Compare gateways
Experiential vs Portkey
Portkey (now Prisma AIRS AI Gateway) is a control layer over your own keys billed per request, while Experiential includes model access, failover and data controls.
Summary
Portkey routes requests to providers through keys you add. It adds configs for fallbacks, load balancing and caching, 50+ guardrails, and request logs. Its docs now carry the banner "Portkey is now Prisma AIRS AI Gateway", linking to Palo Alto Networks, and portkey.ai/pricing redirects to a sales form. Experiential needs no provider accounts and no config objects, and failover is automatic.
import os
from portkey_ai import Portkey
client = Portkey(
api_key=os.environ["PORTKEY_API_KEY"],
config="pc-fallback-123",
)
client.chat.completions.create(
model="@openai-prod/gpt-6-luna",
messages=[{"role": "user", "content": "Hello"}],
)Side by side
| Experiential | Portkey | |
|---|---|---|
| Hosting | Hosted | Hosted, hybrid (gateway in your VPC), or open-source gateway |
| APIs | Chat, Responses, Messages, Gemini generateContent, embeddings, batches | Chat, Responses, Messages (any provider), embeddings, batches |
| Model access | 980 listed models on credits, or your keys | 3,000+ models through your keys |
| Pricing | List price on tokens, no markup | Per request: Dev free (10K a month, 3-day logs), Pro $49 (100K, then $9 per 100K), Enterprise custom |
| Failover | Ordered waterfall, automatic; slow lanes demoted | Fallback, load-balance and conditional configs; retries, circuit breakers |
| Zero data retention | Pro: org switch, per request, verdict per response | Not documented |
| Spend limits | Per-key caps, budgets, tier rate limits | Budgets and rate limits per key or provider |
| Content guardrails | Standard pack or your own classifier | 50+ checks, partner and custom guardrails |
| Response cache | None | Simple and semantic (semantic on Pro and up) |
| SSO | Not yet available | Enterprise |
Where Experiential is better
- Failover without configs. Each model has an ordered provider waterfall, and slow providers are demoted automatically. See Routing and failover.
- Model access included. No provider accounts to open. Credits pay list price, and cost is in each reply.
- Zero-retention and no-training routing, enforced per org or per request and reported per response. See Data controls.
- Published pricing, with no per-request platform fee. See Plans and pricing.
When Portkey may fit better
You need a response cache, conditional routing on metadata, prompt templates, a gateway inside your own VPC, or the Palo Alto Networks security stack.
Migration notes
| What | Portkey | Experiential |
|---|---|---|
| Base URL | https://api.portkey.ai/v1 | https://api.experientiallabs.ai/v1 |
| Auth | x-portkey-api-key plus x-portkey-provider or a virtual key | Authorization: Bearer YOUR_API_KEY only |
| Model ids | @provider-slug/model | Plain slug from GET /v1/models |
x-portkey-config | Fallback, load-balance, retry, cache | Remove it; routing and retries are automatic. Fallbacks to a different model are not carried over |
override_params, default_params | Set by config | Put the values in the request body |
x-portkey-metadata | Tags; _user | X-Explabs-Tags header (a JSON object, up to 16 labels); safety_identifier in the body |
x-portkey-trace-id | Trace id | X-Explabs-Session-Id header |
| Guardrails in configs | Input and output checks | Per-key content guardrails |
Switch with an agent
Paste this into your coding agent. It inventories the project first and asks before anything it cannot map.
POST/v1/chat/completionscurl https://api.portkey.ai/v1/chat/completions \
-H "x-portkey-api-key: $PORTKEY_API_KEY" \
-H "x-portkey-provider: @openai-prod" \
-H 'x-portkey-metadata: {"_user": "u_42", "team": "search"}' \
-H "Content-Type: application/json" \
-d '{"model": "gpt-6-luna",
"messages": [{"role": "user", "content": "Hello"}]}'Sources, checked 2026-11-19
- Feature comparison: plans, request limits, log retention, caching per plan, SSO and VPC on Enterprise.
- Feature overview: 3,000+ models, routing, 50+ guardrails, budgets, observability.
- AI gateway, universal API, Anthropic, batches.
- portkey.ai/pricing: redirects to a Palo Alto Networks contact form. Acquisition: Palo Alto Networks 10-K, FY2026.
- Experiential: /llms.txt, GET /api/models.