Anthropic: Claude Haiku 5.5
anthropic/claude-haiku-5.5
Try Claude Haiku 5.5 for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "anthropic/claude-haiku-5.5"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "anthropic/claude-haiku-5.5"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Claude Haiku 5.5 is the small, low-cost model in Anthropic's 5.5 family, released on October 7, 2026 and available through the API as anthropic/claude-haiku-5.5. It has a 1M token context window and up to 128k output tokens. Pricing is $0.10 per million input tokens and $0.50 per million output tokens for requests under 100,000 tokens, down from $1 and $5 for Haiku 4.5, and $0.50 and $2.50 above that. Effort levels range from low to max, with medium as the default.
Anthropic reports 72.4% on OSWorld 2.1 (offline subset, Haiku 4.5: 15.7%) and 39.2% on Terminal-Bench 4.0 at maximum effort (Haiku 4.5: 0.0%). On the same tests GPT-6 Luna scores 48.9% and 16.4%.
It is aimed at summarizing documents, classifying information, querying databases, and handling subtasks for larger agents. Anthropic recommends Opus and Sonnet for demanding coding work.
Context Window 1M
tokens
Max Output 128K
tokens
Input Cost $0.1
per million tokens
Output Cost $0.5
per million tokens
Input text, image, pdf
modalities
Tool Use Yes
Release Date Oct 7, 2026
Output Speed 235
tokens / sec
Latency 333.79s
time to first token
Try Claude Haiku 5.5 for free
Try Claude Haiku 5.5 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Claude Haiku 5.5 performs on standard evaluations.
| Benchmark | Score |
|---|---|
| Humanity's Last Exam Cross-domain reasoning | 44.4% |
| SciCode Scientific programming | 55.0% |
| LCR Long-context reasoning | 82.7% |
Scores sourced from Artificial Analysis.
Find other Anthropic models →
Claude Sonnet 5.5
Claude Sonnet 5.5 is a mid-tier model from Anthropic, released on September 28, 2026 and available through the API as anthropic/claude-sonnet-5-5. It accepts text, image, and PDF input, with a 1M token context window and up to 128k output tokens. Pricing is $2 per million input tokens and $10 per million output tokens, the same as Claude Sonnet 5. Anthropic says it generates output more than 30% faster than Sonnet 5 and can cut the cost of a task by up to 30%, because it uses fewer tokens and fewer tool calls. Anthropic reports 70.6% on Terminal-Bench 4.0 (Sonnet 5: 10.3%) and 80.1% on OSWorld 2.1 (Sonnet 5: 57.0%). It is aimed at well-scoped everyday tasks, bug fixing, agentic coding, and producing documents, slides, and spreadsheets.
ChatClaude Opus 5.5
Claude Opus 5.5 is Anthropic's newest flagship model, released September 22, 2026 as the successor to Claude Opus 5. Anthropic positions it for agentic coding and long-running autonomous work. Reported benchmark scores include 66.4% on Terminal-Bench 4.0 (up from 52.3% for Opus 5), 54.4% on FrontierCode, 40% on AutomationBench (up from 26.9%), 81.8% on the OSWorld 2.0 computer-use benchmark, and 67.7% on Humanity's Last Exam with tools. It runs about 30% faster than Opus 5 and costs roughly 40% less on typical workloads, at $4 per million input tokens and $20 per million output tokens, a 1M-token context window, and 128K max output tokens. That combination of long-horizon coding performance, multimodal input (text, image, PDF), tool calling, and lower cost makes it a fit for developers building coding agents, codebase-wide migrations, and research or analysis pipelines through the API.
ChatClaude Fable 5.1
Claude Fable 5.1 is Anthropic's successor to Claude Fable 5, released September 1, 2026, about three months after Fable 5. Anthropic also released a companion model, Claude Mythos 5.1, available only through trusted access programs; both share the same underlying model with different safety safeguards. On SWE-bench Pro it scores 81.2%, ahead of Fable 5's 80% and Mythos 5's 80.3%. On Terminal-Bench-Science, a scientific-research agentic benchmark, it reaches 52.6%, more than double Fable 5's 24.7% and ahead of GPT-5.6 Sol's 22.4%. On Terminal-Bench 4.0 for agentic coding it scores 55.8%, versus 42.0% for Fable 5 and 37.3% for GPT-5.6 Sol. Priced at $10/$50 per million input/output tokens, unchanged from Fable 5, with cache reads cut 75% to $0.25 per million tokens. It offers a 1,000,000-token context window, 128,000-token max output, and tool calling. It fits developers running long-horizon agentic coding and research pipelines who want Fable-tier reasoning at lower cost.
Frequently Asked Questions
You can access Claude Haiku 5.5 by Anthropic through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Claude Haiku 5.5 is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
Claude Haiku 5.5 is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.1 |
| Output | $0.5 |
Claude Haiku 5.5 was created by Anthropic and released on Oct 7, 2026.
Claude Haiku 5.5 supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,000 pages of text.
Claude Haiku 5.5 can generate up to 128K tokens in a single response.
Claude Haiku 5.5 accepts the following input types: text, image, pdf. It produces: text.
Yes, Claude Haiku 5.5 supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Claude Haiku 5.5 scores 43.4 on the Artificial Analysis Intelligence Index, outperforming 93% of tracked models.
Yes — the Claude Haiku 5.5 API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add Claude Haiku 5.5 to your app for free
Developers can integrate Claude Haiku 5.5 for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.