claude-opus-4-6 — API, Pricing & Context Window | Vivgrid

claude-opus-4-6 is a high-end Anthropic Opus model built for demanding coding and reasoning tasks. With a 1M-token context window and the Messages API, it excels at understanding large codebases and producing careful, well-structured edits.

Vivgrid accelerates claude-opus-4-6 across AMER and EMEA, so agent workloads get consistent, low-latency performance through one API key and billing surface.

Specifications

Pricing

Pricing in USD per 1M tokens.

What one request costs

The rates above applied to a 20K-token prompt with a 2K-token reply — a typical single agent turn, small enough that every request is billed at the base rate.

API surfaces

The Vivgrid Console catalogs claude-opus-4-6 on one surface, all behind the same API key. The endpoint shown is the one the Console previews for that surface.

Quick start

Get an API key from the Vivgrid Console, then call claude-opus-4-6 directly.

curl https://api.vivgrid.com/v1/messages \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-6",
    "max_tokens": 1024,
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'

Ideal use cases

• Agentic coding and whole-repository refactors
• Careful reasoning over long documents and specs
• Tool-calling agents needing dependable structured output
• Workloads that value Claude's writing and analysis quality

Related models

• gpt-6-astra — OpenAI's frontier gpt-6 coding model
• claude-opus-5-5 — the latest Opus release
• claude-sonnet-4-6 — faster, cheaper sibling