The AI Gateway for coding assistants
Make your coding assistant faster, cheaper, and more reliable.
Compress tokens, route across models, and keep working — even when providers fail or limits are reached.
Make your sessions last up to 26.5% longer with token compression.
Works with Claude, Codex, Cursor, and agentic coding workflows.
Free
For individual developers getting started.
- Token compression (Claude, Codex, Cursor, agentic workflows)
- Multi-provider gateway (200+ models)
- Automatic retries & fallback
- Individual observability dashboard
- Cost tracking
Team
For teams that need visibility, control, and uninterrupted workflows.
Billed annually · Volume discounts from 20 seats
$29 / user / month
Everything in Free, plus:
- Extend usage beyond limits (open-source fallback models)
- Team management (users, roles, access)
- GitHub integration (per repo / per PR attribution)
- Team dashboard + exports
- Spending caps & alerts (coming soon)
- Priority support
Enterprise
For teams with advanced scale, security, or compliance needs.
Volume-based pricing
Custom
Everything in Team, plus:
- SSO / SAML
- Audit logs
- Self-hosted deployments
- Custom data residency (EU, US, or private)
- Private gateway (SaaS or on-prem)
- Privacy controls (PII redaction, ZDR, …)
- Dedicated support & SLA
Token Compression
Same code. Fewer tokens. Longer sessions.
Edgee compresses prompts before they reach LLM providers.
Extend your coding sessions by up to 26.5% — without changing your workflow.
Feature overview
Everything you need to build and scale
Core
- Edgee CLI Free
- Edgee OSS AI Gateway (coming soon) Free
- OpenAI-compatible API Free
- Chat & API access Free
- SDK compatibility Free
- Token compression Free
- Multi-agent support (Claude, Codex, OpenCode — Cursor coming soon) Free
Gateway & Routing
- Multi-provider gateway (200+ models) Free
- 200+ models Provider pricing + 5% Edgee fee
- BYOK (Bring Your Own Key) Free
- Preferred provider routing Free
- Regional routing / pinning Free
- Retries & failover (errors) Free
- Fallback across providers (reliability) Free
Observability
- Observability dashboard Free
- Debug logs Free
- Usage, latency & error metrics Free
- Activity logs & exports Free
- Reports Free
Cost Controls
- Cost attribution (tags) Free
- Token usage & cost tracking Free
- Spending caps & alerts (coming soon) Team
Team & Usage
- Team management Team
- GitHub integration Team
- Per-repo & per-PR attribution Team
- Extend usage beyond limits (open-source fallback — coming soon) Team
Services
- Private models hosting (coming soon) Enterprise
- Private gateway Enterprise
Privacy & Admin
- Data policy routing Free
- SSO / SAML Enterprise
- Privacy controls (coming soon) Enterprise
Support
- Community support (Discord) Free
- Email support Free
- Priority support Team
- Contractual SLA Enterprise
Why Edgee
- Keep coding even when limits are reached or providers fail
- Reduce token usage automatically with built-in compression
- Route across 200+ models with a single API
- Track usage per developer, repo, and team
- No lock-in — bring your own keys or use Edgee
FAQ
Do I need a credit card to start?
Do you charge platform fees or markup model pricing?
What's the difference between BYOK and credits?
How does token compression work?
Can I use multiple providers at once?
Are failed or fallback attempts billed?
Can I separate environments (dev / staging / prod)?
Start building without limits
Use Edgee for free — and upgrade when your team needs more control.
No credit card required
All plans include Edgee’s token compression. You save on LLM costs from day one.