Simple, transparent pricing
Built edge-first so production AI controls stay affordable. Gateway requests and core security are generous by design; heavier retention, full-payload storage, eval replay, archive, and compliance features scale transparently.
Developer
Mission-tier. Real product, no credit card required.
- 250k requests / month
- 1 seat
- 14-day retention
- Full proxy gateway + cost tracking
- Virtual keys
- Basic ThreatPrint
- No credit card required
Pro
Best fit for production builders shipping daily.
- 2M requests / month
- 3 seats
- 30-day retention
- Full ThreatPrint
- Output schema firewall
- Cross-tenant canary detection
- Prompt cache metrics
- Slack + email alerts
- CLI + webhooks
- MCP gateway
Team
Cross-functional governance for high-volume teams.
- 20M requests / month
- 10 seats
- 90-day retention
- SAML SSO + RBAC
- Audit logs + policy bundles
- WebSocket live feed
- Priority support (48-hour response)
Enterprise
Private deployment, compliance, and volume commitments.
- Custom request volume
- Custom retention
- Private deployment
- BYO storage
- DPA/security review
- SLA
- Advanced SAML/SCIM roadmap
- Signed incident reports roadmap
- Dedicated support
Need more than 10 seats, custom retention, or private rollout?
Pulse runs the same edge proxy whether you're a solo dev or a 500-person org. Talk to us about volume, SOC-ready deployments, and private networking.
Resource scaling guardrails
Pulse distinguishes request volume from seats, metadata retention, trace retention, payload storage, replay, archive, export, and support. That keeps the default gateway generous while making expensive storage and compliance choices explicit.
| Resource | Included generously | Scales when heavy |
|---|---|---|
| Gateway requests | 250k requests/month on Developer; millions on paid plans | Custom high-volume commit or metered overage |
| ThreatPrint scans | Included on every gateway request | Optional classifier bindings and higher-volume security review |
| Metadata retention | 14 days on Developer, 30-90 days on paid plans | Custom retention windows |
| Trace storage | Recent trace spans for debugging and incident review | Longer trace retention and export volume |
| Full payload retention | Raw payloads off by default; redacted/configurable storage by plan | Explicit full-payload retention with compliance review |
| Evals/replays | Enough for routine prompt and model checks | Large replay batches and automation |
| Archive/export | Self-serve incident and trace exports | R2 archive, bulk export, BYO storage |
| Support/SLA | Community and standard support | SLA, DPA/security review, dedicated support |
Typed plan limits
| Plan | Requests | Seats | Metadata | Traces | Payload mode | Evals/replays | Archive/export |
|---|---|---|---|---|---|---|---|
| Developer | 250,000 | 1 | 14 days | 7 days | redacted | 100 | 3 |
| Pro | 2,000,000 | 3 | 30 days | 30 days | configurable | 2,500 | 25 |
| Team | 20,000,000 | 10 | 90 days | 90 days | configurable | 25,000 | 250 |
| Enterprise | Custom | Custom | Custom | Custom | full optional | Custom | Custom |
Can I change plans later?
Yes - upgrade or downgrade any time from the Settings page. Changes take effect immediately.
What happens to my data if I downgrade?
Existing records are kept. Retention and monthly request allowances follow your active plan tier.
Is there a free trial?
Developer is permanent and requires no credit card. Pro and Team plans bill monthly with no lock-in.
Do you store my provider API keys?
Only when you opt in to virtual keys or the upstream key pool. Those are AES-256-GCM encrypted with SHA-256-derived keys before they touch the database, and plaintext never leaves the server session.
Which AI providers are supported?
OpenAI, Anthropic, Google AI, Groq, Mistral, Together, Fireworks, Perplexity, Cohere, DeepSeek, xAI, AWS Bedrock, GCP Vertex, Azure OpenAI, OpenRouter, HuggingFace, Replicate, Ollama, Custom. Plus an MCP (Model Context Protocol) gateway for tool servers. Each provider is routed with its native wire format.
What counts as a 'team member'?
Each additional person who can connect their own API keys and view the shared dashboard.
Do you scale past 10 seats?
Yes. Team includes 10 seats by default. For larger teams, private networking, or custom contracts, email contact@orionslock.com and we'll tailor it.