Alternative · Poe points
An alternative to Poe points: prices you see before you send
Poe is Quora's app for chatting with many AI models and bots. In llmwise every message has a fixed price, shown next to the send button, and that's exactly what's charged: on Pro ($20), up to 125 Claude Sonnet 5 messages a month or up to 31 on Claude Fable 5.1.
What you might be looking for
Knowing what a message costs
You see how many messages you have left on the model you pick before you send, and that's exactly what's counted, however long the reply.
Two simple counts
Everyday messages (a daily count) and the monthly allowance (shown as messages per model) are separate, and the sidebar shows both with when they refill.
No surprises
When a chat gets long (past 64k tokens each reply counts as 2, past 128k as 4), the composer says so before you send, and a chat stops at 200k. When a reply reaches your plan's length limit, it stops and offers Continue, at the same price as any message.
The models in llmwise
Pick a model for each message; the badge shows how many messages Pro gets on it.
Claude by Anthropic
- Claude Fable 5.131/mo on Pro
- Claude Opus 5.562/mo on Pro
- Claude Sonnet 5.5125/mo on Pro
- Claude Sonnet 5125/mo on Pro
- Claude Haiku 4.5250/mo on Pro
- Claude Haiku 5.560/day on Pro
GPT by OpenAI
- GPT-6 Astra31/mo on Pro
- GPT-6.1 Sol125/mo on Pro
- GPT-6 Sol125/mo on Pro
- GPT-6 Luna60/day on Pro
Gemini by Google
- Gemini 4 Argon62/mo on Pro
- Gemini 3.1 Pro (preview)125/mo on Pro
- Gemini 3.8 Flash250/mo on Pro
DeepSeek by DeepSeek
- DeepSeek V4 Pro250/mo on Pro
- DeepSeek V4.1 Flash60/day on Pro
Grok by xAI
- Grok 4.7250/mo on Pro
Kimi by Moonshot
- Kimi K3125/mo on Pro
GLM by Z.ai
- GLM 5.3250/mo on Pro
- GLM 5.3 Flash60/day on Pro
Mistral by Mistral
- Mistral Large 4250/mo on Pro
What else is in the chat
Files
Attach PDFs (up to 100 pages), images and text files, up to 10 a message.
Documents
Drafts, code and tables open beside the chat as documents that keep every version; text downloads as PDF, Word or Markdown, tables as Excel or CSV.
Small apps
Ask for a calculator or a small tool and it runs live as an HTML app in the side panel.
Web search
Answers can search the web and cite their sources. On Free, web search works inside your 5 trial messages; on a paid plan each search counts as one more message of the model in use.
Personas and skills
Save instructions as a persona with its own default model, or add skills the model can use.
Paid-plan tools
On Pro and higher plans: research reports (counting as 15 Claude Haiku 4.5 messages Standard, 75 Claude Haiku 4.5 messages Deep), code runs in a sandbox (1 Claude Haiku 4.5 message a run), backend apps (5 Claude Haiku 4.5 messages per started 10 minutes) and MCP servers. Images are made in Create, on every plan.
Plans
Monthly, cancel anytime. A message's price is fixed before you send it.
| Plan | Price | Everyday models | A month on the other models |
|---|---|---|---|
| Free | $0 | A one-time trial of 5 messages on Claude Haiku 5.5 | None: the other models are on paid plans |
| Plus | $10 a month + applicable tax, shown before you pay | 30 a day | 31 messages on Claude Opus 5.5 or Gemini 4 Argon; 62 on Claude Sonnet 5.5-class models; or 125 on Claude Haiku 4.5-class models |
| Pro | $20 a month + applicable tax, shown before you pay | 60 a day | 31 messages on Claude Fable 5.1 or GPT-6 Astra; 62 on Claude Opus 5.5 or Gemini 4 Argon; 125 on Claude Sonnet 5.5-class models; or 250 on Claude Haiku 4.5-class models |
| Max | $50 a month + applicable tax, shown before you pay | 120 a day | 100 messages on Claude Fable 5.1 or GPT-6 Astra; 200 on Claude Opus 5.5 or Gemini 4 Argon; 400 on Claude Sonnet 5.5-class models; or 800 on Claude Haiku 4.5-class models |
| Ultra | $100 a month + applicable tax, shown before you pay | 200 a day | 225 messages on Claude Fable 5.1 or GPT-6 Astra; 450 on Claude Opus 5.5 or Gemini 4 Argon; 900 on Claude Sonnet 5.5-class models; or 1,800 on Claude Haiku 4.5-class models |
| Studio | $200 a month + applicable tax, shown before you pay | 200 a day | 500 messages on Claude Fable 5.1 or GPT-6 Astra; 1,000 on Claude Opus 5.5 or Gemini 4 Argon; 2,000 on Claude Sonnet 5.5-class models; or 4,000 on Claude Haiku 4.5-class models |
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.
Every model's price per message is on the pricing page.
Switching from Poe points
Sign in with your email: we send a link, there's no password to set.
Check the count by each model in the picker: how many messages you have left on it.
Use everyday models for most questions and bigger ones when it matters.
When llmwise isn't the right fit
If you prefer paying per token for exactly what a reply uses, a pay-as-you-go API suits that better than a plan.
Questions
Can a long reply cost more than shown?
No. The price is fixed when you send: the reply's length, its reasoning and its tool steps inside one reply don't change it. Tools such as code runs and images add their own fixed price.
What happens when I run out?
On a paid plan, top up from Settings → Billing: $10 adds 25 messages on Claude Fable 5.1 or GPT-6 Astra; 50 on Claude Opus 5.5 or Gemini 4 Argon; 100 on Claude Sonnet 5.5-class models; or 200 on Claude Haiku 4.5-class models (+ applicable tax, shown before you pay); top-ups last 12 months. Everyday models keep working either way, up to the plan's fair-use limit.
Is llmwise free?
To try it: Free is a one-time trial of 5 messages on Claude Haiku 5.5, with no card. It doesn't refill; paid plans add more models (Pro and higher plans, every model), everyday messages every day and a monthly allowance for the rest.
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.