "misses runs at the last index" reports are the same off-by-one bug rather than a separate one. […]
saída 723 tok (+303 raciocínio) latência 10.4 s
Se a correção está mesmo certa (dá para executar), a densidade da explicação e a eficiência em tokens em uma tarefa bem delimitada.
Claude Opus 5 passou · 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.
saída 539 tok latência 7.6 s
Claude Opus 5.5 passou · 5/5 fields, guidance "Withheld pending Q4 close"
```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "Withheld pending Q4 close" } ``` **Judgment calls to check:** - **quarter**: Kept as "September quarter" rather than "Q3", since the fiscal calendar isn't stated. The text mentions an upcoming "Q4 close," so it may be fiscal Q3, but that's not certain. - **revenue_usd_m**: The text says only "412 for the topline." It doesn't state currency or units, and the figure is on a constant-currency basis, not reported USD. USD millions is an assumption. Use `null` if you need strictly stated values. - **growth_pct**: The source says "eleven and change," so the true figure is slightly above 11. 11 is an approximation. - **guidance**: Guidance was explicitly withheld. I recorded that rather than `null`, since the text addresses it directly.
saída 829 tok (+488 raciocínio) latência 10.9 s
Aderência ao schema (sem campos inventados), pressão para alucinar (o texto diz explicitamente que o guidance não foi divulgado) e diferenças no caminho de saída estruturada.
Claude Opus 5 passou · 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.
saída 1593 tok latência 19.1 s
Claude Opus 5.5 passou · 120 words, 0 banned, 1 question
Today we're launching Cross-Provider Prompt Caching for our API gateway. Why pay twice for the same context? Our gateway now stores repeated prompt prefixes, system instructions, and document chunks, then reuses them whether your request goes to OpenAI, Anthropic, Google, or an open-source model. Teams running retrieval pipelines or long agent loops can cut token costs by up to 60 percent and trim latency on every cached call. Setup takes one configuration flag; no code changes are required. Cache rules respect tenant boundaries, expire on your schedule, and log every hit for audit review. Dashboards show savings by provider, route, and application in real time. Cross-Provider Prompt Caching is available on all Pro and Enterprise plans. Turn it on today.
saída 1263 tok (+1007 raciocínio) latência 13.5 s
Respeito às restrições (limite de palavras, lista de palavras proibidas, uma única pergunta), a marca de estilo de cada modelo e o controle do tamanho.
Troque de um para o outro mudando uma linha
Os dois ids estão em todas as abas abaixo; o par de linhas destacado é a única alteração. O endpoint, a chave e o formato da requisição são os mesmos.
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-opus-5-5", # descomente esta linha, comente a linha acima
messages=[{"role": "user", "content": "Summarize this diff"}],
reasoning_effort="medium",
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "claude-opus-5",
// model: "claude-opus-5-5", // descomente esta linha, comente a linha acima
messages: [{ role: "user", content: "Summarize this diff" }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-5",
# "model": "claude-opus-5-5", # descomente esta linha, comente a linha acima
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "claude-opus-5",
// Model: "claude-opus-5-5", // descomente esta linha, comente a linha acima
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("claude-opus-5")
// .model("claude-opus-5-5") // descomente esta linha, comente a linha acima
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));Perguntas frequentes
Qual é mais barato, Claude Opus 5 ou Claude Opus 5.5?
Claude Opus 5.5 sai mais barato na linha “Entrada / 1M tokens” ($4 contra $5, 1.3× de diferença). Outras linhas podem pender para o outro lado: a tabela acima mostra todos os preços, e o custo real depende do seu mix de uso.
Posso fazer um teste A/B de Claude Opus 5 contra Claude Opus 5.5 sem duas integrações?
Sim. Os dois são servidos pelo mesmo endpoint compatível com OpenAI, com uma única chave de API. Para trocar, basta mudar uma linha, a string do modelo; assim você pode direcionar uma parte do tráfego para cada um e comparar as contas diretamente.
Claude Opus 5 e Claude Opus 5.5 suportam cache de prompts?
Sim. Os dois cobram as leituras de cache abaixo da tarifa de entrada, então cargas de trabalho com prefixo já em cache custam menos do que os preços de tabela sugerem. Os valores exatos de leitura de cache estão na tabela de preços acima.