Guide · Claude

How to use Claude: through the API, or in a chat

There are two ways to use Claude: call it from your own code through Anthropic's API, or talk to it in a chat. llmwise is the second kind. Here's how to choose, which Claude model to use for what, and how to get the most from Claude in a chat.

Start free See pricing

The API or a chat?

Use the API when
You're building software that calls Claude: an app, a script, a pipeline, an agent that runs on its own. You'll need an account with Anthropic (or a cloud platform that offers Claude), and its documentation is the place to start. llmwise can't help there: it isn't an API.
Use a chat when
You want Claude's help with your own work: writing, reading documents, analysing data, code you're working on. A chat needs no code and no setup, and in llmwise a message has a fixed price you see before you send.

Which Claude model to use

Each Claude model in llmwise, dearest first, with what a message uses and its API price from our catalog.

Claude Fable 5.1 (31 messages a month on Pro) — Anthropic's most capable model for the hardest problems.
Claude Opus 5.5 (62 messages a month on Pro) — Deep reasoning for complex work.
Claude Sonnet 5.5 (125 messages a month on Pro) — Newest Sonnet, for coding, documents and everyday work.
Claude Sonnet 5 (125 messages a month on Pro) — Fast, smart all-rounder for writing and reasoning.
Claude Haiku 4.5 (250 messages a month on Pro) — Quick answers at low cost.
Claude Haiku 5.5 (60 messages a day on Pro) — Newest Haiku, fast and low-cost, with thinking.

Claude models in llmwise
Model	On Pro	On Free	Context window	Images	PDFs	Reasoning	API price per 1M, in / out
Claude Fable 5.1Anthropic	31/mo on Pro	No	1M tokens	Yes	Whole file	Yes	$10.00 / $50.00
Claude Opus 5.5Anthropic	62/mo on Pro	1 message	1M tokens	Yes	Whole file	Yes	$4.00 / $20.00
Claude Sonnet 5.5Anthropic	125/mo on Pro	Yes	1M tokens	Yes	Whole file	Yes	$2.00 / $10.00
Claude Sonnet 5Anthropic	125/mo on Pro	Yes	1M tokens	Yes	Whole file	Yes	$2.00 / $10.00
Claude Haiku 4.5Anthropic	250/mo on Pro	Yes	200K tokens	Yes	Whole file	No	$1.00 / $5.00
Claude Haiku 5.5Anthropic	60/day on Pro	Yes	1M tokens	Yes	Whole file	Yes	$0.10 / $0.50

Each badge is how many messages Pro gets on the model: a month’s, or a day’s on an everyday model. Free is a one-time trial of 5 messages on the models marked. “Text only” models get the text of a PDF, not the file. API prices are the per-token prices in our model catalog as of October 2026 (Anthropic: Anthropic's list price). In llmwise you pay per message, not per token. Claude Haiku 5.5: the rate for prompts up to 100K tokens; $0.50 / $2.50 a million over that.

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.

Using Claude in llmwise, step by step

Sign in with your email: we send a link, and there's no password.
Open the model picker in the message box and choose a Claude model. Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 4.5, and Claude Haiku 5.5 are on Free, Claude Opus 5.5 for 1 message; Claude Fable 5.1 needs a paid plan.
Attach what you're working on: PDFs, images and text files.
Ask. For long material, Claude has room: Claude Fable 5.1 reads up to 1M tokens, Claude Haiku 4.5 up to 200K tokens.
Switch to another Claude model, or another family, in the same chat when you want a second answer. The next model sees everything so far.

Getting better answers from Claude

Say who the answer is for and what it's for. Context changes everything else.
Paste the material or attach the file, rather than describing it.
Show one example of what good looks like, and ask for the format you'll use: a table, bullets, a draft email.
For hard problems, pick a model that reasons before it answers (Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Haiku 5.5).
Save instructions you repeat as a persona, with Claude as its default model.

More in prompt optimization, or copy a prompt from the prompt library.

What it costs

Through Anthropic's API you pay per token: at the prices in our catalog as of October 2026, a typical message of 4,000 tokens in and 700 out costs from $0.0008 on Claude Haiku 5.5 to $0.0750 on Claude Fable 5.1. In llmwise a plan gives you a count per model instead: Claude Fable 5.1: 31 messages a month on Pro; Claude Opus 5.5: 62 messages a month on Pro; Claude Sonnet 5.5: 125 messages a month on Pro; Claude Sonnet 5: 125 messages a month on Pro; Claude Haiku 4.5: 250 messages a month on Pro; Claude Haiku 5.5: 60 messages a day on Pro. Full prices on Claude API pricing.

Questions

Is llmwise a way to use the Claude API?

No. llmwise is a chat app: it has no API and no API keys, so it can't serve your own code. To call Claude from code, use Anthropic's API.

Can I use Claude for free?

In llmwise, yes: Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 4.5, and Claude Haiku 5.5 are on the Free plan, a one-time trial of 5 messages, one of them can be on Claude Opus 5.5. No card needed.

Can Claude read my PDFs and images?

Yes: attach up to 10 files a message. Every Claude model reads images, and every one takes a PDF as the whole file, charts and layout included.

Claude, GPT, Gemini, DeepSeek, Grok, Kimi, GLM, and Mistral, 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.