An open-source and managed gateway for model routing, reliability, observability, and governance
Advisor score
Documented editorial evaluation
The decision
Portkey earns a shortlist for teams needing shared model governance and able to engineer the gateway as critical infrastructure. Start with shadow traffic, restrict keys, define fail-open policy, validate cache isolation, and keep a recovery path.
Best for
Multi-provider teams; Central AI budgets and keys.
Choose something else if
Simple one-provider apps; Sensitive logs without controls
Evidence
Editorial research pending · 8.0/10
Pricing checked
From $49 · 2026-09-01
Free access is available, with limits.
Yes. Self-host the gateway or use managed Dev within its limits.
Community choice
Loading weekly votes…
One vote per verified account per tool, counted for seven days. Return after your vote expires to support again. Community votes influence homepage trends, never editorial ratings. Voting does not subscribe you to emails.
Portkey centralizes model access, fallbacks, caching, guardrails, keys, budgets, and traces, but a gateway becomes a critical data and availability boundary that needs failure testing.
Portkey earns a shortlist for teams needing shared model governance and able to engineer the gateway as critical infrastructure. Start with shadow traffic, restrict keys, define fail-open policy, validate cache isolation, and keep a recovery path.
Replay 500 synthetic requests across two providers with outages, limits, slow responses, malformed outputs, injection, PII, changed prices, cache collisions, budget exhaustion, and key revocation. Measure success, fallback drift, cost, latency, guardrail errors, exposure, isolation, and gateway outage behavior.
Personal Recommendation
Portkey earns a shortlist for teams needing shared model governance and able to engineer the gateway as critical infrastructure. Start with shadow traffic, restrict keys, define fail-open policy, validate cache isolation, and keep a recovery path.
Try the recommendation
Open-source data plane
Overall Score
Editorial Review Framework
Overall Score
8.0
Ease of Use
7.6
AI Quality
8.0
Features
8.4
Speed
8.0
Integrations
8.4
Value for Money
8.0
Customer Support
7.6
Learning Curve
7.4
Recommended Because…
Open-source data plane
Scores use a 0-10 editorial scale: 9–10 exceptional, 8–8.9 strong, 7–7.9 capable with material tradeoffs, 6–6.9 limited fit, and below 6 not recommended. Scores publish only when a documented evaluation supports them.
Reusable trial worksheet
Turn this review’s buyer test into evidence. Your entries autosave only in this browser and are never added to shared shortlist links.
Confirm the tool meets every must-have workflow and stakeholder requirement.
Review starting point: Multi-provider teams; Central AI budgets and keys; Production routing and observability
Run the same representative work you would use in production; do not score a polished demo.
Review starting point: Complete three to five representative tasks with known acceptable outcomes and compare them with your current process.
Calculate the effective cost per accepted result, including usage, review, corrections, and required add-ons.
Review starting point: The open-source gateway is free. Managed Dev includes 10,000 monthly requests and three-day retention. Pro is $49 monthly for 100,000 requests, with published overage and 30-day retention. Enterprise uses custom volume, retention, security, and deployment terms. Model usage is separate. Reviewed September 1, 2026.
Define an acceptance threshold, test known answers and edge cases, and record every correction.
Review starting point: Editorial quality signals: features 4.2/5; AI quality 4.0/5. Validate these signals in your own work.
Verify what data enters the product, who can access it, how long it is retained, and whether it trains models.
Review starting point: Use approved low-risk data first. Check roles, consent, deletion, subprocessors, model-training settings, and the contract—not only the marketing page.
Test the real handoffs, permissions, failure states, and export path your team depends on.
Review starting point: OpenAI, Anthropic, Gemini, MCP, LangChain, LlamaIndex
Record training, governance, reliability, accessibility, ownership, and change-management risks before rollout.
Review starting point: Critical central dependency; Fallbacks change quality and cost; Advanced controls are enterprise
Loading saved worksheet… · private to this device or your optional account
Evaluation
Research-based
Price posture
From $49/month
Reviewed
2026-09-01
No authentic product screenshot is published for this review. DiscoverAI does not use generated interface images as product evidence.
Editorial freshness
Pricing and material product claims were checked September 1, 2026.
Community evidence
Structured, editor-moderated experience—not star ratings. This complements our independent review and never changes its score.
No approved community evidence yet. Be the first verified user to contribute.
The gateway is open source, and managed Dev includes 10,000 monthly requests.
Pro is $49 monthly for 100,000 requests, with model usage and overage separate.
No. It routes to providers and adds control; underlying terms and charges still apply.
The open-source gateway runs locally; broader private and air-gapped deployments use enterprise packaging.
Keep Deciding
Not Diamond Review 2026: AI Model Routing and Prompt Optimization
Not Diamond combines pretrained and custom model routing with cross-model prompt optimization, but its value depends on representative evaluation data and measured end-to-end savings.
Portkey AI Review 2026: Gateway, Pricing, Guardrails, and Fit
Portkey centralizes model access, fallbacks, caching, guardrails, keys, budgets, and traces, but a gateway becomes a critical data and availability boundary that needs failure testing.
Best AI Coding Tools
AI coding assistants ranked by real developer workflow fit, not demo magic.
Best AI Tools for Code & Development
A practical shortlist of AI tools for ai coding assistants, code generators, and developer tools.
Code & Development
AI coding assistants, code generators, and developer tools.
Material changes only
Get an occasional email when something decision-relevant changes. This is separate from the weekly newsletter.
See how similar tools stack up
An open-source AI gateway with request monitoring, cost tracking, caching, fallbacks, prompts, and evaluations
Helicone combines multi-provider routing and observability behind a familiar API, but proxy trust, logged payloads, retention, usage-based costs, and gateway dependency need careful architecture review.
Open-source tracing, evaluation, prompt management, and metrics for LLM applications
Langfuse unifies traces, costs, prompts, datasets, and evaluation with cloud and self-hosted options, but telemetry sensitivity, retention, operational load, and fast-rising plan costs demand a scoped pilot.
An evaluation, prompt, dataset, and observability platform for AI product development
Braintrust connects production traces, datasets, experiments, scorers, prompts, and human review, but judge validity, sensitive logs, retention, score volume, and release-gate design require calibration.