Model comparison
Claude Haiku 5.5 vs Claude Sonnet 5.5: pricing, context and features compared
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; Claude Sonnet 5.5 costs $2 and $10. Here is how they compare on specs, on what real workloads cost, and on which to pick for what, from prices updated daily.
Haiku is Anthropic’s small model and Sonnet the everyday one. Many apps use both: Haiku for simple, frequent calls and Sonnet where the answer needs more thought.
- Input / 1M
- $0.10
- Output / 1M
- $0.50
- Context
- 1,000,000
- Max output
- 128,000
- Input / 1M
- $2
- Output / 1M
- $10
- Context
- 1,000,000
- Max output
- 128,000
Verdict
Claude Haiku 5.5 or Claude Sonnet 5.5: which to pick
Claude Haiku 5.5 has the lower list prices: 20× cheaper per input token and 20× per output token. On our data, Claude Haiku 5.5 has the edge for the lowest bill, very long prompts, repeated prompts and batch jobs, and Claude Sonnet 5.5 has no measurable edge; its case rests on answer quality, so choose it only if it does clearly better in your own tests. For scale, a support chatbot handling 1,000 requests a day costs about $8.59 a month on Claude Haiku 5.5 and $169.57 on Claude Sonnet 5.5.
- Lowest bill for typical workloadsPick Claude Haiku 5.5
- Claude Haiku 5.5 costs less on all 4 workloads below, 18× to 20× cheaper than Claude Sonnet 5.5 at list prices.
- Very long prompts (whole codebases, long documents)Pick Claude Haiku 5.5
- Both read about 1,000,000 tokens per request. One 800,000-token prompt with a 2,000-token reply costs $0.41 on Claude Haiku 5.5 and $1.62 on Claude Sonnet 5.5. Claude Haiku 5.5 charges $0.50 / $2.50 per 1M once a prompt passes 100,000 tokens.
- Long replies (reports, large code files)Either
- Both cap a single reply at about 128,000 tokens.
- Images, audio, video or files in the promptEither
- Both accept images and files as well as text.
- Repeated long prompts (prompt caching)Pick Claude Haiku 5.5
- Claude Haiku 5.5 bills cached input at $0.01 per 1M (10% of its input price), against $0.10 per 1M (5% of its input price) for Claude Sonnet 5.5.
- Overnight batch jobsPick Claude Haiku 5.5
- Both offer batch prices; on the document summariser workload Claude Haiku 5.5 costs $5.02 a month against $100.38.
- Self-hosting or choosing your own hostEither
- Neither has downloadable weights: both are only available through their provider’s API and cloud partners.
Criteria use only list prices, published limits and the features each provider declares. We don’t rank answer quality; test both models on your own prompts before you commit.
Specs
Claude Haiku 5.5 vs Claude Sonnet 5.5 side by side
| Spec | Claude Haiku 5.5 | Claude Sonnet 5.5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Input / 1M tokens | $0.10 (better) | $2 |
| Output / 1M tokens | $0.50 (better) | $10 |
| Cached input / 1M | $0.01 (better) | $0.10 |
| Cache write / 1M | $0.125 | $2.50 |
| Batch in / out | $0.05 / $0.25 (better) | $1 / $5 |
| Long-prompt price | $0.50 / $2.50 over 100,000 | None |
| Context window | 1,000,000 | 1,000,000 |
| Max output | 128,000 | 128,000 |
| Accepts | text, images, files | text, images, files |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
| Prompt caching | Yes | Yes |
| Structured output | Yes | Yes |
| Open weights | No | No |
| Knowledge cutoff | Not published | Not published |
| First listed | 2026-10-07 | 2026-09-28 |
Prices in US dollars per million tokens. Highlighted: the lower price or larger limit where the difference is over 5%. Features are as declared by each provider’s API; “First listed” is when our data source first listed the model. Long-prompt prices apply to the whole request once the prompt passes the threshold.
