Claude Sonnet 4.5
claude-sonnet-4-5Compare claude-sonnet-4-5 API pricing, supported endpoints, capabilities and access options on Modelsell.
- Starting price
- Input / Output · 1M
- Context
- 200K
- Maximum input window
- Max output
- 64K
- Maximum tokens per response
- Modalities
- →
- Knowledge cutoff
- Jan 2025
- Released
- Sep 2025
Pricing by Supplier
Capabilities / Supported modalities
Provider & data privacy
Anthropic Claude tokenizerPerformance
Benchmarks
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows
Metrics sourced fromArtificial Analysis 2026-09-30·Claude Sonnet 4.5
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.
About Claude Sonnet 4.5
日常开发与文档工作的协作助手
Claude Sonnet 4.5 适合阅读项目代码、分析问题、起草内容和整理资料。你可以用它解释一个模块、根据需求规划改动，或把会议讨论转成任务与验收项。对于已经采用这一版本的应用，它也适合做固定任务回归与既有流程维护。
它支持文字和图片输入，输出文字。产品截图、流程示意和图文材料可以补充需求描述，例如根据截图分析表单提示是否清楚，或对照流程图检查代码缺少的异常分支。让它引用可见区域、文件位置或资料段落，可以使团队更容易核对。
在编程场景中，提供运行环境、关联文件与预期行为，再要求最小修改与测试方案。扩展思考可以帮助处理多条件判断；函数调用可以连接查询、文件处理与执行工具；结构化输出则适合把结果转成工单或检查记录。所有实际操作都需要相应工具反馈来确认。
较长的上下文能够容纳项目资料，但应把当前规范与历史讨论区分清楚。处理长文时，可以先生成索引和重点问题，再按章节分析，最后统一术语与结论。不要将未确认的讨论意见直接写成既定规则。
维护已有应用
现在还适合新项目选用吗？ 官方已将 Sonnet 4.5 列为弃用，并计划于 2026 年 11 月 30 日退役。新项目和长期工作流应安排版本评估，既有调用也要关注渠道通知。
切换版本时怎样检查？ 保留真实任务样本，对比回答格式、工具调用和业务结果，确认满足原有验收条件后再调整应用。
Use cases and prompting
用明确任务维护现有流程
说明当前行为、改动目标和保持兼容的部分。
根据这份反馈，改进注册表单的错误提示。
结合页面截图和校验规则，找出用户难以理解的地方，给出简短清楚的替换文案。
保留字段名称和校验条件；按触发场景列出旧文案、新文案与原因，再给交互验收步骤。
代码修改附上相关测试，长文编辑列明必须保留的事实。维护版本迁移时保存代表样本，核对结构化字段、工具参数和异常分支；同时留意模型退役时间与渠道可用性。
API access
API documentation
Code samples
/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.
Authentication
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.
Supported parameters
| 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 |
Rate limits
| Supplier | RPM | TPM | RPD |
|---|---|---|---|
| claude特供 | Unlimited | Unlimited | Unlimited |
| default | Unlimited | Unlimited | Unlimited |
| AmazonBedrock | Unlimited | Unlimited | Unlimited |
| Anthropic | Unlimited | Unlimited | Unlimited |
| CCMax | Unlimited | Unlimited | Unlimited |
| CCMax-ZL | Unlimited | Unlimited | Unlimited |
| Claude kiro | Unlimited | Unlimited | Unlimited |
No restriction
Frequently asked questions about claude-sonnet-4-5
What is claude-sonnet-4-5?
Compare claude-sonnet-4-5 API pricing, supported endpoints, capabilities and access options on Modelsell.
How do I call claude-sonnet-4-5?
Create an API key with access to claude-sonnet-4-5, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.
How is claude-sonnet-4-5 priced?
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.
What is the context window of claude-sonnet-4-5?
The model catalog lists a context window of 200000 tokens. Check the selected endpoint for request limits.
What is the maximum output of claude-sonnet-4-5?
The model catalog lists a maximum output of 64000 tokens. Your request settings may set a lower limit.
How should I evaluate claude-sonnet-4-5 for my project?
Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.