Claude
Anthropic's LLM for complex reasoning, code, analysis, and extended-context tasks.
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/claude -gInstall 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.
Claude is Anthropic's large language model family available in Opus, Sonnet, and Haiku tiers, designed for nuanced reasoning, long-context analysis, and code generation. It emphasizes accuracy, instruction following, and predictable outputs.
- Installable agent skill
- Unified API key
- SDK examples included
- 失敗した生成は課金されません
バリアント
| Variant | Billing | From | |
|---|---|---|---|
| claude-haiku-4-5-20251001 | 1K tokens | $0.050 | 見る → |
| claude-opus-4-5-20251101 | 1K tokens | $0.250 | 見る → |
| claude-opus-4-6 | 1K tokens | $0.250 | 見る → |
| claude-opus-4-7 | 1K tokens | $0.250 | 見る → |
| claude-opus-4-8 | 1K tokens | $0.250 | 見る → |
| claude-sonnet-4-5-20250929 | 1K tokens | $0.130 | 見る → |
| claude-sonnet-4-6 | 1K tokens | $0.130 | 見る → |
Use this model from your agent
# User prompt to the agent
"Review this pull request for security vulnerabilities, performance issues, and suggest concrete improvements."// Code generated by the agent via @runapi.ai/claude
import { ClaudeClient } from '@runapi.ai/claude';
const client = new ClaudeClient();
const result = await client.message.run({
model: 'claude-haiku-4-5-20251001',
prompt: 'Review this pull request for security vulnerabilities, performance issues, and suggest concrete improvements.',
});How to call this model
Install the skill
Add the model skill to your agent or install the SDK package.
Authenticate once
Use your RunAPI key for every supported model.
Send a request
Use the unified schema for the endpoint you need.
Receive output
Poll by task ID or handle the callback when the generation completes.
SDK quickstart
curl -X POST https://runapi.ai/v1/messages \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-haiku-4-5-20251001",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Review this pull request for security vulnerabilities, performance issues, and suggest concrete improvements."
}
]
}'import { ClaudeClient } from "@runapi.ai/claude";
const client = new ClaudeClient();
const result = await client.message.run({
model: "claude-haiku-4-5-20251001",
max_tokens: 1024,
messages: [{"role":"user","content":"Review this pull request for security vulnerabilities, performance issues, and suggest concrete improvements."}],
});require "runapi/claude"
client = RunApi::Claude::Client.new
result = client.message.run(
model: "claude-haiku-4-5-20251001",
max_tokens: 1024,
messages: [{role: "user", content: "Review this pull request for security vulnerabilities, performance issues, and suggest concrete improvements."}]
)Where Claude fits
Claude is Anthropic's LLM family, spanning Opus (frontier), Sonnet (balanced), and Haiku (fast). Through RunAPI, all Claude variants share the same API shape and per-token billing.
Why use Claude through RunAPI
One API key
Use the same credentials across models and providers.
Agent-ready
Installable skills include docs and schema for tool calls.
Predictable billing
Usage-based pricing is visible before you call.
Frequently asked questions
How do I call this model?
Use the RunAPI SDK, CLI, or REST endpoint shown on this page.
Do failed generations cost money?
失敗した生成は課金されません
Can agents use it directly?
Yes. Install the model skill and your agent gets the docs, schema, and examples.
