Pricing
Pricing
No subscription needed, no minimum spend, and credit does not expire. New accounts start with $0.50 of credit for the chat.
Top up or pick a plan
Pay as you go
$5minimum top-up
Credit never expires+$5 on your first top-up of $10 or more
- No subscription needed
- 3 requests at once
Starter
$15a month + tax
Monthly $35 credits2.3× what you pay
- Try it with your agent
- Never logged
- Tool calling, 262K context
- 3 requests at once
Pro
Popular$39a month + tax
Monthly $100 credits2.6× what you pay3× Starter
- For daily coding with an agent
- Everything in Starter
- Upgrade keeps unused credits
- 5 requests at once
Max
$99a month + tax
Monthly $300 credits3× what you pay9× Starter
- For agents running all day
- Everything in Pro
- Lowest rate per token
- 8 requests at once
Models
Prices per million tokens
| Model | Input | Cached input | Output |
|---|---|---|---|
| Qwen3.8 27B Uncensored | $1.00 | $0.10 | $3.00 |
- Welcome credit
- $0.50
- Wake fee
- $0.01 when the model was idle
- Requests at once
- 3 per account; 5 on Pro, 8 on Max
Cached input: when your tool resends the start of a conversation, those tokens cost $0.10 per million instead of $1.00. Cached-input pricing applies to the API and coding tools; messages in the web chat pay the full input price.
Credit
Top up $5, $10, $25 or $50, or any whole-dollar amount from $5 to $1,000.
Your first top-up of $10 or more adds $5 of bonus credit. New accounts start with $0.50 of credit, and credit never expires. API keys work after your first top-up.
Tax is added at checkout where your country requires it.
What things cost
- A web chat message
- 1,500 tokens in, none cached, 500 out: $0.003
- A coding-agent turn
- 60,000 tokens in, 55,000 of them cached, 1,500 out: $0.015
- A long-context request
- 200,000 tokens in, none cached, 2,000 out: $0.206
These are token costs at the prices above. A request that wakes a sleeping GPU adds $0.01. Nothing extra is charged while the model is already running.