| What it does | Open-source LLMOps platform for engineering teams
| One OpenAI-compatible API for every model with adaptive routing, hosted agents, pipelines, and observability
|
|---|
| Stage | MVP
| Startup
|
|---|
| Founded | Not given
| 2025
|
|---|
| Based in | Not given
| IN
|
|---|
| Pricing model | Open source
| Not given
|
|---|
| Pricing | Free during beta. Self-hosted is free under Apache 2.0 license. Enterprise options available on request.
| Free: $1 free credits on signup (90 days), 50 requests and 500K tokens per day on free models. Starter: $14/month (30% off with PROMO code), includes $20 in monthly credits, 10 RPM burst 1.5x, 2 pipelines. Paid: $35/month (30% off), includes $50 in monthly credits, 20 RPM, 4 pipelines. Pro Plus: $70
|
|---|
| Key features | - Prompt versioning with named aliases and diffs
- Server-side prompt templating with conditionals and loops
- OpenAI-compatible AI gateway with automatic model fallbacks
- Virtual keys, budgets and per-key rate limits
- LLM tracing through the gateway or over OpenTelemetry
- Versioned tool catalog for function calling
- Offline experiments and online evaluation rules
- Prompt optimization with candidate rewrites
- Team-wide audit trail of every change
- MCP server for Claude Code, Claude Desktop, Cursor
| - Access to 100+ open-weight and frontier AI models behind one endpoint
- OpenAI-compatible HTTP endpoint
- Semantic caching to reduce latency and costs
- Reproducible pipelines composing models, tools, and data
- Per-request structured traces with latency and cost breakdown
- Adaptive routing with latency-aware fallbacks
- Model-agnostic RAG, web search, and PII redaction via single header
- Works with existing OpenAI SDK without code changes
|
|---|
| What makes it different | - Change prompts without a deploy by moving production alias
- OpenAI-compatible drop-in gateway keeping existing code paths intact
- Every call is automatically traced with model, tokens, latency and cost
- Audit trail records every change with the person who made it
- Open source Apache 2.0 license with self-hosting option
| - One unified invoice and observability dashboard across all models, agents, and pipelines
- Transparent prepaid credits with per-token rates published in your dashboard
- Hosted agents with explicit CPU and memory caps and fail-closed credit gates
- No synthetic data in dashboards; all metrics reflect actual user traffic
- No model retraining on customer data
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 12 ▲ +1 (up) since last check | 27 ▲ +4 (up) since last check |
|---|
| Trust Flow (Majestic) | 12 | 3 |
|---|
| Citation Flow (Majestic) | 33 | 19 |
|---|
| Referring domains (Majestic) | 49 | 16 |
|---|
AcruxCore