Detailed feature comparison
Every capability, across all four plans.
← swipe to compare plans →
| Features | DeveloperFree | Team | RecommendedBusiness | EnterpriseCustom |
|---|---|---|---|---|
| AI Gateway | ||||
| Universal API - chat, responses, embeddings, rerank, images, audio (speech / transcription / realtime), video, OCR, files, batch & async jobs | ✓ | ✓ | ✓ | ✓ |
| 29 providers (OpenAI, Anthropic, Azure, Bedrock, Vertex, Gemini, Mistral, Groq, Cohere, xAI, DeepSeek, Fireworks, OpenRouter, Hugging Face, Ollama, vLLM, SGLang & more) + bare-model-name routing | ✓ | ✓ | ✓ | ✓ |
| Drop-in SDK passthrough - OpenAI, Anthropic, Bedrock, Google GenAI, Cohere, LangChain, LiteLLM, Pydantic AI, Cursor | ✓ | ✓ | ✓ | ✓ |
| Automatic fallbacks, retries & load balancing | ✓ | ✓ | ✓ | ✓ |
| Adaptive routing (latency / cost / health-aware) | - | ✓ | ✓ | ✓ |
| Per-model rate limits & cost budgets | 2 models | 25 models | 100 models | Unlimited models |
| Bring-your-own model endpoint (Ollama / SGLang / vLLM) | ✓ | ✓ | ✓ | ✓ |
| Private LLM connectivity (PrivateLink / VPC-SC / Private Endpoints) | - | - | - | ✓ |
| Providers & Model Management | ||||
| Model catalog with pricing metadata | ✓ | ✓ | ✓ | ✓ |
| Custom per-model pricing overrides & margin calc | - | ✓ | ✓ | ✓ |
| Model limits (RPM / TPM / cost) | 2 | 25 | 100 | Unlimited |
| Routing rules | 1 | 10 | 25 | Unlimited |
| Guardrails & Safety | ||||
| Heuristic engine + injection / jailbreak + PII / secrets / toxicity | ✓ | ✓ | ✓ | ✓ |
| 70+ pattern presets (22 groups) + builder cards incl. OWASP LLM Top 10 (2025) | ✓ | ✓ | ✓ | ✓ |
| Multimodal attachment text-extraction scan | ✓ | ✓ | ✓ | ✓ |
| Guardrail policies | 1 | Unlimited | Unlimited | Unlimited |
| ML detector sidecar (7 models - injection, jailbreak, PII, extended PII, toxicity, hate speech, content moderation) + deep semantic classifier | - | ✓ | ✓ | ✓ |
| Custom guardrail cards (your own regex patterns in the policy builder) | - | ✓ | ✓ | ✓ |
| Partner guardrails (Bedrock / Model Armor / Azure) + webhook | - | ✓ | ✓ | ✓ |
| PII redaction (zero-latency auto-mask in transit) | - | ✓ | ✓ | ✓ |
| OWASP Agentic Top-10 + 7 domain packs (BFSI, healthcare, insurance, enterprise copilot, customer support, development assistant, agentic) + coverage badge | - | - | ✓ | ✓ |
| Compiled control cross-walk per pack (MITRE / NIST / HIPAA / SOC2) | - | - | ✓ | ✓ |
| Defense & export-control pack | - | - | - | ✓ |
| RAG Security | ||||
| Chunk filtering SDK + per-chunk trust / injection scoring | ✓ | ✓ | ✓ | ✓ |
| guard_retriever() / guard_embedder() framework hooks | ✓ | ✓ | ✓ | ✓ |
| Source ACL tags, citation enforcement, PII-in-chunk blocking | - | ✓ | ✓ | ✓ |
| Context-poisoning detection + decision traces + findings | - | ✓ | ✓ | ✓ |
| Shadow / enforce mode + compliance evidence export bundle | - | ✓ | ✓ | ✓ |
| Agentic Security (PEP / PDP) | ||||
| Agentic SDK - zero-code instrumentation for 12 frameworks (LangGraph, CrewAI, AutoGen, LlamaIndex, Pydantic AI & more) | ✓ | ✓ | ✓ | ✓ |
| PDP core - decide, rule builder, Rego, ABAC, decision cache, audit | - | ✓ | ✓ | ✓ |
| OWASP Agentic threat templates (T1 memory poisoning → T17 supply chain) + ABAC operands (AST ≡ Rego) | - | ✓ | ✓ | ✓ |
| Policy lifecycle (draft → staged → published) + per-policy targeting | - | ✓ | ✓ | ✓ |
