claude-fable-5-2Compare claude-fable-5-2 API pricing, supported endpoints, capabilities and access options on Modelsell.
| Input/ 1M tokens | Output/ 1M tokens | Cache Read/ 1M tokens | Cache Write (5m)/ 1M tokens | Cache Write (1h)/ 1M tokens |
|---|---|---|---|---|
$7.2 | $36 | $0.18 | $9 | $14.4 |
| Input/ 1M tokens | Output/ 1M tokens | Cache Read/ 1M tokens | Cache Write (5m)/ 1M tokens | Cache Write (1h)/ 1M tokens |
|---|---|---|---|---|
$2.4 | $12 | $0.06 | $3 | $4.8 |
Anthropic Claude tokenizerScores on standardized evaluations. Higher percentages are better — and rank percentile shows
Metrics sourced fromArtificial Analysis 2026-09-30·Claude Fable 5.2
This model is not included in the current benchmark snapshot.
Missing models or measurements are not zero scores.
Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.
Claude Fable 5.2 是 Anthropic 面向高难度推理与长周期智能体工作的模型,适合复杂编程、多步骤深度研究,以及结合工具制作文档、表格和演示成果。它支持文本和图片输入、文本输出,具有 1,000,000 token 上下文和 128,000 token 最大输出;知识截止日期为 2026 年 6 月,参数量未公开。
模型始终开启自适应思考,默认 effort 为 high,可以通过 output_config.effort 调整推理投入。长任务应明确目标、阶段交付物和验收方法,并保留完整的工具结果与对话。文件制作和代码执行需要应用提供相应工具。
相较 Fable 5.1,官方报告该版本在编程、推理和视觉理解方面有所提升,标准输入与输出单价降低 20%。官方建议多数日常编程和知识任务先使用 Opus 5.5,再按任务难度选用 Fable 5.2。
单位均为美元 / 百万 token;以下为 Anthropic 第一方 API 价格。
| 项目 | 价格 |
|---|---|
| 标准输入 | 8 |
| 标准输出(包含思考 token) | 40 |
| 缓存读取 | 0.20 |
| 5 分钟缓存写入 | 10 |
| 1 小时缓存写入 | 16 |
| Fast 输入 / 输出 | 16 / 80 |
| Batch 输入 / 输出 | 4 / 20 |
标准价格覆盖完整 1M 上下文,无额外长上下文阶梯加价。Fast 与 Batch 是不同服务模式,Fast 不支持 Batch;它们的官方价格不代表本站渠道已开通对应能力。本站实际费用仍由已接入渠道与所选分组确定。
资料核实日期:2026-11-10。
接入支持该模型的渠道后,可使用 Anthropic Messages 协议:
POST /v1/messages
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
anthropic-version: 2023-06-01
{
"model": "claude-fable-5-2",
"max_tokens": 4096,
"output_config": { "effort": "high" },
"messages": [
{
"role": "user",
"content": "分析这项跨模块改造:先列出约束和风险,再给出实施步骤、验证方法和需要补充的信息。"
}
]
}
该示例依据官方参数说明与本站鉴权方式编写,尚无本站该模型渠道的实测记录。
temperature、top_p、top_k;不发送关闭 thinking 或手动 budget_tokens 的配置。auto、none;强制 any 或指定 tool 会报 400。不支持 assistant 消息预填充。/v1/messages| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
Replace <YOUR_API_KEY> with the API key from your token settings.
All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.
Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.
| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
| Supplier | RPM | TPM | RPD |
|---|---|---|---|
| Anthropic | Unlimited | Unlimited | Unlimited |
| CCMax | Unlimited | Unlimited | Unlimited |
No restriction
Compare claude-fable-5-2 API pricing, supported endpoints, capabilities and access options on Modelsell.
Create an API key with access to claude-fable-5-2, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.
Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.
The model catalog lists a context window of 1000000 tokens. Check the selected endpoint for request limits.
The model catalog lists a maximum output of 128000 tokens. Your request settings may set a lower limit.
Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.
