Skip to content

AI chat

AI chat with every top model in one place

21 models from 8 AI companies in one chat, each with a published count: from Claude Haiku 5.5, up to 60 messages a day on Pro, to Claude Fable 5.1, up to 31 messages a month. Each family has its own page below.

A real answer from our test runs

Claude Haiku 5.5

Write an email to Tom declining his invitation to a vendor demo on Wednesday at 11:00, because you're presenting to the board then. Offer Thursday at 10:00 or Friday at 14:00 instead. Polite and brief: at most 120 words.

Claude Haiku 5.5 · passed our check · October 7, 2026

Subject: Re: Vendor Demo on Wednesday

Hi Tom,

Thank you for the invitation to the vendor demo on Wednesday at 11:00. Unfortunately, I'm presenting to the board at that time, so I won't be able to attend.

Would Thursday at 10:00 or Friday at 14:00 work for you instead? I'd be glad to reschedule.

Thanks for understanding, and I look forward to hearing from you.

Best regards,
[Your Name]

Ask Claude Haiku 5.5 your own question: it's on Plus and Pro. Paid monthly from the day you start. Cancel in two clicks in Settings → Billing.

Get started

Test runs and prices checked . Updated .

Short answer

Pick the model for each message. In our test runs, DeepSeek V4.1 Flash, an everyday model with 60 messages a day on Pro, passed 48 of 50 prompts; of the models on the monthly allowance, DeepSeek V4 Pro passed 49 of 50. Every family below has a page of its own.

Chat with one family

Each family's models with Pro's count on each, and its own chat page.

  • Chat with Claude

    Claude Fable 5.1 (31 a month), Claude Opus 5.5 (62 a month), Claude Sonnet 5.5 (125 a month), Claude Sonnet 5 (125 a month), Claude Haiku 4.5 (250 a month), Claude Haiku 5.5 (60 a day). On Plus and Pro (Claude Fable 5.1 on Pro).

  • Chat with GPT-6

    GPT-6 Astra (31 a month), GPT-6.1 Sol (125 a month), GPT-6 Sol (125 a month), GPT-6.1 Terra (250 a month), GPT-6 Luna (60 a day). On Plus and Pro (GPT-6 Astra on Pro).

  • Chat with Gemini

    Gemini 4 Argon (62 a month), Gemini 3.1 Pro (125 a month), Gemini 3.8 Flash (250 a month). On Plus and Pro.

  • Chat with DeepSeek

    DeepSeek V4 Pro (250 a month), DeepSeek V4.1 Flash (60 a day). On Plus and Pro.

  • Chat with Grok

    Grok 4.7 (250 a month). On Plus and Pro.

  • Chat with Kimi

    Kimi K3 (125 a month). On Plus and Pro.

  • GLM

    GLM 5.3 (250 a month), GLM 5.3 Flash (60 a day). On Plus and Pro.

  • Mistral

    Mistral Large 4 (250 a month). On Plus and Pro.

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.

Which model for which job

The model that passed the most of each job's prompts in our runs. On most jobs many models passed every prompt, so the pick is the one that costs least of them: for these, a flagship isn't needed.

  • Coding

    GLM 5.3 Flash, 5 of 5 passed (2 of 2 hard). 18 other models passed as many; GLM 5.3 Flash costs less.

  • Writing

    GPT-6 Luna, 5 of 5 passed (2 of 2 hard). GPT-6.1 Terra, DeepSeek V4 Pro, and GPT-6 Astra passed as many; GPT-6 Luna costs less.

  • Math

    Claude Haiku 5.5, 5 of 5 passed (2 of 2 hard). 19 other models passed as many; Claude Haiku 5.5 costs less.

  • Summarization

    DeepSeek V4.1 Flash, 5 of 5 passed (2 of 2 hard). 11 other models passed as many; DeepSeek V4.1 Flash costs less.

  • Data analysis

    GPT-6 Luna, 5 of 5 passed (2 of 2 hard). 16 other models passed as many; GPT-6 Luna costs less.

  • Customer support

    GLM 5.3, 5 of 5 passed (2 of 2 hard). Claude Sonnet 5, Gemini 3.1 Pro, and Claude Opus 5.5 passed as many; GLM 5.3 costs less.

  • Translation

    GPT-6 Luna, 5 of 5 passed (2 of 2 hard). 19 other models passed as many; GPT-6 Luna costs less.

  • SQL

    GPT-6 Luna, 5 of 5 passed (2 of 2 hard). 20 other models passed as many; GPT-6 Luna costs less.

  • RAG and answering from documents

    GPT-6 Luna, 5 of 5 passed (2 of 2 hard). 20 other models passed as many; GPT-6 Luna costs less.

  • Agents and tool use

    GPT-6 Luna, 5 of 5 passed (2 of 2 hard). 19 other models passed as many; GPT-6 Luna costs less.

More ways to chat

The other chat pages, each with its own models and test results.

Questions

Is this AI chat free?

No: there's no free plan or trial. Both were abused, so every plan is paid from day one. Without a plan you can sign in, read your chats and manage your settings, but can't send messages. Every plan is month to month: cancel in two clicks. Plus is $10 a month and Pro $20.

Which AI chat model is best?

It depends on the job. In our test runs on October 27, 2026, DeepSeek V4 Pro passed the most prompts (49 of 50), and DeepSeek V4.1 Flash did best of the everyday models (48 of 50), which Pro gives 60 of a day. Start on an everyday model and move up when an answer matters.

Can I switch models in the middle of a chat?

Yes. Pick another model for the next message: it sees the whole conversation, and the message box shows what that message counts as before you send it.

Do I need to install an app?

No: llmwise runs in your browser. You sign in with a link sent to your email, with no password to set.

Claude, GPT, Gemini, DeepSeek, Grok, Kimi, GLM, and Mistral, in one chat.

See what a message costs before you send it. Every plan is month to month: cancel in two clicks. Sign in with an email link, no password.