The right plan for every team.

Wrap your pipeline with server-side security scanning before any data is stored. Fluiq checks every prompt, response, tool call, and retrieved document, so attack patterns are never shipped in the public SDK.

• PII Detection & Redaction: Names, emails, phone numbers, SSNs, and credit cards, detected and redacted before persistence.
• Prompt Injection Blocking: Catches injection patterns in real time, before the prompt reaches your model.
• Jailbreak & Skeleton Key Detection: Dedicated scanners for jailbreak framings and skeleton-key attacks that try to unlock restricted behaviour.
• Semantic Attack Scoring: Similarity scoring against known attack vectors, so a reworded attack still scores as one.
• Secret Leak Prevention: Scans model output for leaked API keys, tokens, and high-entropy credential strings.
• Indirect Injection & RAG Poisoning: Inspects tool outputs and retrieved chunks for second-order injection, and flags documents that read like an attack.
• Tool Abuse Defense: Catches sensitive data exfiltrated through tool-call arguments, and tools invoked outside your allowlist.
• Multi-Agent Trust: Detects cross-agent injection and risk escalating across agent handoffs in the trace DAG.
• Image & Multimodal Scanning: Images and other media attached to a call are scanned alongside the text.
• Custom Guardrail Policies: Set your own thresholds and categories per organisation instead of taking the defaults.
• Warn or Block mode: warn (default) flags risks and attaches security metadata to the trace. block intercepts before the LLM call and raises FluiqSecurityError.

fluiq.instrument(api_key="fl_...")
fluiq.secure()  # warn mode flags risks on the trace
fluiq.secure(mode="block")  # block mode

Fluiq mines your trace history to find which calls repeat, provisions a dedicated Redis cache for your account, and serves the repeats. You get the latency back as well as the money.

• Trace-Driven Cache Profiling: The backend mines your trace history to build a cache profile. No manual configuration.
• Prompt Response Caching: Real responses are stored on the first call; matching prompts afterwards are served from Redis.
• Embedding Caching: Repeated embedding calls are cached separately from prompts, with their own hit rate.
• Observe mode: Records what would have been a cache hit without intercepting, so you can price the saving before you opt in.
• Cache hit dashboard: Hit rates, latency saved, and estimated cost saved, split by cache kind.
• Optimization Insights: Ranks your repeated prompts by how much they would save if cached, with a projected monthly figure.
• Cost Hotspots: Surfaces your top-spending models and agents, slowest calls, and where errors cluster.
• Zero code changes: One fluiq.optimize() call after instrument(). The SDK handles connection, profiling, and lookup.

fluiq.instrument(api_key="fl_...")
fluiq.optimize()  # cache mode
fluiq.optimize(mode="observe")  # observe mode