Model · Claude
Claude Haiku 5.5: price, limits and messages on every plan
Anthropic's Claude Haiku 5.5 in llmwise: how many Claude Haiku 5.5 messages each plan gives, what counts against them, what Claude Haiku 5.5 reads, where your messages go, and what it costs at Anthropic's API prices.
Prices and limits checked against OpenRouter's Claude Haiku 5.5 page. Updated .
Short answer
Claude Haiku 5.5 is in llmwise's one-time free trial of 5 messages. As an everyday model it has a daily count: 60 Claude Haiku 5.5 messages a day on Pro ($20), 120 on Max ($50), 200 on Ultra ($100) and 200 on Studio ($200), refilled every day at 00:00 UTC. Each Claude Haiku 5.5 message's price is shown before you send it.
In the news: Claude Haiku 5.5 is out: what changed, and what it costs you ().
What Anthropic announced, sourced on its launch page:
- Anthropic calls Haiku 5.5 the cheapest, fastest and most capable small model it has released, built for high-volume work such as summaries, classification, subagents and browser use.
- A prompt of over 100,000 tokens costs more: $0.50 per million input tokens and $2.50 per million output. Anthropic says about 90% of requests to Haiku 4.5 were shorter than that.
- Cache reads cost $0.01 per million tokens and cache writes $0.125 per million on prompts up to 100,000 tokens, a tenth of Haiku 4.5's.
Claude Haiku 5.5 on every plan
What Claude Haiku 5.5 costs in llmwise is a count, not a token bill: 60 a day on Pro, and it's one of the models in the 5-message free trial.
| Plan | Price | Claude Haiku 5.5 messages |
|---|---|---|
| Free | $0 | In the one-time trial of 5 messages |
| Pro | $20 a month | 60 a day |
| Max | $50 a month | 120 a day |
| Ultra | $100 a month | 200 a day |
| Studio | $200 a month | 200 a day |
Prices don't include tax, which is added where it applies and shown before you pay. Claude Haiku 5.5 is an everyday model: its count is a day's, refilled at 00:00 UTC, and it doesn't touch the monthly allowance the other models share. How pricing works.
Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Pro $7.50, Max $20, Ultra $42, Studio $85. Using every message on your plan at typical sizes stays under it; very large messages and heavy research use it faster. Every limit, explained.
Claude Haiku 5.5 usage limits, explained
Every limit on Claude Haiku 5.5 in llmwise is published. Here's each one, in Claude Haiku 5.5 messages.
Claude Haiku 5.5 has a daily count on every paid plan: 60 Claude Haiku 5.5 messages on Pro, 120 Claude Haiku 5.5 messages on Max, 200 Claude Haiku 5.5 messages on Ultra, 200 Claude Haiku 5.5 messages on Studio. The Claude Haiku 5.5 count refills at 00:00 UTC, and yesterday's unused Claude Haiku 5.5 messages don't carry over.
Long Claude Haiku 5.5 chats count more, because each Claude Haiku 5.5 reply resends the whole conversation. Past 64k tokens a Claude Haiku 5.5 reply counts as 2 messages, so Pro's 60 Claude Haiku 5.5 messages become up to 30 such replies; past 128k it counts as 4 (up to 15 Claude Haiku 5.5 replies); past 200k the Claude Haiku 5.5 chat is full.
Claude Haiku 5.5's native context window is 1M tokens; llmwise stops a Claude Haiku 5.5 chat at 200k tokens, so a Claude Haiku 5.5 chat uses at most 200k of its 1M tokens.
A Claude Haiku 5.5 reply can run to 8,000 tokens on Pro and 16,000 on Max, Ultra, and Studio, at the same Claude Haiku 5.5 price however long it runs.
On a paid plan each web search or link read in a Claude Haiku 5.5 reply counts as 1 Claude Haiku 4.5 message.
A $10 top-up adds to the monthly allowance, not to Claude Haiku 5.5's daily count of 60 on Pro.
Claude Haiku 5.5 replies share every plan's soft cap of 100 replies an hour with the other models.
What Claude Haiku 5.5 reads and does
| Made by | Anthropic |
|---|---|
| Model at OpenRouter | anthropic/claude-haiku-5.5 |
| Context window | 1M tokens |
| Longest chat in llmwise | 200k tokens |
| Images you attach | Reads them |
| PDFs you attach | Reads the whole file, charts and layout included |
| Tools (search, documents, code, apps) | Yes |
| Reasoning | On, at low effort |
| API price, per million tokens | $0.10 in, $0.50 out (the rate for prompts up to 100K tokens; $0.50 / $2.50 a million over that) |
| A typical message at API prices | $0.0008 |
| On Pro | 60 a day |
Where your Claude Haiku 5.5 messages go
A Claude Haiku 5.5 message goes to Anthropic directly when llmwise can reach Anthropic, or through OpenRouter when it can't.
