---
id: "anthropic/claude-opus-5"
also: ["anthropic/claude-opus-5-20260723", "requesty/anthropic/claude-opus-5", "vercel/anthropic/claude-opus-5"]
card_usd_per_m: "5.0 in, 25.0 out, at anthropic"
cheapest_list_usd_per_m: "5.0 in, 25.0 out, at amazon-bedrock on openrouter"
cheapest_effective_usd_per_m: "0.9064 in, 27.5 out, at bedrock@ap-northeast-1 on requesty"
context: 1000000
max_output: 128000
input: ["text", "image", "file"]
output: ["text"]
released: "2026-07-24"
reasoning: ["max", "xhigh", "high", "medium", "low", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "reasoning_effort", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity"]
endpoints: 28
gateways: "openrouter (12), requesty (12), vercel (4)"
no_training: 27
trains: 0
retains_prompts: 6
intelligence: 44.2000
coding: 78
agentic: 56.5000
---
# Anthropic: Claude Opus 5

Opus 5 is a workhorse model for agentic coding. It is strongest on difficult tasks, including
multi-file features, larger refactors, and end-to-end feature work. It also performs well on
easier tasks like single-turn edits, though the difference from prior models is smaller. Opus
5 completes full tasks rather than leaving stubs or placeholders.