Pricing
Pay for the tokens you use at the listed model rate. No subscription, no seat fees, no monthly minimum.
0%
Markup on per-token model rates
Every request is billed at the model's published input and output rate.
5%
Platform fee on credit top-ups
A flat fee when you add credits. A $20 top-up costs $21.
$0
For failed requests
Requests that fail before a provider answers never deduct credits.
Included on every account
There are no plans or tiers. Everyone gets the same platform.
Sign up for free- Every model in the catalogue
- OpenAI & Anthropic compatible endpoints
- Automatic retries and failover
- Usage and cost analytics dashboard
- Unlimited API keys with spend caps
- Key expiry and instant revocation
- 600 requests/min to start
- Email support
- $20 minimum top-up
- Prepaid credits start at $20. Auto top-up is available but optional.
- Invoices for every top-up
- Each purchase produces an invoice in your dashboard and in your inbox.
- Spend limits per key
- Cap spend on any API key so a runaway workload cannot drain your balance.
Estimate your monthly cost
Pick a model and your expected volume. Rates come from the live catalogue.
Estimated monthly total
$3.15
- GPT OSS 120B usage$0.03 in · $0.14 out per 1M
- $3.00
- Platform fee (5%)
- $0.15
Pricing questions
Is there a free tier or subscription?
There is no subscription. You prepay credits and pay only for the tokens you use at listed model rates.
What does the 5% fee cover?
Payment processing and platform costs. It applies to credit top-ups only; per-token usage carries no markup.
Do credits expire?
See the Terms of Use for the current credit policy. Your balance and every transaction are visible in the dashboard.
Can I get volume pricing?
Yes. Email hello@vichar.io to talk about committed volume.