Claude

Claude Haiku 4.5

AnthropicToken-based
Alias:claude-haiku-4-5
Create API Key

Compare claude-haiku-4-5 API pricing, supported endpoints, capabilities and access options on Modelsell.

textimagestreamingfunction_callingtoolsvisionreasoningcachingcontext:200000
Starting price
Input / Output · 1M
Context
200K
Maximum input window
Max output
64K
Maximum tokens per response
Modalities
→
Knowledge cutoff
Feb 2025
Released
Oct 2025

Pricing by Supplier

Anthropic
-10%
Anthropic 官方
Input$1$0.9/ 1M
Output$5$4.5/ 1M
Cache Read$0.1$0.09/ 1M
Cache Write (5m)$1.25$1.125/ 1M
Cache Write (1h)$2$1.8/ 1M
AmazonBedrock
-40%
AWS 官方
Input$1$0.6/ 1M
Output$5$3/ 1M
Cache Read$0.1$0.06/ 1M
Cache Write (5m)$1.25$0.75/ 1M
Cache Write (1h)$2$1.2/ 1M
claude特供
-40%
适合生产环境,AWS Bedrock组成
Input$1$0.6/ 1M
Output$5$3/ 1M
Cache Read$0.1$0.06/ 1M
Cache Write (5m)$1.25$0.75/ 1M
Cache Write (1h)$2$1.2/ 1M
CCMax
-70%
使用自用 vibe coding,纯血 ccmax号池
Input$1$0.3/ 1M
Output$5$1.5/ 1M
Cache Read$0.1$0.03/ 1M
Cache Write (5m)$1.25$0.375/ 1M
Cache Write (1h)$2$0.6/ 1M
Claude kiro
-90%
使用自用 vibe coding,kiro号池
Input$1$0.1/ 1M
Output$5$0.5/ 1M
Cache Read$0.1$0.01/ 1M
Cache Write (5m)$1.25$0.125/ 1M
Cache Write (1h)$2$0.2/ 1M
CCMax-ZL
-70%
CCmax微注-可蒸
Input$1$0.3/ 1M
Output$5$1.5/ 1M
Cache Read$0.1$0.03/ 1M
Cache Write (5m)$1.25$0.375/ 1M
Cache Write (1h)$2$0.6/ 1M

Capabilities / Supported modalities

Function callingToolsJSON modeStructured outputReasoningVisionPrompt caching
Input
Output

Provider & data privacy

Provider
AnthropicDocs
Tokenizer
Anthropic Claude tokenizer
License
Proprietary (commercial)Proprietary
Data retention89 daysNot used for upstream training by default

Performance

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis 2026-09-30·Claude Haiku 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 Haiku 4.5

为高频助手任务提供及时反馈

Claude Haiku 4.5 适合任务明确、调用频繁的应用,例如给客服消息分类、提取文档字段、生成简短回复、解释局部代码,或为更大的工作流程整理输入。对需要快速获得可继续处理结果的团队,可以用它承担基础分析与常规沟通。

它接受文字和图片,输出文字。除了处理纯文本工单,也可以读取截图、票据或图文说明。例如,从客服截图中提取错误提示与操作步骤,再整理成技术工单;从表单图片中提取已填写内容,并标出缺失项。图片中的小字和关键数字应返回原文,便于人工或程序校验。

函数调用与结构化输出让它能成为业务流程的一环。可以规定分类标签、字段和缺失值,再把输出交给系统保存;也可以让它选择查询工具,获取订单或知识库结果后生成回复。实际查询、数据更新与权限检查由应用工具完成。

需要更多分析时,它支持手动开启扩展思考。这与自适应思考的配置不同,应使用对应的 thinking 设置并预留预算。对简单字段提取,清楚的规则与少量示例往往比增加思考更直接;对多条件判断,则可以评估开启思考后的质量和延迟。

工作流问题

适合承担哪些分工? 文档初筛、信息整理、常规代码解释和格式转换都适合定义清楚的输入输出。

什么时候转交更强模型? 遇到证据冲突、复杂跨模块问题或重要决策时,可以先整理事实与待解决问题,再交给深入分析流程。

Use cases and prompting

让快速结果能直接交接

给出固定分类与字段,保留足够原文依据。

根据这段客服对话和报错截图生成技术工单。
返回 JSON:title、category、steps、error_text、expected_behavior、missing_info。
category 只选登录、支付、文件上传或其他。
steps 按用户已描述的操作排序;不清楚的内容放入 missing_info,不自行补全。

代码问题限定到函数或模块,并附样例。需要扩展思考时按手动 thinking 配置启用;日常分类先用代表样本检查标签混淆、字段缺失和结果格式,再接入高频调用。

API access

API documentation

Code samples

RequestPOST/v1/messages
Example request
Parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum 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
integer0 ~ 20Number 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

Generation parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum 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
integer0 ~ 20Number 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

SupplierRPMTPMRPD
claude特供UnlimitedUnlimitedUnlimited
defaultUnlimitedUnlimitedUnlimited
AmazonBedrockUnlimitedUnlimitedUnlimited
AnthropicUnlimitedUnlimitedUnlimited
CCMaxUnlimitedUnlimitedUnlimited
CCMax-ZLUnlimitedUnlimitedUnlimited
Claude kiroUnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about claude-haiku-4-5

What is claude-haiku-4-5?

Compare claude-haiku-4-5 API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call claude-haiku-4-5?

Create an API key with access to claude-haiku-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-haiku-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-haiku-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-haiku-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-haiku-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.