tanveloSimple, predictable pricing for resilient AI infrastructure
Every plan includes all core gateway features: smart multi-provider routing, sub-180ms automatic failover, spend controls, privacy redaction, and 100% Bring-Your-Own-Key (BYOK).
Inference tokens are billed directly by your AI providers. Tanvelo subscriptions cover gateway orchestration, routing, circuit breakers, and rate limit telemetry. You configure your own provider keys (OpenAI, Anthropic, Gemini, Groq, DeepSeek, etc.) and Tanvelo never marks up token prices.
Free
Explore Tanvelo with 5,000 gateway requests each month, one workspace, and all core gateway features.
Pro
Build and ship with 200,000 gateway requests each month, 5 workspaces, and prioritized support.
Elite
Scale your AI applications with 1,000,000 gateway requests each month, 25 workspaces, and team collaboration.
Full Feature Comparison
Detailed comparison of quotas, limits, and team collaboration across plans.
| Limit / Feature | Free | Pro | Elite |
|---|---|---|---|
| Monthly Price | $0 | $19/mo | $49/mo |
| Gateway requests / month | 5,000 | 200,000 | 1,000,000 |
| Active workspaces | 1 | 5 | 25 |
| Core gateway features | All included | All included | All included |
| 147+ AI model providers | All supported | All supported | All supported |
| Smart routing & failover | Included | Included | Included |
| Spend controls & rate limits | Included | Included | Included |
| Team collaboration | — | — | Included |
| Team invitations & roles | — | — | Available |
| Support level | Standard / community | Priority email | Priority support |
| Analytics & log retention | Standard limits | Higher limits | Highest plan limits |
Frequently Asked Questions
Clear answers regarding billing, usage quotas, and data policies.
How are gateway requests counted against my monthly quota?
One accepted incoming gateway request counts as one quota unit. Internal automatic failovers, circuit breaker switches, or retries do not consume extra quota units. Quota resets at the start of each billing cycle (or on the 1st of each calendar month in UTC for Free accounts).
Are AI model inference tokens included in Tanvelo pricing?
No. Tanvelo is a Bring-Your-Own-Key (BYOK) gateway. You configure your own provider keys (OpenAI, Anthropic, Gemini, Groq, DeepSeek, etc.) and your providers bill you directly without any token markup from Tanvelo.
What happens to my data if I downgrade?
Tanvelo never silently deletes workspaces or configuration data. If an account downgrades and holds more workspaces than the new plan permits, new workspace creation is blocked, but existing workspaces and keys remain intact. You can choose which workspaces to delete or keep at your own pace.
Who can invite team members?
Team collaboration and invitations are available exclusively on the Elite plan. Elite account owners and admins can invite team members with specific roles (Admin, Member) to collaborate securely across workspaces.
© 2026 Tanvelo LLM Federation Gateway. All rights reserved.