Pay for what you use
Every plan includes a monthly token quota — start free with 500K tokens/month. Paid plans can top up with credits anytime, priced per model. No hidden fees, no long-term contracts.
Free
Get started with Convoy
500K tokens/month included
- 500K tokens/month
- 1 project
- 1 team member
- Core models (Nova, Haiku, Llama, Gemma, and more)
- Webhook callbacks
- Usage analytics
- Documentation & knowledge base
Starter
For growing teams
1M tokens/month included · buy credits for more
- 1M tokens/month
- 5 projects
- 5 team members
- All supported models
- Multimodal file uploads (images, PDFs, documents)
- Webhook callbacks
- Usage analytics
- Email support
Pro
For production workloads
5M tokens/month included · buy credits for more
- 5M tokens/month
- Unlimited projects
- Unlimited team members
- All supported models
- Multimodal file uploads (images, PDFs, documents)
- Webhook callbacks
- Usage analytics
- Higher rate limits
- Priority support
- SLA guarantee
Enterprise
Self-hosted in your AWS account
- Deploy in your own AWS account
- Use your own AI providers (e.g., Amazon Bedrock)
- Multimodal file uploads with GuardDuty malware scanning in your own AWS account
- Unlimited projects and team members
- Available via AWS Marketplace or direct engagement
- RBAC and access policies
- Dedicated support & SLA
Compare Plans
| Feature | Free | Starter | Pro | Enterprise |
|---|---|---|---|---|
| Usage | ||||
| Included monthly tokens | 500K | 1M | 5M | Customer-managed |
| Buy additional credits | — | |||
| Burst capacity (instant requests) | 100 | 1,000 | 5,000 | Infrastructure-dependent |
| Sustained rate (requests/min) | 30 | 120 | 600 | Infrastructure-dependent |
| Features | ||||
| All supported models | Core models only | |||
| Webhook callbacks | ||||
| Usage analytics | ||||
| Multiple projects | ||||
| Team members | 1 | 5 | Unlimited | Unlimited |
| Deployment | Cloud | Cloud | Cloud | Your AWS account |
| Use your own AI providers (e.g., Bedrock) | ||||
| RBAC & access policies | ||||
| Support | ||||
| Documentation & knowledge base | ||||
| Email support | ||||
| Priority support | ||||
| SLA guarantee | ||||
| Dedicated support | ||||
Frequently Asked Questions
How does token-based billing work?
Usage is measured in tokens — both input (your prompts) and output (model responses). Each plan includes a monthly token quota. On paid plans, if you need more you can purchase credits at any time, which are applied to your usage based on each model’s per-token pricing.
What happens when I hit my included token quota?
On paid plans, you can purchase credits from the billing dashboard to keep processing immediately, or upgrade to a plan with a larger monthly quota. On the Free plan, upgrade to a paid plan to continue processing before your quota resets.
How do credits work?
Credits are one-time purchases ($10–$250) available on paid plans, added to your account balance. When usage exceeds your plan’s included monthly tokens, additional usage draws down your credit balance at each model’s listed per-token rate. This lets you handle usage spikes without changing plans.
Can I change plans at any time?
Yes. You can upgrade or downgrade at any time through the billing dashboard. Upgrades take effect immediately. Downgrades take effect at the end of your current billing period.
Can I submit a whole batch of requests at once?
Yes. Convoy uses a burst-friendly token bucket rate limiter: every plan includes a burst allowance (100 requests on Free, 1,000 on Starter, 5,000 on Pro) that you can submit instantly, then a sustained rate (30, 120, or 600 requests/minute) once the burst is spent. If you exceed the limit, requests return a 429 with a Retry-After header telling you exactly when to retry.
What is batch processing and why is it cheaper?
Convoy uses batch processing to handle requests asynchronously, with pricing around 40% below realtime API rates on most supported models. Actual savings vary by model and token mix. Results are typically available within minutes to hours depending on volume.
Do you offer refunds?
We offer a 14-day money-back guarantee for new paid subscriptions. Contact support@cnvy.ai within 14 days of your first payment for a full refund.
Is there a free trial?
The Free plan is available indefinitely with 500K tokens/month — no credit card required. This lets you evaluate Convoy before committing to a paid plan.
What is the Enterprise plan?
Enterprise is a self-hosted version of Convoy that runs entirely in your own AWS account. You use your own AI providers — such as Amazon Bedrock — for inference, and your data never leaves your account. Pricing is tailored to your deployment — contact our sales team to discuss.
How do I get the Enterprise plan?
Enterprise is available through AWS Marketplace or direct engagement with our team (including air-gapped environments). Contact our sales team and we will walk you through deployment with our Terraform module or CloudFormation template, licensing, and onboarding.