GPT by OpenAI, Claude by Anthropic, Gemini by Google, DeepSeek, Qwen, Grok and hundreds more in one chat.
You pay per answer. A simple question to DeepSeek costs a fraction of a cent. You can switch models mid-conversation and attach up to 10 files and images per message.
Popular models
GPT-5.6 Terra
1,064 tokens ≈ $0.035 per answer
An OpenAI model, as in ChatGPT.
Claude Sonnet 5.5
912 tokens ≈ $0.030 per answer
Careful answers, code and long documents.
Gemini 3.8 Flash
376 tokens ≈ $0.013 per answer
Google's fast model with a large context.
DeepSeek V4.1 Flash
57 tokens ≈ $0.002 per answer
The cheapest of the popular ones.
What the chat does
Switch models
Start cheap, switch to a flagship in the same thread.
Files
Up to 10 files and images per message.
Examples
Write the task as you would explain it to a colleague.
Code
Find the bug in this Python function and explain why it happens
Parameters
Models
more than 370 text models
Attachments
up to 10 files and images
Billing
per answer
How much an answer costs
Model
Tokens
USD
GPT-5.6 Terra
1,064 tokens
≈ $0.035
Claude Sonnet 5.5
912 tokens
≈ $0.030
Gemini 3.8 Flash
376 tokens
≈ $0.013
DeepSeek V4.1 Flash
57 tokens
≈ $0.002
An answer here means a 1,000-token question and a 1,000-token reply, about 700 words together. USD at the Basic rate: $5 = 150,000 tokens. Long threads and reasoning cost more.
$5 by card gives 150,000 tokens. That covers 164 Claude Sonnet 5.5 answers.
How to start
Sign in
With Google, Telegram or email. Takes under a minute.
Top up
From $5 by card or from $2 in crypto. No subscription, and tokens never expire.