Claude Opus 5 API
claude-opus-5Claude Opus 5 — frontier reasoning and generation through one API.
by Anthropic
Pricing: Input 190 credits / 1M tokens (≈ $1.9), Output 980 credits / 1M tokens (≈ $9.8). Cached Input 19 credits / 1M tokens (≈ $0.19), Cache Writes 237.5 credits / 1M tokens (≈ $2.375) — applied automatically when the upstream reports cached tokens for your prompt; there is no field to request them.
Save up to 65%with the $1,250 top-up pack (+10% bonus) — 62% lower than direct rates even without itTop up24H Status Monitor
OperationalTools
Web search feeds the results back as input tokens, so a searched turn typically costs many times a normal turn (measured: 18–87×). Billed per token as usual — nothing extra per search.
claude-opus-5, chat, Input
textAnthropic
claude-opus-5, chat, Output
textAnthropic
Claude Opus 5, Cache Writes
textAnthropic
Claude Opus 5, Cached Input
textAnthropic
Explore more LLM models
Kimi K3
Frontier coding, native vision, and 1M-token agents from Moonshot AI.

Gemini 3.6 Flash
Google's newest speed-optimized multimodal model — fast text, vision, and reasoning.

Gemini 3.7 Flash
Google's newest Flash model — a 1M-token context window and up to 65,536 tokens of output, at the same price as 3.6.

Gemini 3.8 Flash
Google's newest Flash model — a 1M-token context window and up to 65,536 tokens of output, at the same price as 3.7.

GPT-6 Astra
OpenAI's GPT-6 Astra — frontier reasoning with a 1M-token context window, served through one API.

GPT-5.6 Terra
GPT-5.6 — frontier reasoning and generation through one API.