• featured
claude-opus-4-5 Robot

claude-opus-4-5

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high. Opus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.

Input Balance $4.25 / 1M tokens, Output Cost $21.25 / 1M tokens

Input

No template available.
You can add a prompt template in the admin panel.

Output

Anthropic Claude 4.5 Opus Documentation

Claude 4.5 Opus is built for complex multi-agent setups, autonomous research, and multi-step planning tasks. It features improved robustness to prompt injections, enhanced tool-use execution, and a dedicated verbosity parameter that allows developers to optimize token overhead based on task requirements.

Key Capabilities

  • Long-Horizon Computer Use: Specially optimized to handle complex spreadsheet and browser manipulation tasks natively.
  • Dynamic Effort & Verbosity: Supports granular control over generation depth (low, medium, high verbosity) to manage token usage and latency.
  • Advanced Tool Use & Multi-Agent Coordination: Designed to serve as the central orchestrator in complex, multi-agent frameworks.
  • High Prompt Injection Robustness: Built with enhanced safety alignments to handle untrusted third-party data or logs securely.
  • Structured Reasoning: Delivers near-zero deviation when executing strict code refactoring, structural debugging, and technical planning.

Request Parameters

To interact with this model via an OpenAI-compatible gateway or OpenRouter endpoint:

Parameter Type Required Description
model string Yes Use "claude-opus-4.5" or "anthropic/claude-4.5-opus".
messages array Yes Array of standard conversation objects (role/content).
max_tokens integer No Limits the generation length. Supports extended outputs.
temperature float No Recommended: 0.0 for code/logic; 0.5 for planning.
extra_body object No Pass provider-specific flags like OpenRouter's verbosity.

Extended Thinking Configuration

claude-opus-4-5 uses the legacy extended thinking format with budget_tokens. Newer models use "type": "adaptive" instead.

Important Constraints

  • budget_tokens must be strictly less than max_tokens (minimum value: 1024).
  • If thinking is enabled, temperature must be 1.0 (or omitted).

Request Example

json Copy 
{
  "model": "claude-opus-4-5",
  "max_tokens": 16000,
  "thinking": {
    "type": "enabled",
    "budget_tokens": 8000
  },
  "messages": [
    {
      "role": "user",
      "content": "Your question here"
    }
  ]
}

Tip: Increase budget_tokens for harder problems. A common starting point is 25–50% of max_tokens.

Unlock the most affordable AI hosting

Run models at scale with our fully managed GPU infrastructure, delivering enterprise-grade uptime at the industry's best rates.

Contact Sales