anthropic·chat· vision

Claude Opus 4.6

anthropic/claude-opus-4.6

Anthropic's premium tier for the hardest reasoning and coding tasks.

At a glance

  • · $5.00 input / $25.00 output per 1M tokens (provider list price, billed in credits)
  • · Context window: 200,000 tokens
  • · OpenAI-compatible — model: "anthropic/claude-opus-4.6" (provider: anthropic)
  • · Best for: Highest hit rate on SWE-bench among closed-source models

Strengths

  • +Highest hit rate on SWE-bench among closed-source models
  • +Excellent at multi-day agentic tasks without drift
  • +Top performance on multi-repo code analysis

Weaknesses

  • Substantially pricier per token than Sonnet — rarely worth the markup
  • Higher latency, especially with extended thinking enabled

Use cases

  • Architecture reviews of large codebases
  • Autonomous agents on long, critical tasks (migrations, security audits)
  • Complex scientific analysis with chained reasoning

Not the right pick for

  • ×Routine coding and chat — Sonnet is cheaper and nearly tied

Benchmarks

TestScoreSource
SWE-bench Verified79.4%www.anthropic.com

Alternatives in the catalog

How to call it

Drop-in OpenAI-compatible. Just swap the `model` string and you're using this model.

curl https://www.getmorecredits.com/v1/chat/completions \
  -H "Authorization: Bearer $GMC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4.6",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Good for

Frequently asked questions

How much does Claude Opus 4.6 cost?

Input is $5.00 per million tokens; output is $25.00 per million tokens — provider list price. On getmorecredits.com you pay in credits, no subscription, no minimum spend.

What's the context window of Claude Opus 4.6?

Claude Opus 4.6 accepts up to 200,000 input tokens, with a maximum of 32,000 output tokens per response. That fits whole code repos or book-length documents into a single call.

What can Claude Opus 4.6 do?

Claude Opus 4.6 supports image input (vision), tool calling, structured output, reasoning mode. Anthropic's premium tier for the hardest reasoning and coding tasks.

Is Claude Opus 4.6 OpenAI-compatible?

Yes. On getmorecredits.com you call Claude Opus 4.6 with the same request shape as OpenAI: POST /v1/chat/completions with "model": "anthropic/claude-opus-4.6". Existing OpenAI SDKs (Python, Node, etc.) work by changing the base URL and API key.