Anthropic

Claude Opus 4

anthropic/claude-opus-4

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Claude Opus 4

reasoning tools

Anthropic anthropic/claude-opus-4

Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...

Input $/1M: $15.0
Output $/1M: $75.0
Context: 200K
Max output: 32K
Released: May 22, 2025
Modalities: imagetextfile

Cached input reads $1.50 per 1M

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Claude Opus 4
targets:
  - id: claude-opus-4
    kind: llm
    name: Claude Opus 4
    metadata:
      model: anthropic/claude-opus-4          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 200000
    cost:
      usd_per_1k_tokens: 0.045000

Price among Anthropic models

Input list price per million tokens; Claude Opus 4 is the most expensive of 13 listed.

More from Anthropic

Other models by the same vendor in the catalogue.