Edgee records 6,558 monthly visits with +96.9% month-over-month growth and Freemium, Contact for Pricing pricing. Promptr records 0 monthly visits with 0% growth and Pay-as-you-go pricing.
Agent gateway that routes, compresses and observes your LLM token spend
Compress LLM prompts with one REST API call and cut token costs
| Dimension / Metric | | |
|---|---|---|
| Official Domain | edgee.ai | promptr.dev |
| Pricing Model | Freemium, Contact for Pricing | Pay-as-you-go |
| Monthly Visits | 6.56K (6,558) | 0 (0) |
| MoM Traffic Delta | +3.23K (+96.9%) | 0 (0%) |
| Primary Market & Share | 🇩🇪 Germany (54.5%) | 🌐 Global (—) |
| Direct Visits / mo | 2.66K | 0 |
| User Rating | 4.2 | 3.6 |
| Supported Platforms | Website | Website |
Agent gateway that routes, compresses and observes your LLM token spend
Assign token budgets per developer, squad or org, and let Edgee reroute requests to open-weight models mid-task when budgets fill or providers fail.
Trims tool-result payloads at the gateway and shortens output verbosity so coding tasks bill fewer tokens for the same result.
Attribute cost and usage by developer, repository, PR and model so engineering leaders can see where spend comes from.
A transparent gateway for Claude Code, Codex, Copilot, Cursor, OpenCode and your own apps, installed via CLI in about five minutes.
Compress LLM prompts with one REST API call and cut token costs
Send your prompt to a single REST endpoint and receive a shorter version back as plain text, ready to pass to your model.
The vendor reports up to 40% lower LLM input cost, with a worked example showing a 45% reduction on a sample prompt.
Copy-paste examples are provided for curl, Python, JavaScript and C#, so integration takes minutes rather than days.
Wrap sections in tags to exclude them from compression or to set a specific compression ratio for that block.
Free / Open-sourceHigh-efficiency open-weight and hosted reasoning AI powered by DeepSeek-V4 and R1 at ultra-low token costs.
Free / Open-sourceHigh-efficiency open-weight and hosted reasoning AI powered by DeepSeek-V4 and R1 at ultra-low token costs.
One API key for hundreds of AI models from every major provider
One OpenAI-compatible gateway for adaptive LLM routing, guardrails, and spend control
One OpenAI-compatible gateway for adaptive LLM routing, guardrails, and spend control
Free / Open-sourceOpen-source, memory-efficient fine-tuning and local model running
Free / Open-sourceOpen-source, memory-efficient fine-tuning and local model running
Free / Open-sourceOne open-source AI gateway for 100+ LLM providers
One unified API for 100+ AI models, with insurance when output disappoints
One unified API for 100+ AI models, with insurance when output disappoints
One OpenAI-compatible key for discounted GPT, Claude and Gemini access
AI gateway, observability and guardrails for production LLM apps
One API gateway and LLM router for around 1,000 AI models
Free / Open-sourceCut AI agent token costs with recoverable context compression and smart model routing
Free / Open-sourceCut AI agent token costs with recoverable context compression and smart model routing
Free / Open-sourceOne OpenAI-compatible API to route, monitor and control 250+ LLM models
Free / Open-sourceOne OpenAI-compatible API to route, monitor and control 250+ LLM models
Free / Open-sourceOpen-source AI memory that reasons, not just stores
