A gateway, guardrails, evals, and an audit trail — billed by use.
Query your warehouse in place; per-tenant isolation from the first call.
Pick a model through one gateway, add tools and knowledge, test in the Playground.
Attach guardrails and an eval set. Gate releases on pass-rate.
One governed endpoint, six surfaces. Guardrails, audit, and billing on every call.
Each routine maps a trigger to an agent to a deploy target. Start from one and customize.
A recurring, multi-step agent that runs on a schedule and reports back — daily digests, triage sweeps, recurring reviews.
An agent that drives a real browser through a sandboxed computer-use runtime — fill forms, gather data, reconcile portals.
Fires on an incoming event — a new email, ticket, row, or upload — runs the agent, and routes or replies.
Drop files in, get structured objects out. Chunk, extract, validate against a schema, and land the result.
A grounded chat assistant embedded in your own product via the widget or API — answers from your KB, with citations.
One agent calls another as a tool — a router hands off to specialists. Each hop is governed and traced.
Deploy widens reach, never permission — guardrails, audit, and billing apply to every call.
One host. Your tenant is resolved from the key — isolated by default.
Input and output policies — PII redaction, no-promises, escalation — enforced before and after every call.
Datasets and pass-rate gating. Catch regressions before they ship; gate releases on a threshold.
Every run, guardrail decision, and write-back carries actor, intent, and a policy decision id — append-only.
Span-level visibility into every model call, tool, and guardrail. Export and retain per plan.
Route by cost, latency, or region. Bring your own keys; they decrypt only inside the gateway runtime.
| MODEL | PROVIDER | IN / 1M | OUT / 1M | P99 | REGION |
|---|---|---|---|---|---|
| Claude Sonnet 4.6 | anthropic | $3.00 | $15.00 | 1.4 s | US-East |
| Claude Opus 4.7 | anthropic | $18.00 | $72.00 | 2.8 s | US-East |
| Claude Haiku 3.6 | anthropic | $0.80 | $2.40 | 0.4 s | US-East |
| GPT-5.2 | openai | $5.00 | $20.00 | 1.8 s | US-East |
| Gemini 2.5 Pro | $2.50 | $10.00 | 1.6 s | EU-West | |
| Llama 4.1 70B | meta | $0.40 | $0.80 | 0.9 s | On-prem |
| Mistral Large 3 | mistral | $2.00 | $6.00 | 1.2 s | EU-West |
| DeepSeek V3 | deepseek | $0.50 | $2.00 | 1.3 s | On-prem |
Free to start: 1 agent, 1k runs/mo, no card. Per-seat plus metered usage when you grow.