Claude API pricing › Opus 5.5 vs Sonnet 5.5

Claude Opus 5.5 vs Claude Sonnet 5.5: price comparison

Prices in USD per million tokens, checked against the official Claude pricing page on 2026-11-10.

Opus 5.5 costs 2× as much as Sonnet 5.5 for input tokens and 2× as much for output tokens. Here is what that difference looks like on real workloads.

Prices per million tokens

ItemOpus 5.5Sonnet 5.5
Input$4$2
Output$20$10
Cache write, 5 minutes$5$2.5
Cache write, 1 hour$8$4
Cache read$0.2$0.1
Batch API input$2$1
Batch API output$10$5

Model ids: claude-opus-5-5 and claude-sonnet-5-5.

The gap on real workloads

WorkloadOpus 5.5Sonnet 5.5Difference
Chatbot, per message$0.011$0.0057$0.0057
Support bot, per ticket$0.094$0.047$0.047
Coding agent, per task$1.27$0.637$0.637
Document Q&A (RAG), per question$0.034$0.017$0.017
Document summarization, per document$0.140$0.070$0.070
Classification & extraction, per item$0.0048$0.0024$0.0024

With prompt caching. Each workload links to its assumptions (tokens per call, calls per task).

How to decide

  • Measure, do not guess: run 50 to 200 of your real requests through both models and score the answers. Our guide to evals for Claude agents shows a small setup.
  • Route by request: send routine requests to Sonnet 5.5 and hand only the hard ones to Opus 5.5. Even a 70/30 split cuts most of the gap.
  • Cache first: prompt caching often saves more than a model switch on agent and chat workloads.

Questions

Is Sonnet 5.5 cheaper than Opus 5.5?

Yes. Sonnet 5.5 costs $2 input / $10 output per million tokens, against $4 / $20 for Opus 5.5: 2× cheaper on input and 2× cheaper on output.

How much more does Opus 5.5 cost than Sonnet 5.5 per month?

For a chatbot with 1,000 active users (300 messages each, with caching), about $1,695 more per month on Opus 5.5. The worked examples on this page show the gap for other workloads.

Should I use Opus 5.5 or Sonnet 5.5?

Price is only half the answer. Run the same set of real tasks through both (a small eval of 50 to 200 examples is enough) and use Sonnet 5.5 wherever it passes. Many apps route most requests to the cheaper model and send only hard ones to Opus 5.5.

Other comparisons: Fable 5.2 vs Opus 5.5 · Fable 5.2 vs Sonnet 5.5 · Fable 5.2 vs Haiku 5.5 · Opus 5.5 vs Haiku 5.5 · Sonnet 5.5 vs Haiku 5.5

Run your own numbers. The free Claude API cost calculator works out cost per request, per user and per month, and the Claude Pricing MCP server lets Claude, Cursor or any MCP client answer the same questions inside your editor.

Building a Claude-powered SaaS? Agentwright Starter records token usage per user and turns it into dollars with this same price table.