Claude Haiku 5.5 is Anthropic's smallest and fastest model in the Claude 5.5 family, released on October 7, 2026.
Start a free chat in three steps. No sign up, no credit card.
Write your question in the chat box at the top of the page.
It is already selected on this page. Switch models any time from the menu.
Then keep going. Ask more, upload a file or make an image.
ForFreeAI gives you 100k free tokens that reset every day, so you can use Claude Haiku 5.5 free on our platform. It is funded by ads.
Built for speed, with replies at up to 235 tokens per second.
Works across very long documents and chats in one go.
Pulls names, numbers and key details out of text.
One of the cheapest models to run, and free on ForFreeAI.
Features
Claude Haiku 5.5 is best for summarizing long files, sorting large amounts of text and reading charts. It holds 1M tokens of context and replies at up to 235 tokens per second. It also scores 46.4% on Chartography, up from 6.4% for Haiku 4.5.
Turn long reports, PDFs and email threads into short summaries. No need to split them up.
Try it
Label reviews, tickets or messages in bulk. The same rules apply every time.
Try it
Explain what a chart, table or screenshot shows.
Try it
Independent benchmark results for intelligence, speed and price, compared with similar models.
Artificial Analysis · max effort · higher is better
Tokens per second · max effort · higher is better
USD per 1M tokens · lower is better
USD per 1M tokens · lower is better
Artificial Analysis Intelligence Index · higher is better
Medium is the default effort. Higher effort scores better but writes more tokens per answer.
Source: Artificial Analysis, Intelligence Index v4.3.2. Data checked October 22, 2026.
From this analysis, Claude Haiku 5.5 is less suited for large coding projects. It scored 39.2% on Terminal-Bench 4.0 against 70.6% for Claude Sonnet 5.5, so pick a larger model in the menu for complex code.
Launch results compared with Claude Haiku 4.5, GPT-6 Luna and Claude Sonnet 5.5.
| Knowledge work | Computer use | Reasoning | Agentic coding | Visual reasoning | ||||
|---|---|---|---|---|---|---|---|---|
| GDPval-AA v2.1 | AA-Briefcase v1.1 | OSWorld 2.1 | HLE, no tools | HLE, with tools | Terminal-Bench 4.0 | FrontierCode 1.1 | Chartography | |
| 1620 | 1578 | 72.4% | 45.9% | 57.4% | 39.2% | 46.4% | 46.4% | |
| 735 | — | 15.7% | 10.2% | 18.7% | 0.0% | — | 6.4% | |
| 1437 | — | 48.9% | — | — | 16.4% | 42.4% | — | |
| 1840 | — | 83.9% | 56.9% | 64.5% | 70.6% | 52.1% | — | |
Max effort results from Anthropic's launch table. GDPval-AA and AA-Briefcase are Elo ratings run by Artificial Analysis. HLE is Humanity's Last Exam. A dash means no published score.
API prices per 1 million tokens.
Per 1M tokens.
| ≤ 100K prompt | > 100K prompt | |
|---|---|---|
| Input | $0.10 | $0.50 |
| Output | $0.50 | $2.50 |
| Cache read | $0.01 | $0.05 |
| Batch input | $0.05 | $0.25 |
| Batch output | $0.25 | $1.25 |
Standard API price per 1M tokens.
| Model | Input | Output | Context |
|---|---|---|---|
| $0.10 | $0.50 | 1M | |
| $0.10 | $0.50 | 1.05M | |
| $0.30 | $2.50 | 1.05M | |
| $1.00 | $5.00 | 200K | |
| $2.00 | $10.00 | 1M |
Try other models for better performance.
Best for
Fast everyday answers, emails and short writing.
Best for
Research, fact finding and working with images.
Best for
Multilingual chat, translation and coding.
Best for
Reading and analyzing long documents and PDFs.
ForFreeAI gives you 100k free tokens, and you can claim more as many times as you like. So in the end, you can chat with Claude Haiku 5.5 without limits.
Every day starts with 100,000 tokens. Just type and chat, nothing to fill in.
When your tokens run out, claim another 100k for free. Share ForFreeAI and you get 500k.
Claim as often as you need, so you can keep chatting with Claude Haiku 5.5 for free.
Common questions about Claude Haiku 5.5.
Yes. You can chat with Claude Haiku 5.5 free on ForFreeAI and claim 100,000 tokens every day, with no sign up and no credit card.
Claude Haiku 5.5 is Anthropic's smallest and fastest model in the Claude 5.5 family. It reads text and images and replies in text.
Anthropic released Claude Haiku 5.5 on October 7, 2026.
On the Anthropic API it costs $0.10 per 1M input tokens and $0.50 per 1M output tokens for prompts up to 100K tokens, and $0.50 and $2.50 above that. On ForFreeAI it is free.
Claude Haiku 5.5 has a 1 million token context window and can write up to 128K tokens in one answer.
Both have the same API price. Claude Haiku 5.5 scored 43 on the Artificial Analysis Intelligence Index against 38 for GPT-6 Luna, and ran at about 235 tokens per second against 122.
No. ForFreeAI connects to the model for you, so you only need to type your message.
Last updated October 22, 2026
Share ForFreeAI on social media and get 500,000 more tokens to keep chatting.
Tokens are an estimate kept in this browser.
Your balance: 100,000 tokens. It shows on the left once you start a chat.
Tell us if this AI content is offensive, harmful or wrong. We review every report and use it to improve our filters.