变体 · Anthropic / Claude

Claude claude-opus-4-8 API

同一套 API，同一个 SDK — 切换变体只需改一个参数。

运行中 · text · 可商用

# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/claude -g

The -g flag installs globally so every project picks it up.

Or paste this prompt to your AI agent:

Install the Claude skill for me:

1. Clone https://github.com/runapi-ai/claude
2. Copy the skills/claude/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.

切换变体

claude-haiku-4-5-20251001 claude-opus-4-5-20251101 claude-opus-4-6 claude-opus-4-7 claude-sonnet-4-5-20250929 claude-sonnet-4-6

概览

claude-opus-4-8 在 Claude 家族中处于质量与成本的最佳平衡点。

USD 按次定价
失败不计费
模型支持时流式
Schema 校验后的工具调用

定价

失败的生成不计费

Messages API

Input $2.50 / 1M tokens

Output $12.50 / 1M tokens

Cache read $0.25

Cache write 5m $3.13

Cache write 1h $5.00

规格

技术细节

模型 ID	claude-opus-4-8
提供方	Anthropic
模态	text
任务类型	synchronous
计费单位	1K tokens
API 端点	/v1/messages
商用许可	允许商用
状态	运行中

快速开始

Quickstart — claude-opus-4-8

runapi.ai

curl -X POST https://runapi.ai/v1/messages \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-opus-4-8",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "审查这个 PR 的安全漏洞和性能问题，并给出具体改进建议。"
    }
  ]
}'

import { ClaudeClient } from "@runapi.ai/claude";

const client = new ClaudeClient();
const result = await client.message.run({
    model: "claude-opus-4-8",
    max_tokens: 1024,
    messages: [{"role":"user","content":"审查这个 PR 的安全漏洞和性能问题，并给出具体改进建议。"}],
});

require "runapi/claude"

client = RunApi::Claude::Client.new
result = client.message.run(
    model: "claude-opus-4-8",
    max_tokens: 1024,
    messages: [{role: "user", content: "审查这个 PR 的安全漏洞和性能问题，并给出具体改进建议。"}]
)

@runapi.ai/claude v1

工作流程