| Human-in-the-loop approvals (four-eyes queue) | - | - | ✓ | ✓ |
| Tool Integrity Engine + AIBOM / tool pinning + tool grants | - | - | ✓ | ✓ |
| Code-threat scanning + function identity (T11 RCE / T17 supply chain) | - | - | ✓ | ✓ |
| ReBAC / OpenFGA fine-grained authorization | - | - | ✓ | ✓ |
| Agent identity (Entra / SPIFFE / OIDC, DPoP) + Shadow / Canary / Enforce rollouts | - | - | ✓ | ✓ |
| Service graph, agent discovery, server-side analytics | - | - | ✓ | ✓ |
| Compliance cross-walk on audit export (NIST AI RMF / ISO 42001 / EU AI Act / MITRE ATLAS) | - | - | ✓ | ✓ |
| Agentic & MCP Tool Control | ||||
| MCP servers (register & broker) | 1 | 25 | 50 | Unlimited |
| MCP transports (stdio / SSE / streamable HTTP / in-process) + per-server auth | ✓ | ✓ | ✓ | ✓ |
| MCP tool sync + per-server health monitor | ✓ | ✓ | ✓ | ✓ |
| Parallel MCP guardrail classification | - | ✓ | ✓ | ✓ |
| MCP tool-result caching (per-tool TTL) | - | ✓ | ✓ | ✓ |
| MCP relationship authorization (ReBAC - who may use a server / invoke a tool) | - | - | ✓ | ✓ |
| Code-mode sandboxing for tool execution (Starlark) | ✓ | ✓ | ✓ | ✓ |
| Agentic Observability | ||||
| Agent run traces + span / observation timeline | - | - | ✓ | ✓ |
| Langfuse integration (model / token / cost / score enrichment) | - | - | ✓ | ✓ |
| Vendor-neutral OTLP export (Tempo / Honeycomb / Datadog / Grafana) | - | - | ✓ | ✓ |
| LLM-as-judge + tool-integrity score + AI tool-behavior summaries | - | - | ✓ | ✓ |
| Opt-in ZDR prompt-preview capture | - | - | ✓ | ✓ |
| Agentic Cache (verdict-gated) | ||||
| Verdict-gated, boundary-scoped post-decision cache (tool-result) | - | - | ✓ | ✓ |
| Per-VK scope + workspace settings + obligation-honoring on hit | - | - | ✓ | ✓ |
| Unified platform-savings reporting + admin flush | - | - | ✓ | ✓ |
| Caching & Cost Optimization | ||||
| Provider prompt-cache hints + request coalescing + TTFT prefix reorder (no vector store needed) | ✓ | ✓ | ✓ | ✓ |
| Guardrail evaluation cache + parallel-tool safety | ✓ | ✓ | ✓ | ✓ |
| Exact response cache + semantic cache (own switch, 0.88 default similarity) + Direct-gate L1 + cache warmer | - | ✓ | ✓ | ✓ |
| Cascade routing (plan- and key-scoped) + per-VK cache scoping (7 modes) | - | ✓ | ✓ | ✓ |
| Prompt compression (LLMLingua-2) + RAG re-ranking with enforced max chunks (bge) | - | ✓ | ✓ | ✓ |
| Conversation summarization + reasoning-effort throttling | - | ✓ | ✓ | ✓ |
| Batch eligibility analysis (reporting only - no provider batch submission) | - | ✓ | ✓ | ✓ |
| Token-savings reporting + per-layer drift sampler | - | ✓ | ✓ | ✓ |
| Per-technique plan labels, validated partial saves with rollback, per-workspace settings | ✓ | ✓ | ✓ | ✓ |
| Bring-your-own vector store (Pinecone / Qdrant / Weaviate / Redis) | - | - | - | ✓ |
| Accuracy & Safety | ||||
| Hallucination control (pre-LLM) + evaluation (post-LLM) | - | - | ✓ | ✓ |
| Ground-truth management + 5-metric quality dashboard (faithfulness, answer relevance, coherence, helpfulness, citation precision) | - | - | ✓ | ✓ |
| Response consistency - exact / semantic / pinned / strict | - | - | ✓ | ✓ |
| Model Hub & Fine-Tune | ||||
| Model inventory + per-model limits & overrides | ✓ | ✓ | ✓ | ✓ |
| DeepintShield Models sidecar (Hugging Face detector inventory) | - | ✓ | ✓ | ✓ |
