Claude

Claude Opus 4.8

AnthropicToken-based
Alias:claude-opus-4-8
Create API Key

Compare claude-opus-4-8 API pricing, supported endpoints, capabilities and access options on Modelsell.

textimagestreamingfunction_callingtoolsvisionreasoningcachingcontext:1000000
Starting price
Input / Output · 1M
Context
1M
Maximum input window
Max output
128K
Maximum tokens per response
Modalities
→
Knowledge cutoff
Jan 2026
Released
May 2026

Pricing by Supplier

Anthropic
-10%
Anthropic 官方
Input$5$4.5/ 1M
Output$25$22.5/ 1M
Cache Read$0.5$0.45/ 1M
Cache Write (5m)$6.25$5.625/ 1M
Cache Write (1h)$10$9/ 1M
AmazonBedrock
-40%
AWS 官方
Input$5$3/ 1M
Output$25$15/ 1M
Cache Read$0.5$0.3/ 1M
Cache Write (5m)$6.25$3.75/ 1M
Cache Write (1h)$10$6/ 1M
Vertex Claude
-30%
Google Vertex 官方 Claude直连
Input$5$3.5/ 1M
Output$25$17.5/ 1M
Cache Read$0.5$0.35/ 1M
Cache Write (5m)$6.25$4.375/ 1M
Cache Write (1h)$10$7/ 1M
claude特供
-40%
适合生产环境,AWS Bedrock组成
Input$5$3/ 1M
Output$25$15/ 1M
Cache Read$0.5$0.3/ 1M
Cache Write (5m)$6.25$3.75/ 1M
Cache Write (1h)$10$6/ 1M
CCMax
-70%
使用自用 vibe coding,纯血 ccmax号池
Input$5$1.5/ 1M
Output$25$7.5/ 1M
Cache Read$0.5$0.15/ 1M
Cache Write (5m)$6.25$1.875/ 1M
Cache Write (1h)$10$3/ 1M
Claude kiro
-90%
使用自用 vibe coding,kiro号池
Input$5$0.5/ 1M
Output$25$2.5/ 1M
Cache Read$0.5$0.05/ 1M
Cache Write (5m)$6.25$0.625/ 1M
Cache Write (1h)$10$1/ 1M
CCMax-ZL
-70%
CCmax微注-可蒸
Input$5$1.5/ 1M
Output$25$7.5/ 1M
Cache Read$0.5$0.15/ 1M
Cache Write (5m)$6.25$1.875/ 1M
Cache Write (1h)$10$3/ 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 retention79 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 Opus 4.8

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 Opus 4.8

让长材料形成清楚的判断

Claude Opus 4.8 适合在信息量大、约束较多的工作中做深入分析。你可以把项目说明、旧代码、接口约定和报错记录一起提供,让它解释系统行为、查找冲突并提出修改方案;也可以让它对照多份合同、研究资料或访谈记录,梳理各方观点与证据,形成便于审阅的报告。

它接受文本和图片,并以文字作答。产品原型、流程截图、图表等视觉材料可以与说明文档一起分析,例如检查页面状态是否符合业务规则,或解释图中趋势与报告结论是否一致。对于关键数字,最好同时提供原始表格或文字,便于逐项核算。

百万 Token 级上下文使它能够处理较长的资料包。实际使用时,把材料按文件和章节命名,先说明需要解决的问题,再要求引用相关段落,比直接堆放全部内容更容易获得可核查的答案。它的自适应思考机制适合需要权衡多种方案的任务,也支持用函数调用和结构化结果衔接应用流程。

在研发场景中,可让它从需求推到实现计划、测试覆盖和代码审查;在写作场景中,可约定受众、语气、术语与论证顺序,让长报告保持一致。若接入外部查询或执行工具,应给出工具权限与停下来的条件,方便控制任务范围。

使用中常问

能用它检查合同差异吗? 可以先提取条款,再按同一主题比较责任、期限和例外;让它标注原文位置,供专业人员复核。

怎样让建议更具体? 给出真实限制,例如兼容版本、工期、预算和不可修改的行为,要求说明每个方案的代价与适用条件。

Use cases and prompting

用对照任务发挥长文档能力

把文档编号,明确比较维度,并区分原文事实与推论。

请比较附件 A 的采购合同和附件 B 的供应商修订稿。
只分析交付验收、违约责任和数据保密三类条款。
每个差异给出两份文件的段落位置、义务变化、可能影响及需要向对方确认的问题。
最后写一封简洁的谈判要点草稿,保留我方提出的 30 天验收期限。

代码任务请同时提供相关文件、错误表现和预期结果;要求它先画清调用关系,再给最小修改与回归检查。长篇输出可按章节分次生成,并保持同一术语表。

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
AmazonBedrock-ZLUnlimitedUnlimitedUnlimited
AnthropicUnlimitedUnlimitedUnlimited
CCMax-ZLUnlimitedUnlimitedUnlimited
Claude kiroUnlimitedUnlimitedUnlimited
Claude kiro ZLUnlimitedUnlimitedUnlimited
claude特供UnlimitedUnlimitedUnlimited
Vertex ClaudeUnlimitedUnlimitedUnlimited
AmazonBedrockUnlimitedUnlimitedUnlimited
CCMaxUnlimitedUnlimitedUnlimited
defaultUnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about claude-opus-4-8

What is claude-opus-4-8?

Compare claude-opus-4-8 API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call claude-opus-4-8?

Create an API key with access to claude-opus-4-8, 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-opus-4-8 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-opus-4-8?

The model catalog lists a context window of 1000000 tokens. Check the selected endpoint for request limits.

What is the maximum output of claude-opus-4-8?

The model catalog lists a maximum output of 128000 tokens. Your request settings may set a lower limit.

How should I evaluate claude-opus-4-8 for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.