CheckPre

Claude Opus 5.5 vs Claude Opus 5 API Cost

What moving from Claude Opus 5 to Opus 5.5 saves: 20% off input and output, and 60% off cache hits, on your own workload.

Updated · By Niraj Kumar · 6 sources

Models

Each request

Count text inCount text in
tokens

System prompt, conversation history, documents and tool definitions are all resent on every call.

tokens

The visible answer.

Count tokens from a prompt or JSON payloadShow

Plain text, OpenAI Chat or Responses JSON, or Anthropic Messages JSON. A final assistant message or a response body counts as output. Counted in your browser; nothing is uploaded.

Loading the tokenizer…

Counts use OpenAI's o200k tokenizer, so they are exact for GPT-6 and GPT-5 models, plus a few tokens of message framing. Other providers' tokenizers count the same text differently and do not publish a conversion factor; Anthropic says Claude models from 4.7 on produce about 30% more tokens than earlier Claude models. For an exact count on another model, paste one of its API responses: the usage it reports is shown above.

tokens

Thinking tokens are billed as output. Leave at 0 for models or settings that do not reason.

Volume

PricePrice

30,000 requests over 30 days.

Discounts

%
0%100%

The share of input that repeats exactly at the start of every request, such as a fixed system prompt. The prompt caching calculator prices cache writes and expiry in detail.

Batch APIBatch API
Cheaper for this workloadClaude Opus 5.520% less, saving $165.00 a month
Claude Opus 5.5
$660.00 a month
$0.022 a request · 20th cheapest of 24
Claude Opus 5
$825.00 a month
$0.0275 a request · 22nd cheapest of 24
At 10× the volume
$1,650 a month apart
Cheapest listed model
Claude Haiku 5.5
$16.50 a month
Side by side
MeasureClaude Opus 5.5Claude Opus 5
Input, per 1M tokens$4$5
Cache hit, per 1M tokens$0.20$0.50
Output, per 1M tokens$20$25
Context window1M tokens1M tokens
Max output128K tokens128K tokens
Batch discount50%50%
Long-context surchargeNoneNone
Input cost a month$360.00$450.00
Output cost a month$300.00$375.00
Every model on this workload, per month3,000 tokens in, 500 out, 1,000 a day. Hover or focus a row for rates.
  1. 1Claude Haiku 5.5Anthropic$16.50
  2. 2GPT-6 LunaOpenAI$16.50
  3. 3Qwen3.8 FlashAlibaba$20.55
  4. 4GPT-5.6 LunaOpenAI$36.00
  5. 5DeepSeek V4.1 FlashDeepSeek$45.00
  6. 6Qwen3.7 PlusAlibaba$60.00
  7. 7Gemini 3.5 Flash-LiteGoogle$64.50
  8. 8Gemini 3.8 FlashGoogle$123.75
  9. 9Grok 4.3xAI$150.00
  10. 10Claude Haiku 4.5Anthropic$165.00
  11. 11DeepSeek V4 ProDeepSeek$178.20
  12. 12Grok 4.7xAI$270.00
  13. 13Qwen3.8 MaxAlibaba$270.00
  14. 14Claude Sonnet 5.5Anthropic$330.00
  15. 15Claude Sonnet 5Anthropic$330.00
  16. 16GPT-6.1 SolOpenAI$330.00
  17. 17GPT-6 SolOpenAI$330.00
  18. 18GPT-5.6 TerraOpenAI$360.00
  19. 19Gemini 3.1 ProGoogle$360.00
  20. 20Claude Opus 5.5Anthropic$660.00
  21. 21GPT-5.6 SolOpenAI$660.00
  22. 22Claude Opus 5Anthropic$825.00
  23. 23Claude Fable 5.1Anthropic$1,650
  24. 24GPT-6 AstraOpenAI$1,650

How the Claude Opus 5.5 vs Claude Opus 5 API Cost works

cost = (fresh input × input rate + cached input × cache rate + (output + reasoning) × output rate) ÷ 1,000,000

This page uses the same method as the LLM API Cost Calculator, which explains each term and assumption in full.

Worked example

A chat feature sending 3,000 input tokens and getting 500 back, 1,000 times a day, priced on both models with no caching.

  1. 1Claude Opus 5.5: 3,000 × $4 + 500 × $20, ÷ 1,000,000 = $0.022 a request, $660.00 a month
  2. 2Claude Opus 5: 3,000 × $5 + 500 × $25, ÷ 1,000,000 = $0.0275 a request, $825.00 a month
  3. 3Difference: $165.00 a month

Claude Opus 5.5 is $165.00 a month cheaper for this workload, 20% less.

Frequently asked questions

Which is cheaper, Claude Opus 5.5 or Claude Opus 5?

At standard list rates, Claude Opus 5.5 is 20% cheaper than Claude Opus 5 on a typical chat request (3,000 tokens in, 500 out); Claude Opus 5.5 is 20% cheaper than Claude Opus 5 on output-heavy generation (500 in, 2,000 out); and Claude Opus 5.5 is 31% cheaper than Claude Opus 5 on a large cached prompt (20,000 in, 90% cached, 500 out). Claude Opus 5.5 charges $4 input and $20 output per million tokens; Claude Opus 5 charges $5 and $25.

Is Opus 5.5 a drop-in replacement for Opus 5?

On price it is simply cheaper: $4 and $20 against $5 and $25, with cache hits at $0.20 against $0.50 and the same tokenizer. On the API it is not a pure swap. Anthropic lists changes on Opus 5.5, including thinking that cannot be disabled and a lower default effort, so run your prompts through it and read the migration notes first.

Sources

Related calculators

More in AI, Cloud & Developer