| Detector fine-tune - regex extraction + LoRA (train → deploy → reset) | - | ✓ | ✓ | ✓ |
| Prompt Management | ||||
| Prompt repository + versioning + diff (save / commit / delete) | Read-only | ✓ | ✓ | ✓ |
| Unsaved multi-provider playground - variables, streaming, runtime virtual key | ✓ | ✓ | ✓ | ✓ |
| Role-based (RBAC) prompt access control | - | ✓ | ✓ | ✓ |
| Observability | ||||
| Real-time KPI dashboard (RPS, p50 / p95 / p99 latency, error %, $) | ✓ | ✓ | ✓ | ✓ |
| Per-request audit trail + custom metadata tagging + free-text search | ✓ | ✓ | ✓ | ✓ |
| MCP tool-call observability + provider-dimension dashboards | ✓ | ✓ | ✓ | ✓ |
| Log retention | 7 days | 30 days | 90 days | 365 days |
| Alerts - email / Slack / HMAC-signed webhook | - | ✓ | ✓ | ✓ |
| Usage attribution (by customer / virtual key / team) | - | ✓ | ✓ | ✓ |
| CSV download + scheduled log exports (daily / weekly) | - | ✓ | ✓ | ✓ |
| Prometheus /metrics + OpenTelemetry export (Jaeger / Datadog / New Relic) | - | - | ✓ | ✓ |
| Telemetry plugin - Prometheus Pushgateway + sample Grafana dashboard | - | - | ✓ | ✓ |
| Configurable export to data lake (S3 / GCS / Azure Blob / BigQuery / Redshift / Snowflake) | - | - | - | ✓ |
| Governance, RBAC & Multi-Tenancy | ||||
| Included seats (users) | 1 | 10 | 30 | 50 |
| Workspaces (included allowance) | 1 | 10 | 25 | Unlimited |
| Virtual keys (per-key budgets, rate limits, allowlists, guardrail bindings) | 3 | 100 | 500 | Unlimited |
| Built-in roles (admin / viewer) at user, org and tenant level | ✓ | ✓ | ✓ | ✓ |
| Custom roles | - | - | - | ✓ |
| Customers - end-user attribution | - | ✓ | ✓ | ✓ |
| Org-level metadata reporting | - | - | - | ✓ |
| Single-tenant slice on shared control plane | - | - | - | ✓ |
| Regional customer-hosted data planes (US / EU / India, one per org) | - | - | - | ✓ |
| Org management (multi-org admin) | - | - | - | ✓ |
| Dedicated control-plane namespace | - | - | - | Add-on |
| Authentication & Security | ||||
| Username / password sign-in (Google OAuth2 optional, admin-configured) | ✓ | ✓ | ✓ | ✓ |
| Native TOTP MFA + single-use recovery codes | ✓ | ✓ | ✓ | ✓ |
| Self-service DSAR personal-data export (GDPR / DPDP) | ✓ | ✓ | ✓ | ✓ |
| Consent history + sealed subscription-agreement PDFs (Account → Legal) | ✓ | ✓ | ✓ | ✓ |
| HTTP / SOCKS5 proxy + custom-CA trust | - | - | - | ✓ |
| Microsoft Entra / OIDC SSO + SAML 2.0 + SCIM 2.0 + JIT provisioning | - | - | - | ✓ |
| Outbound-only mTLS tunnel (no inbound from vendor) | - | - | - | ✓ |
| Compliance & Hosting | ||||
| Managed cloud control plane | ✓ | ✓ | ✓ | ✓ |
| Customer-hosted data plane (Helm / Compose / GKE / EKS / AKS) | - | - | - | ✓ |
| Multi-cloud (GCP / AWS / Azure) + on-prem + air-gapped | - | - | - | ✓ |
| Data residency | US | US | US | You choose (US / EU / India) |
| Audit log of admin actions (immutable, hash-chained) + tamper-verify | - | - | - | ✓ |
| HIPAA BAA · GDPR DPA · SOC 2 / ISO 27001 control cross-walk | DPA* | DPA | DPA | ✓ |
| SDKs & Integrations | ||||
| Python SDK v2.7.1 (20 extras) + native framework binders + MCP adapters (OpenAI / Anthropic / LangChain) | ✓ | ✓ | ✓ | ✓ |
| Framework instrumentation - LangGraph, LangChain, CrewAI, AutoGen, Pydantic AI, OpenAI Agents, LlamaIndex, LiteLLM, Temporal, AWS Strands, Google ADK, Hermes (+ OpenClaw gateway config) | ✓ | ✓ | ✓ | ✓ |
