Most "enterprise AI" demos are a sales deck.
Here's 6 minutes of the actual product:
→ spend + tokens broken down by model, per project, per user, per api key....
→ restrict routing by provider HQ country, compliance policy, ZDR....
→ SAML SSO with Microsoft Entra
→ per-developer budgets, IAM rules on every key
No slides. Just the dashboard.
Your usage comparisons don’t have to follow the calendar anymore. 📊
In @llmgateway, you can now choose the exact start date for week-over-week or month-over-month comparisons, making changes in token usage and cost much easier to spot.
Should be live soon
lol what, are you that far behind?
1. Get @LLMDevPass for x3 usage
2. Use GLM 5.3 and GLM 5.3 Flash (50% off until 9th September)
- https://t.co/wD0qJqeTgK
- https://t.co/omt4eLpT55
Works with any coding agent
7 days on the gateway: 119.6B tokens, 3.9M requests, 163 models ranked.
#1 was DeepSeek V4 Flash at 17.3B — down 22.8% from last week and still on top.
Nothing grew like GLM-5.3: +429.7%.
The board doesn't reward incumbency.
Your default model has a shelf life.
Last 24h on the gateway: 19.2B tokens, 560.1K requests, 102 models ranked.
GLM-5.3 Flash took #1 with 17.4% of all tokens, up 148.1%.
Last generation's GLM-5.2: down 49.5%.
Hardcode one model and you're pinned to last month's board.
New for DevPass: No AI training
Enable it in Settings to route only through providers that explicitly state API inputs aren’t used for training. Providers with unknown policies are excluded, so some models may become unavailable.
Available on every DevPass tier. DevPass remains metadata-only as before.
Learn more: https://t.co/xwwclLx9vZ
The models directory gained lifecycle status filters, model pages sort providers by price, speed, or context, and API key lists flag the keys that are near or at their limit.
Check yourself: https://t.co/lVjGQB33ah
Hash-Only API Key Storage
Gateway API keys are now stored only as keyed HMAC-SHA-256 fingerprints and provider credentials only as AES-256-GCM ciphertext. Every plaintext read path is gone, so a key's secret is visible exactly once per issuance — at creation or roll.
Learn more: https://t.co/5BmkN0SbYJ
Yesterday's #1 model is today's #5.
24h on the gateway: 17.4B tokens, 517.1K requests, 109 models.
Gemini 3.7 Flash took the crown at 2.7B.
GLM-5.3: +177.2%
GLM-5.3 Flash went from zero to #6 in a day.
Annual model commitments age fast.
Organization Teams and Directory Sync
Group developers under one shared policy — a project ceiling, per-developer budgets, and IAM rules — instead of configuring each person by hand. Microsoft Entra groups map onto teams over SCIM, and a default team catches everyone who joins without one. Available on the Enterprise plan.
Learn more: https://t.co/PxIzDgL7Us
Docs: https://t.co/M7cTPABu9G