If Anthropic fails before a Claude Haiku 5.5 reply starts (an overload, a server error, a dropped connection), llmwise resends the Claude Haiku 5.5 request through OpenRouter, to endpoints that, according to OpenRouter, don't store prompts for their own use or train on them.
The Privacy Policy lists every company a Claude Haiku 5.5 message can reach.
Claude Haiku 5.5's API price, and what a message costs
Claude Haiku 5.5's API price is $0.10 per million tokens in and $0.50 out: Anthropic's list price, the rate for prompts up to 100K tokens; $0.50 / $2.50 a million over that. At that price a typical Claude Haiku 5.5 message (4,000 tokens in, 700 out) costs about $0.0008.
In llmwise a Claude Haiku 5.5 message isn't billed by the token: it's one of 60 Claude Haiku 5.5 messages a day on Pro, however long the Claude Haiku 5.5 reply runs.
What Claude Haiku 5.5's replies cost in our test runs, job by job, and Claude Haiku 5.5 beside the rest of its family: Claude Haiku 5.5 pricing: API price, cost per message and plans.
When to use Claude Haiku 5.5, and when a cheaper model will do
llmwise's catalog describes Claude Haiku 5.5 as “Newest Haiku, fast and low-cost, with thinking”. No benchmark scores here: ask Claude Haiku 5.5 your own question, then switch the picker to another model in the same chat, which sees Claude Haiku 5.5's answer too.
Claude Haiku 5.5 is an everyday model, so nothing in llmwise costs less: its 60 messages a day on Pro come on top of the monthly allowance.
Same count as Claude Haiku 5.5 on every plan: GPT-6 Luna, DeepSeek V4.1 Flash and GLM 5.3 Flash.
Claude Haiku 5.5 in our test runs
Claude Haiku 5.5 passed 45 of our 50 test prompts, sent through llmwise's own pipeline and checked the same way for every model.
- Coding5 of 5 passed
- Writing3 of 5 passed
- Math5 of 5 passed
- Summarization3 of 5 passed
- Data analysis5 of 5 passed
- Customer support4 of 5 passed
- Translation5 of 5 passed
- SQL5 of 5 passed
- RAG and answering from documents5 of 5 passed
- Agents and tool use5 of 5 passed
How Claude Haiku 5.5 began its reply to our first writing prompt, “Write a LinkedIn post of 100 to 150 words announcing that our small bakery, Crumb & Co., opens a second shop in Leeds on 14 November. Mention the free coffee…”:
Big news from Crumb & Co.: we're opening a second shop in Leeds on 14 November! When we started, we had one oven, a handful of loyal regulars, and a dream of making bread that people look forward to. Those regulars told their friends, and now we're ready to share the same warm loaves, slow-proved pastries, and morning buns with a whole new neighbourhood. To celebrate, every customer on opening day gets a free coffee. Come in, say hello, and let us make you a cup. Thank you to everyone who has supported us so far. We couldn't have done this without you, and we can't wait to see you in Leeds. See you on the 14th.
Questions
Is Claude Haiku 5.5 free in llmwise?
Claude Haiku 5.5 is in llmwise's one-time free trial of 5 messages, with no card. After that it needs a paid plan: Pro ($20 a month) gets 60 Claude Haiku 5.5 messages a day.
What are Claude Haiku 5.5's usage limits in llmwise?
Claude Haiku 5.5 has a published daily count on each paid plan (60 Claude Haiku 5.5 messages a day on Pro), refilled at 00:00 UTC. A long Claude Haiku 5.5 chat counts each reply as 2 Claude Haiku 5.5 messages past 64k tokens and 4 past 128k.
What happens when my Claude Haiku 5.5 messages run out?
Your 60 Claude Haiku 5.5 messages come back at 00:00 UTC. Until then, the models on the monthly allowance keep answering.
How much context does Claude Haiku 5.5 have in llmwise?
1M tokens is Claude Haiku 5.5's native context window. A Claude Haiku 5.5 chat in llmwise stops at 200k tokens, and past 64k each Claude Haiku 5.5 reply counts as more than one message, so a new Claude Haiku 5.5 chat for each new task goes further.
Claude, GPT, Gemini, DeepSeek, Grok, Kimi, and GLM, in one chat.
See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.