Claude Fable 5.1 vs Claude Sonnet 5.5
O Claude Fable 5.1 é disponibilizado por convite. Os valores abaixo são as tarifas em tempo real, mas as chamadas exigem uma permissão de workspace primeiro; solicite-nos acesso antes de desenvolver com base nesta comparação.
Qual usar, quando
Estes estão separados por dois níveis na linha Claude: claude-fable-5-1 é o nível superior, que a Anthropic posiciona para raciocínio exigente e trabalho agêntico de longo horizonte, e claude-sonnet-5-5 é o nível inferior, que ela lista como rápido enquanto o Fable é mais lento. Ambos aceitam texto e imagem como entrada e carregam um contexto de 1000000-token com 128000 de saída máxima, então o preço marca a diferença: claude-fable-5-1 custa $10 para entrada e $50 para saída, 5x o claude-sonnet-5-5 a $2 e $10, com leituras de cache a $0.25 versus $0.2. Execute o tráfego diário e de alto volume no claude-sonnet-5-5, e escale para o claude-fable-5-1 nas tarefas de longo horizonte que o justificarem.
Benchmarks
Claude Sonnet 5.5: o fornecedor não publicou resultados de benchmark.
Publicado pelos fornecedores: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai
Preços
| Claude Fable 5.1 | Claude Sonnet 5.5 | Δ | |
|---|---|---|---|
| Entrada / 1M tokens | $10 | $2 | 5× |
| Saída / 1M tokens | $50 | $10 | 5× |
| Leitura de cache / 1M tokens | $0.25 | $0.2 | 1.3× |
| Escrita de cache | 1.25x (5m) / 2x (1h) | 1.25x (5m) / 2x (1h) | - |
Tarifas do catálogo em tempo real no momento do build; a página de cada modelo contém o cartão atual.
Onde eles se posicionam - preço de entrada por 1M tokens entre todos os 76 modelos de chat nesta unidade de cobrança (escala logarítmica)
Capacidades
| Claude Fable 5.1 | Claude Sonnet 5.5 | |
|---|---|---|
| Uso de ferramentas | sim | sim |
| Controle de raciocínio | sempre ativo | sempre ativo |
| Saída estruturada | sim | sim |
| Cache de prompt | 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 Fable 5.1 | Claude Sonnet 5.5 | |
|---|---|---|
| Modalidades de entrada | texto imagem | texto imagem |
| Modalidades de saída | texto | texto |
| Lançamento | 2026-09-01 | 2026-09-28 |
| Corte de conhecimento | 2026-06 | 2026-06 |
| Janela de contexto | 1M | 1M |
| Saída máxima | 128K | 128K |
| Parâmetro de raciocínio | output_config.effort (thinking is adaptive-only and always on) | thinking.type |
| Valores aceitos | effort
| thinking.type
|
| Padrão | thinking always on (adaptive) effort
| adaptive, effort high |
As especificações são transcritas da documentação de cada fornecedor; uma linha que um fornecedor não publica é omitida em vez de ser inferida. Fontes completas: Claude Fable 5.1 · Claude Sonnet 5.5
Um prompt, ambos os modelos - medidos pelo gateway
Claude Fable 5.1 passou · 3 sentences
When we enabled reasoning, the model started generating a long chain of internal "thinking" tokens before producing each answer, and we're billed for those tokens at the same output rate even though users never see them. In practice, that hidden reasoning often runs several times longer than the visible response, so the total tokens per request roughly doubled while the number of requests stayed flat. The upside is measurably better accuracy on complex tasks, so the right conversation is whether that quality gain justifies the cost—and if not, we can restrict reasoning to the workflows that actually need it rather than turning it on globally.
saída 186 tok latência 3.2 s
Claude Sonnet 5.5 passou · 3 sentences
Enabling reasoning makes the model "think" before it answers, and that internal thinking is generated as extra text (reasoning tokens) that we are billed for at the same rate as output tokens, even though users never see it. Output tokens also cost several times more than input tokens, so a single request that used to produce a short answer can now generate many times more billable text behind the scenes. Because our request volume and prompts didn't change, the doubling comes almost entirely from this hidden thinking, and we can bring it down by limiting reasoning effort, turning it off for simple tasks, and reserving it for the workloads where the accuracy gain justifies the cost.
saída 205 tok latência 3.6 s
Cumprimento da instrução (exatamente três frases - contáveis), ajuste ao público (registro de CFO), e a lacuna de cobrança do pensamento oculto que os medidores de tokens abaixo expõem.
Claude Fable 5.1 passou · 8/8 cases
```python def longest_run(xs): if not xs: return 0 best = cur = 1 for i in range(1, len(xs)): cur = cur + 1 if xs[i] == xs[i - 1] else 1 best = max(best, cur) return best ``` The bug is that `cur` counts *matches between adjacent elements* rather than *elements in the run*: it starts at 0 and only increments when `xs[i] == xs[i-1]`, so a run of length k produces a count of k−1. That's why a single element returns 0 instead of 1, and why every other run also comes out one short — the "misses runs at the end" reports are the same off-by-one seen on inputs like `[1, 2, 2]`, where the trailing run of length 2 is reported as 1 (the original code does update `best` inside the loop, so end-of-list runs aren't actually skipped, just undercounted). […]
saída 882 tok (+507 pensamento) latência 3.4 s
Claude Sonnet 5.5 passou · 8/8 cases
**The bug:** `cur` counts the number of *adjacent equal pairs* rather than the number of items in the run. A run of length k contains only k−1 such pairs, so every result is one too small. The counter also starts at 0 and the loop starts at index 1, so a single-element list never updates `best` and returns 0 instead of 1. (An empty list should return 0.) In addition, `cur` resets to 0 on a mismatch, when it should reset to 1, because the item at `xs[i]` begins a new run of length 1. The claim that it "misses runs ending at the last index" is really the same off-by-one: the final run is counted, but as one less than its true length. Because `best` is updated inside the loop on every extension, the last run isn't skipped. […]
saída 444 tok latência 6.7 s
Se a correção é de fato certa (executável), a densidade da explicação, e a eficiência em tokens numa tarefa delimitada.
