Pricing
Per-token rates in USD per 1M tokens for all three model tiers. You pay from a prepaid balance as you go — no subscriptions, no seat licenses.
| MODEL | INPUT / 1M | OUTPUT / 1M | STREAMING | TOOLS |
|---|---|---|---|---|
| unst33r-flashGLM-5.3-Flash Uncensored | $0.50 | $1.50 | Included | Included |
| unst33r-deepseekDeepSeek-V4.1-Flash Abliterated | $1.20 | $3.20 | Included | Included |
| unst33r-proGLM-5.3 Uncensored | $2.50 | $4.50 | Included | Included |
// rates from catalog version 2026-10-15-launch-v1
Prepaid balance, metered per request
Top up once
Add balance in the console with a one-time Stripe payment — $1, $20, $50, $100, or $500 USD. No subscription, no seat licenses.
Call any model
One API key and one base URL cover all three tiers. Streaming and tool calling are included in every model's token rate.
Pay per request
Each call deducts from your balance by tokens used: input and output are metered separately at the model's rates. The console lists tokens and cost per request.
What one request costs
A mid-size chat request: 1,500 input tokens (prompt, system message, tool definitions) and 600 output tokens. Cost = tokens ÷ 1M × rate, computed from the live rates above.
| MODEL | INPUT COST | OUTPUT COST | REQUEST TOTAL | × 1,000 REQUESTS |
|---|---|---|---|---|
| unst33r-flash | $0.00075 | $0.00090 | $0.00165 | $1.65 |
| unst33r-deepseek | $0.00180 | $0.00192 | $0.00372 | $3.72 |
| unst33r-pro | $0.00375 | $0.00270 | $0.00645 | $6.45 |
// illustrative arithmetic from the live rates — your calls are metered by actual token counts
Before you top up
Start with a $1 balance.
Create a key, top up what you need, and pay only for the tokens you use.