OpenAI compatible API. Attested gateway. Public status.
Pricing — Usage-Based, No Subscription
Prepaid credits, BYOK, or usage-based billing — pay the provider price plus a small routing margin, with no monthly plan. Per-model prices are published on the models page.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
Pay as you go
Prepaid credits. Add a card and you're charged only for what you route — provider cost plus a small routing margin. Auto-refill keeps prepaid routes flowing. Wallet accounts can start at $0.
Bring your own key
BYOK for any provider where you already have committed spend or enterprise rate limits. Keep your discounts; gain the attested prompt path, failover, and one unified API.
Migration credits
Teams already spending more than $100/month on LLMs can request migration credits by approval. Move your workloads over with one base_url change and keep your runway.
Transparent, usage-based. No subscription.
- ✓ No monthly plan or seat fees — you pay for tokens you route
- ✓ Per-model prices are published on the models page
- ✓ Prepaid credits, BYOK, and usage-based billing all supported
- ✓ Metadata-only billing records — no prompt or output bodies stored
- ✓ Stripe and stablecoin checkout for prepaid credits
What you payper request
# You are billed the provider's price for the
# tokens you use, plus a small routing margin.
#
# Per-model prices (prompt / completion per 1M
# tokens) are listed on /models — e.g.:
#
# anthropic/claude-sonnet-4.5 $3.00 / $15.00
# openai/gpt-5.1 $2.50 / $10.00
# deepseek/deepseek-v4-flash $0.27 / $0.27
#
# trustedrouter/auto picks a healthy route and
# bills at the selected provider's price.🛡 Privacy is structural, not a paid add-on — every plan routes through the attested, no-log gateway.
↺ Provider failover with
trustedrouter/auto is included on every plan.