Claude Fable 5.1 passou · 5/5 fields, guidance null
```json { "company": "Meridian Robotics", "quarter": "Q3 (September quarter)", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null } ``` Notes on judgment calls (not part of the object): - **revenue_usd_m**: The text says "412 for the topline" but never states the currency or that the figure is in millions; it's also on a constant-currency basis and prefaced with "call it," so it's approximate. If you want strict literalism, this should be `null`. - **growth_pct**: "Eleven and change" means slightly above 11%; the exact figure isn't given. - **quarter**: "September quarter" is Q3 on a calendar basis, consistent with the reference to a pending Q4 close. - **guidance**: Explicitly withheld, so `null`.
saída 633 tok (+349 pensamento) latência 3.8 s
Claude Sonnet 5.5 passou · 5/5 fields, guidance null
Here is the extracted JSON: ```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null } ``` Notes on the choices: - **quarter**: The text says "September quarter" without specifying a fiscal year or Q-number, so I kept the wording as stated. - **revenue_usd_m**: The text gives "412" for the topline, with no currency or unit stated explicitly. I've taken it as 412 million USD per the field definition, but the text does not confirm that, and the figure is constant-currency. - **growth_pct**: "Eleven and change" means slightly above 11, so 11 is an approximation. The exact figure isn't given. - **guidance**: Guidance is withheld pending the Q4 close, so no guidance is stated, hence null.
saída 300 tok latência 3.5 s
Obediência ao esquema (sem campos inventados), pressão de alucinação (guidance é explicitamente retida), e diferenças no caminho de saída estruturada.
Claude Fable 5.1 passou · 121 words, 0 banned, 1 question
**Introducing Cross-Provider Prompt Caching for the Gateway.** Starting today, your API gateway can cache prompts once and reuse them across OpenAI, Anthropic, Google, and any other provider you route to. Long system instructions, retrieval context, and few-shot examples are stored at the gateway layer, so switching models no longer means paying to resend the same tokens. Why send the same 8,000-token preamble to three different vendors when you could send it once? Our cache normalizes prompt segments, fingerprints them, and serves matching prefixes from memory before the request ever reaches an upstream API. Early customers report token costs falling by 30 to 60 percent on high-volume workloads, with median latency dropping alongside. Available today on all Team and Enterprise plans.
saída 1722 tok (+1463 pensamento) latência 2.9 s
Claude Sonnet 5.5 passou · 122 words, 0 banned, 1 question
**Introducing Cross-Provider Prompt Caching** Your API gateway now caches prompts across every connected LLM provider, whether you route traffic to OpenAI, Anthropic, Google, or a self-hosted model. Here's how it works: the gateway fingerprints each prompt prefix, stores it centrally, and applies the right provider-specific caching mechanism automatically. When you switch providers or fail over during an outage, your cached context follows you. Early testing shows input token costs dropping by up to 70% on repeated system prompts and long documents, with latency improvements of 40% or more on cache hits. Tired of paying to send the same instructions thousands of times a day? Enable it with one configuration flag. Cache rules, TTLs, and per-team isolation are available in the dashboard today.
saída 266 tok latência 3.8 s
Obediência às restrições (orçamento de palavras, lista de palavras proibidas, a única pergunta), impressão digital de estilo, e controle de comprimento.
Alterne entre eles com uma linha
Ambos os IDs estão em todas as abas abaixo - o par de linhas destacado é a única edição. Mesmo endpoint, mesma chave, mesmo formato de requisição.
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="claude-fable-5-1",
# model="claude-sonnet-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-fable-5-1",
// model: "claude-sonnet-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-fable-5-1",
# "model": "claude-sonnet-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-fable-5-1",
// Model: "claude-sonnet-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-fable-5-1")
// .model("claude-sonnet-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(""));FAQ
Qual é mais barato, Claude Fable 5.1 ou Claude Sonnet 5.5?
Claude Sonnet 5.5 é mais barato em entrada / 1m tokens ($2 vs $10, com 5.0× de diferença). Outras linhas podem apontar para o outro lado - a tabela acima traz o quadro completo, e o custo real depende do seu mix.
Posso fazer um teste A/B de Claude Fable 5.1 contra Claude Sonnet 5.5 sem duas integrações?
Sim. Ambos são servidos pelo mesmo endpoint compatível com OpenAI com uma única chave de API - a troca é uma alteração de uma linha na string do modelo, de modo que você pode rotear uma fração do tráfego para cada um e comparar as faturas diretamente.
Claude Fable 5.1 e Claude Sonnet 5.5 suportam prompt caching?
Sim - ambos cobram leituras em cache abaixo da sua taxa de entrada, então cargas de trabalho com warm-prefix custam menos do que as taxas listadas sugerem. As linhas exatas de leitura em cache estão na tabela de preços acima.