| shield.agentic.* PDP surface + in-SDK prompt / Gemini cache helpers | ✓ | ✓ | ✓ | ✓ |
| Coding-agent & chat-client endpoints (Claude Code, Codex CLI, Gemini CLI, Qwen Code, Opencode, Cursor, Zed, Roo Code, Open WebUI, LibreChat) | ✓ | ✓ | ✓ | ✓ |
| Plugin SDK (custom Go middleware) | - | ✓ | ✓ | ✓ |
| Terraform module + Helm chart + Admin Console | - | - | - | ✓ |
| Configuration & Operations | ||||
| API-key management UI + caching config (TTL / similarity / scoping) | ✓ | ✓ | ✓ | ✓ |
| Governance plugin (VK enforcement, header rules, MCP catalog binding) | ✓ | ✓ | ✓ | ✓ |
| Fast JSON (sonic) + LiteLLM compat plugin + streaming-JSON parser plugin | ✓ | ✓ | ✓ | ✓ |
| Performance / pricing / observability config + margin reporting | - | ✓ | ✓ | ✓ |
| Request mocker / replay + per-org feature releases (“Updates”) | - | ✓ | ✓ | ✓ |
| Data-plane management (tunnel delta-sync, metering, heartbeat) | - | - | - | ✓ |
| eBPF / XDP kernel prefilter (Linux) | - | - | - | ✓ |
| Enterprise-VPC provisioning wizard + Phase-3 mTLS tunnel + signed bundles | - | - | - | ✓ |
| Support & SLA | ||||
| Community (GitHub, Discord) | ✓ | ✓ | ✓ | ✓ |
| Email support | Best-effort | 24-hr | 12-hr | 1-hr |
| Dedicated Slack + solution-architect onboarding | - | - | - | ✓ |
| 24×7 phone + named TAM | - | - | - | Add-on |
| Uptime SLA | - | 99.5% | 99.9% | 99.5% (GA) → 99.95% |
| Custom roadmap input + N / N-1 version support | - | - | - | ✓ |
| Volume, Billing & Overage | ||||
| Included governed requests / month | 10K | 250K | 1M | Custom |
| Beyond the included limit (additional requests) | Hard cap - HTTP 429 (blocked, $0) | $19 per 100K | $15 per 100K | Custom (aggregate-metered) |
| Logged-request overage (secondary meter) | - | No surcharge | No surcharge | - |
| Overage ceiling → next step | Blocked at 10K (HTTP 429) | No hard cap · Business recommended past 1M | No hard cap · talk to us past 5M | Unlimited / contracted |
| Token markup on routed provider spend | 0% | 0% | 0% | 0% (negotiated) |
| Extra seats | No additional seat | $20 per seat / month, prorated | $20 per seat / month, prorated | Per contract |
| Monthly extras invoice (request overage + extra seats, + GST in INR) | - | Issued after month-end · Razorpay link or UPI AutoPay (INR) | Issued after month-end · Razorpay link or UPI AutoPay (INR) | Per contract |
| Unpaid invoice: reminders → restrictions | - | Day 1/3/7/14 reminders · day 7 pauses new seats & resources · day 14 pauses requests | Day 1/3/7/14 reminders · day 7 pauses new seats & resources · day 14 pauses requests | Per contract |
| Billing cadence | Free forever · never renews | Base monthly or annual · extras monthly | Base monthly or annual · extras monthly | Annual contract |
| Taxes | - | INR: +18% GST · USD: none | INR: +18% GST · USD: none | Per contract |
| Cancellation & refunds | - | Cancel any time in Account → Billing · effective at term end | Cancel any time in Account → Billing · effective at term end | Per contract |
*Refunds per the Cancellation, Refund & Shipping Policy; purchases are governed by the Terms and Conditions and Privacy Policy. · All plans run self-hosted with no prompt or key egress on customer-hosted deployments.