Compare gateways
Experiential vs OpenRouter
Both are hosted gateways with one key, and Experiential keeps OpenRouter's paths and ids while adding native Gemini, per-response ZDR verdicts and no fee on your own keys.
このページはまだ翻訳されていません。英語版を表示しています。
Summary
OpenRouter is a hosted marketplace with 600+ models and 80+ providers. It charges a fee when you buy credits, and on your own keys above a monthly allowance. Experiential serves the same OpenRouter paths and model id spellings, so most projects move by changing the base URL and key.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key=os.environ["OPENROUTER_API_KEY"],
)
client.chat.completions.create(
model="openai/gpt-6-luna",
messages=[{"role": "user", "content": "Hello"}],
extra_body={"usage": {"include": True}},
)Side by side
| Experiential | OpenRouter | |
|---|---|---|
| APIs | Chat, Responses, Messages, Gemini generateContent, embeddings, batches | Chat, Responses, Messages, embeddings, batches |
| Native Gemini API | Yes, every model | Not documented |
| Price on tokens | List price, no markup | 5.5% fee on credit purchases (Standard), 8% (Business) |
| Bring your own key | No markup; first paid key needs Pro | No fee on the first $25K a month, then 5% |
| Models | 980 listed, all callable | 600+ |
| Failover | Ordered waterfall; slow lanes demoted and recovered on their own | Provider fallbacks, models fallback list |
| Zero data retention | Pro: org switch or provider.zdr; x-gateway-zdr on every response | Org setting or provider.zdr |
| No-training routing | Every plan | Privacy setting |
| Spend limits | Per-key daily, weekly, monthly, yearly caps; budgets | Per-key limits, guardrail budgets |
| Content guardrails | Standard pack or your own classifier, per key | Budget, access and moderation policies |
| SSO | Not yet available | Enterprise |
Where Experiential is better
- No fee on your own keys, at any volume. See Plans and pricing.
- Proof on every response.
x-gateway-providerandx-gateway-zdrname the provider that served the request and its zero-retention verdict. See Data controls. - Native Gemini at
/v1betabeside native Messages, reaching every catalog model. - Slow lanes are demoted automatically, not just failed ones. See Routing and failover.
When OpenRouter may fit better
You need SSO or SAML today, or a provider we do not list.
Migration notes
| What | OpenRouter | Experiential |
|---|---|---|
| Base URL | https://openrouter.ai/api/v1 | https://api.experientiallabs.ai/api/v1 (same paths) or /v1 |
| Anthropic SDK base | https://openrouter.ai/api | https://api.experientiallabs.ai (no /v1) |
| Auth | Authorization: Bearer sk-or-v1-... | Authorization: Bearer YOUR_API_KEY |
| Model ids | vendor/model | vendor/slug works when listed in GET /api/v1/models; use its canonical_slug otherwise |
| Variants | :nitro, :floor, :online, :thinking | Remove them; only :free and, where a model lists it, :fast exist |
usage: {"include": true} | Adds usage | Accepted and ignored; usage and usage.cost are always there |
provider object | Routing preferences | Ignored, except provider: {"zdr": true} |
models fallback list | Model fallbacks | Use the first model; failover is automatic |
HTTP-Referer, X-Title | App attribution | Accepted, not shown |
/generation, /credits, /auth/key, /activity | Account reads | /generation, /credits, /key, /activity under /api/v1 |
Switch with an agent
Paste this into your coding agent. It inventories the project first and asks before anything it cannot map.
GET/api/v1/modelscurl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "openai/gpt-6-luna:nitro",
"messages": [{"role": "user", "content": "Hello"}],
"provider": {"order": ["azure"], "zdr": true},
"usage": {"include": true}}'Sources, checked 2026-11-19
- OpenRouter pricing: plans, 5.5% and 8% platform fees, BYOK allowance, 600+ models, 80+ providers, SSO on Enterprise.
- OpenRouter FAQ: credit fee, BYOK fee, data retention tiers.
- Anthropic Messages, Responses, embeddings, batch API.
- Provider routing, ZDR, guardrails, prompt caching.
- Experiential: /llms.txt, GET /api/models (
total: 980).