PROVEEDOR

Anthropic

Claude Opus, Sonnet, and Haiku — Anthropic's reasoning-first LLMs for code, analysis, and extended context.

1 models · 7 variants · desde $0.050
RESUMEN

Anthropic builds the Claude family of large language models, spanning Opus (frontier reasoning), Sonnet (balanced), and Haiku (fast and efficient). All variants excel at complex reasoning, code generation, analysis, and extended-context tasks.

  • Single API key shared across providers
  • Per-call billing, no commitment
  • Las generaciones fallidas no se cobran
  • Streaming supported where the model supports it
FUNCIONES

What stands out

MODELOS

All models from Anthropic

INSTALAR

Start with any Anthropic model.

Pick a model, install the skill, and start calling from any agent.

# 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.
REFERENCIA

Every variant from Anthropic

Tabla completa de precios →
Model Variant Billing From
Claude
claude-haiku-4-5-20251001 1K tokens $0.050 Ver →
claude-opus-4-5-20251101 1K tokens $0.250 Ver →
claude-opus-4-6 1K tokens $0.250 Ver →
claude-opus-4-7 1K tokens $0.250 Ver →
claude-opus-4-8 1K tokens $0.250 Ver →
claude-sonnet-4-5-20250929 1K tokens $0.130 Ver →
claude-sonnet-4-6 1K tokens $0.130 Ver →
FAQ

Frequently asked questions about Anthropic

Is this an official Anthropic integration?

RunAPI exposes a managed API surface with transparent pricing, capability, and error behavior.

Do I need a Anthropic account?

No. Your RunAPI key is enough for managed access.

How is pricing billed?

Per-call or per-unit metered, with failed generations not charged.

EMPEZAR

Start calling Anthropic models from one API.