Content safety, PII detection, and audit logging come standard. Start free, scale with managed models. No add-on subscriptions, no surprises.
Try the API with $5 of free credit on our shared cluster. No credit card required. Or self-host with our open-source stack.
Managed model catalog with full compliance stack. Per-token billing — pay only for what you use.
BYOB (Bring Your Own Backend) support, policy templates, and BAA available. Full compliance reporting for auditors.
Customer-deployed inference project, private endpoints, custom models. Full compliance documentation and support.
All tiers pay per token. Enterprise gets committed capacity at a flat monthly rate.
| Model | Input | Output | Tiers |
|---|---|---|---|
| GPT-4o | $3.50 / 1M tokens | $14.00 / 1M tokens | Pro+ |
| GPT-4o mini | $0.20 / 1M tokens | $0.80 / 1M tokens | Free+ |
| GPT-4.1 | $2.50 / 1M tokens | $10.00 / 1M tokens | Pro+ |
| GPT-4.1 mini | $0.50 / 1M tokens | $2.00 / 1M tokens | Free+ |
| o4-mini | $1.50 / 1M tokens | $6.00 / 1M tokens | Business+ |
| DeepSeek R1 | $0.70 / 1M tokens | $2.80 / 1M tokens | Pro+ |
| Llama 4 Scout | $0.30 / 1M tokens | $0.90 / 1M tokens | Pro+ |
| Phi-4 | $0.14 / 1M tokens | $0.28 / 1M tokens | Free+ |
| Llama 3.1 8B | $0.06 / 1M tokens | $0.12 / 1M tokens | Free+ |
| Mistral Small | $0.15 / 1M tokens | $0.45 / 1M tokens | Free+ |
| Mistral Large | $2.60 / 1M tokens | $7.80 / 1M tokens | Business+ |
| Grok 3 Mini | $0.50 / 1M tokens | $1.50 / 1M tokens | Pro+ |
| text-embedding-3-large | $0.17 / 1M tokens | — | All |
| text-embedding-3-small | $0.03 / 1M tokens | — | All |
| Whisper large-v3 | — | $0.13/min | Pro+ |
Free tier $5 credit burns at these rates. Volume discounts available on Business+.
Estimate your monthly spend based on model and usage.
Every ACAI deployment includes production-grade guardrails and audit logging at no extra cost. Because compliance shouldn't be a premium feature.
Content safety scoring for hate, violence, self-harm, and sexual content on every request.
Included free10 built-in patterns (SSN, credit cards, PHI, MRN, DOB) with detect, redact-logs, or redact-all modes.
Included free4-layer detection pipeline: encoding analysis, pattern matching, heuristic scoring, and Prompt Shield API.
Included freeEvery request logged with full audit trail. 7 compliance export formats (HIPAA, SOC 2, PCI DSS, GDPR, CCPA, NIST 800-53, FERPA). Legal holds and retention policies.
Included freeEverything scales with your tier. No add-on subscriptions.
| Feature | Free | Pro | Business | Enterprise |
|---|---|---|---|---|
| Content safety + PII detection | ✓ | ✓ | ✓ | ✓ |
| Audit logging | 7 days | 30 days | 1 year | Unlimited |
| Prompt injection prevention | — | ✓ | ✓ | ✓ |
| 7-framework compliance exports | — | ✓ | ✓ | ✓ |
| Semantic cache | — | ✓ | ✓ | ✓ |
| Batch API | — | ✓ | ✓ | ✓ |
| RAG (knowledge bases) | — | — | 5 GB | Unlimited |
| Routing + A/B testing | — | — | ✓ | ✓ |
| Custom guardrail rules | — | — | — | ✓ |
| Custom models + fine-tuning | — | — | — | ✓ |
| Legal holds | — | — | — | ✓ |
| BAA (HIPAA) | — | — | ✓ | ✓ |
| Compute isolation | Shared | Shared | BYOB | VNet |
| SLA | — | 99.5% | 99.9% | 99.99% |
| Support | Community | Email 48hr | Email 24hr | Slack 1hr |
What it takes to build the same compliance pipeline in-house.
Typically requires 2-3 engineers for 3-6 months to build and maintain.
Pro starts at $99/month + per-token usage. First $5 free, no credit card.
Every plan — including Free — includes content safety filtering, PII detection and redaction, prompt injection prevention, and full audit logging. Compliance exports for all 7 frameworks (HIPAA, SOC 2, PCI DSS, GDPR, CCPA, NIST 800-53, FERPA) are available on Pro and above. BAA execution is available on Business and above.
Free and Pro tiers bill per token processed. Rates vary by model — premium models like GPT-4o cost more per token than lightweight models like Llama 3.1 8B or Phi-4. Your Free $5 credit burns at the same per-model rates. See the pricing table above for exact rates.
Pro uses our managed model catalog — great for development and moderate production workloads. Business adds BYOB (Bring Your Own Backend) support so you can route through your own provider keys while keeping the full compliance layer. Business also unlocks BAA execution for HIPAA compliance.
Yes. Most customers start on Pro to validate their use case, then upgrade to Business when they need dedicated compute or BAA. The API is identical — same endpoints, same SDKs, zero migration effort.
Free self-hosted containers are available on GitHub Container Registry (ghcr.io/devoptimum/acai-api and acai-web). Pull the images, bring your own inference backend, and run the full compliance pipeline locally. Self-hosted evidence packs are marked ‘unattested’ — upgrade to SaaS for ACAI-signed evidence packs with chain-of-custody verification.
All tiers access a managed model catalog (GPT-4o, GPT-4.1, DeepSeek R1, Llama 4, Phi-4, Mistral, and 37 models total). Business adds BYOB — bring your own OpenAI, Anthropic, or any provider keys. Enterprise adds custom fine-tuned models.
Free and Pro run in US East and US South Central. Business can deploy to additional regions. Enterprise supports sovereign and government cloud regions.