Try it
AI playground: try every major model online
llmwise's playground is the whole chat: 20 models in 8 families (Claude, GPT, Gemini, DeepSeek, Grok, Kimi, GLM, and Mistral) in your browser, with no API keys. Sign in with an email link and start with 5 free messages, no card. Each model's count shows before you send.
Start in three steps
Sign in with your email: we send a link, and there's no password to set.
Ask something real. A new chat starts on GPT-6 Luna, an everyday model; the picker in the message box has the rest.
Switch to Claude, GPT, Gemini, DeepSeek, Grok, Kimi, GLM, or Mistral whenever you want a second answer. The next model sees the whole chat.
What's on the Free plan
What you can try without paying, and what needs a plan.
A one-time trial of 5 messages on Claude Haiku 5.5. It doesn't refill.
On a paid plan: Claude Opus 5.5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 4.5, GPT-6.1 Sol, GPT-6 Sol, GPT-6 Luna, Gemini 4 Argon, Gemini 3.1 Pro, Gemini 3.8 Flash, DeepSeek V4.1 Flash, DeepSeek V4 Pro, Grok 4.7, Kimi K3, GLM 5.3, GLM 5.3 Flash, and Mistral Large 4 from Plus ($10), Claude Fable 5.1 and GPT-6 Astra from Pro ($20), and the paid tools.
Every plan is on the pricing page, and every part of the free offer on free AI chat. To start from one family, the AI chat page links each one's own.
Things to try
The same question, two models
Ask one real question, then switch models in the picker and ask again. The second model sees the first one's answer, so you can ask it what it would change.
Your own files
Attach a PDF or a screenshot and ask about it. The table below shows which models read images and which take a PDF as the whole file.
A small app
Ask for a calculator, a quiz or a small tool, and it runs live as an HTML app beside the chat.
A document
Ask for a draft, a table or a slide deck: it opens as a document you can edit and download.
Which model should you try first?
From our test runs of September 27, 28, 29 and October 2, 7, 8, 9, 15, 2026: for each job, the least expensive model that passed every prompt, with what a reply cost us. Start there; move up when your own question needs more.
Coding: GLM 5.3 Flash ($0.0003 a reply)
Writing: GPT-6 Luna ($0.0001 a reply)
Math: Claude Haiku 5.5 ($0.0001 a reply; in the free trial)
Summarization: DeepSeek V4.1 Flash ($0.0002 a reply)
Data analysis: GPT-6 Luna ($0.0002 a reply)
Customer support: GLM 5.3 ($0.0005 a reply)
Translation: GPT-6 Luna ($0.0001 a reply)
SQL: GPT-6 Luna ($0.0001 a reply)
RAG and answering from documents: GPT-6 Luna ($0.0001 a reply)
Agents and tool use: GPT-6 Luna ($0.0001 a reply)
Each message goes to the model's maker when llmwise can reach it directly, or through OpenRouter, which picks among the hosts it lists for that model (OpenRouter's provider routing docs). The failover post shows which hosts answered our runs.
Every model you can try
Straight from our model catalog: what a message uses, whether Free has it, and what each model reads.
| Model | On Pro | On Free | Context window | Images | PDFs | Reasoning |
|---|---|---|---|---|---|---|
| Claude Fable 5.1Anthropic | 31/mo on Pro | No | 1M tokens | Yes | Whole file | Yes |
| Claude Opus 5.5Anthropic | 62/mo on Pro | No | 1M tokens | Yes | Whole file | Yes |
| Claude Sonnet 5.5Anthropic | 125/mo on Pro | No | 1M tokens | Yes | Whole file | Yes |
| Claude Sonnet 5Anthropic | 125/mo on Pro | No | 1M tokens | Yes | Whole file | Yes |
| Claude Haiku 5.5Anthropic | 60/day on Pro | Yes | 1M tokens | Yes | Whole file | Yes |
| Claude Haiku 4.5Anthropic | 250/mo on Pro | No | 200K tokens | Yes | Whole file | No |
| GPT-6 AstraOpenAI | 31/mo on Pro | No | 1.05M tokens | Yes | Whole file | Yes |
| GPT-6.1 SolOpenAI | 125/mo on Pro | No | 1.05M tokens | Yes | Whole file | Yes |
| GPT-6 SolOpenAI | 125/mo on Pro | No | 1.05M tokens | Yes | Whole file | Yes |
| GPT-6 LunaOpenAI | 60/day on Pro | No | 1.05M tokens | Yes | Whole file | Yes |
| Gemini 4 ArgonGoogle | 62/mo on Pro | No | 1.05M tokens | Yes | Whole file | Yes |
| Gemini 3.1 Pro (preview)Google | 125/mo on Pro | No | 1.05M tokens | Yes | Whole file | Yes |
| Gemini 3.8 FlashGoogle | 250/mo on Pro | No | 1.05M tokens | Yes | Whole file | Yes |
| DeepSeek V4.1 FlashDeepSeek | 60/day on Pro | No | 1.05M tokens | Yes | Text only | Yes |
| DeepSeek V4 ProDeepSeek | 250/mo on Pro | No | 1.05M tokens | No | Text only | Yes |
| Grok 4.7xAI | 250/mo on Pro | No | 500K tokens | Yes | Whole file | Yes |
| Kimi K3Moonshot | 125/mo on Pro | No | 1.05M tokens | Yes | Text only | Yes |
| GLM 5.3Z.ai | 250/mo on Pro | No | 1.05M tokens | No | Text only | Yes |
| GLM 5.3 FlashZ.ai | 60/day on Pro | No | 1.05M tokens | Yes | Text only | Yes |
| Mistral Large 4Mistral | 250/mo on Pro | No | 1.05M tokens | Yes | Text only | Yes |
Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Plus $3.75, 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.
A chat, not a console
llmwise is a chat app, not a developer console: there are no API keys to paste and no parameters to tune. You get the models themselves, and the tools a chat can use: web search with sources, files, documents and small apps. Not sure which model to start with? Try the model picker.
The playground: questions
Do I need to sign up?
Yes, with just your email: we send a link that works for 15 minutes, and there's no password. The first link creates a Free account; no card needed.
Is it free?
To try it: Free is a one-time trial of 5 messages on Claude Haiku 5.5. It doesn't refill; paid plans have everyday messages every day and a monthly allowance for the rest.
Is this a developer playground?
No. It's the models themselves in a chat: there are no API keys, no temperature sliders and no raw request editor.
Open the chat and ask
5 messages, once, with no card and no password: an email link signs you in. After that, Pro ($20) counts every model's messages before you send.