Costs
What Claude Haiku 5.5 and Claude Sonnet 5.5 cost for real workloads
| Workload | Tokens in / out | Requests/day | Claude Haiku 5.5 / month | Claude Sonnet 5.5 / month | Cheaper |
|---|---|---|---|---|---|
| Support chatbotCalculator: Claude Haiku 5.5 · Claude Sonnet 5.5 | 1,500 / 400 | 1,000 | $8.5950% cached | $169.5750% cached | Claude Haiku 5.5 (20×) |
| RAG appCalculator: Claude Haiku 5.5 · Claude Sonnet 5.5 | 6,000 / 500 | 500 | $11.2820% cached | $223.8720% cached | Claude Haiku 5.5 (20×) |
| Coding agentCalculator: Claude Haiku 5.5 · Claude Sonnet 5.5 | 40,000 / 2,000 | 200 | $12.9080% cached | $238.4780% cached | Claude Haiku 5.5 (18×) |
| Document summariserCalculator: Claude Haiku 5.5 · Claude Sonnet 5.5 | 8,000 / 600 | 300 | $5.02batch | $100.38batch | Claude Haiku 5.5 (20×) |
Each row uses the same token counts for both models and list prices, with caching and batch discounts only where the provider publishes them. A month is 365 ÷ 12 days. The support chatbot reads 50% of its prompt from the cache. The RAG app reads 20% of its prompt from the cache. The coding agent reads 80% of its prompt from the cache. The document summariser runs as a batch job where a batch price exists. Open either model in the LLM cost calculator to change any number.
Tokenizers
Are their per-token prices comparable?
Yes: Claude Haiku 5.5 and Claude Sonnet 5.5 use the same tokenizer, so a given text is the same number of tokens on both and the prices above compare directly.
| Model | Tokenizer | Tokens per 1,000 words | Output per 1M words |
|---|---|---|---|
| Claude Haiku 5.5 | Claude (Opus 4.7 and later)Provider’s published figure | 1,802 | $0.90 |
| Claude Sonnet 5.5 | Claude (Opus 4.7 and later)Provider’s published figure | 1,802 | $18.02 |
English prose, measured on the Universal Declaration of Human Rights (2026-10-11) or taken from the provider’s published words-per-token figure. Code, JSON and other languages use more tokens per word. Count your own text in the token counter or convert with tokens to words.
FAQ
Claude Haiku 5.5 vs Claude Sonnet 5.5 questions
Is Claude Haiku 5.5 cheaper than Claude Sonnet 5.5?
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; Claude Sonnet 5.5 costs $2 and $10. For a support chatbot handling 1,000 requests a day, that is about $8.59 a month on Claude Haiku 5.5 against $169.57 on Claude Sonnet 5.5, so Claude Haiku 5.5 is 20× cheaper there. Try your own numbers in the LLM cost calculator.
Which has the bigger context window, Claude Haiku 5.5 or Claude Sonnet 5.5?
Their context windows are about the same size. Claude Haiku 5.5 reads up to 1,000,000 tokens (roughly 750,000 English words) and writes up to 128,000 tokens per reply. Claude Sonnet 5.5 reads up to 1,000,000 tokens (roughly 750,000 English words) and writes up to 128,000 tokens per reply. The window is shared between your prompt and the reply. Word counts use a rough 0.75 words per token; real ratios depend on the tokenizer.
Is Claude Haiku 5.5 or Claude Sonnet 5.5 better for coding?
We don’t publish benchmark scores, so this page can’t say which writes better code. What we can show is cost: a coding agent re-sending 40,000 tokens of context (80% cached) and writing 2,000 tokens, 200 times a day, costs about $12.90 a month on Claude Haiku 5.5 and $238.47 on Claude Sonnet 5.5. Both support tool calling. Test both on tasks from your own repository.
Can Claude Haiku 5.5 and Claude Sonnet 5.5 read images?
Claude Haiku 5.5 accepts images and files as well as text. Claude Sonnet 5.5 accepts images and files as well as text. So both can read screenshots, photos and scanned pages. This is what each provider declares for its API, not a measure of how well it works.
Are Claude Haiku 5.5 and Claude Sonnet 5.5 open source?
No. Neither Claude Haiku 5.5 nor Claude Sonnet 5.5 has published weights: you can only use them through Anthropic’s API and their cloud partners. If you need a model you can host yourself, compare open-weight options in the model comparison table.
Do Claude Haiku 5.5 and Claude Sonnet 5.5 count tokens the same way?
Yes. Both use the same tokenizer (Claude (Opus 4.7 and later)), so the same text is the same number of tokens on each and their per-token prices compare directly: about 1,802 tokens per 1,000 English words (the provider’s published figure). Other languages and code use more tokens per word. Count your own text with the token counter or convert with tokens to words.