Skip to content
Solutions
Platform
LLM Gateway Routing
Route to 600+ models intelligently
Analytics
Real-time LLM observability
Integrations
OpenAI-compatible, works with any SDK
EU Data Residency
GDPR-compliant EU hosting
For your team
Enterprise
SSO, RBAC, audit logs and budget controls
Security
Encryption, retention and access control
Speak to Founders
Schedule a call with our team
Models
EU
Customers
Pricing
Rankings
Resources
Blog
Guides, benchmarks and release notes
Join Discord
Ask us and other users directly
Docs
Sign in
Get started free
Models
EU
Customers
Pricing
Rankings
LLM Gateway Routing
Analytics
Integrations
Enterprise
Security
Blog
Join Discord
Docs
LLM gateway routing
Analytics
Integrations
Free models
Careers
Sign in
Get started free
Requesty Blog
AI Models
Every post tagged AI Models.
All
168
Best Practices
78
Integrations
58
Routing
39
Agents
38
Requesty Features
31
AI Models
19
Observability
16
Security
13
Cost Optimization
13
Industry
7
Enterprise
6
Pricing
6
AI Gateway
6
Infrastructure
6
2026
19 posts
SEP '26
Which of the smartest models can you run inside the EU, and what is the residency premium?
Enterprise
SEP '26
Claude in the EU: 47 region deployments, one quota wall, and how to fail over without…
AI Models
SEP '26
DeepSeek V4.1 Flash retires V4 Pro by redirect: on 14 September your pinned model id…
AI Models
SEP '26
GLM-5.3 Flash vs DeepSeek V4 Flash 0731: which flash model fits your API workload?
AI Models
SEP '26
GPT-6 Astra is the best model you may not be allowed to call: gated access, the EU gap…
AI Models
SEP '26
The list price is now a range: peak hours, promo windows and host floors
Pricing
SEP '26
GPT-6 Astra scores 61 on the independent index, the same as Sol, at 2.5x the price
AI Models
SEP '26
Record on Terminal-Bench, catastrophic on a private eval: Fable 5.1 and the case for your…
AI Models
SEP '26
Fable 5.1 cut cache reads 75% to $0.25 per million: the launch line nobody screenshotted
Cost Optimization
AUG '26
Five open weight releases in nine days: GLM-5.3-Flash, Qwen3.8-Flash, Hy4 and the…
AI Models
AUG '26
A 320B model trained on Chinese AI chips at 1/100 frontier price: the inference supply…
AI Models
AUG '26
20 trillion tokens in 6 days: what the Ox Alpha stealth launch taught us about model IDs
AI Models
AUG '26
Claude Opus 5 vs GPT-5.6 Sol: API speed, coding and cost
AI Models
AUG '26
Free model IDs now ship with expiry dates: how to use promotional inference without…
AI Models
AUG '26
36x the price for 22% more quality: the Pareto data that should decide your model mix
AI Models
JUL '26
The supply side is exploding: 136 providers, 502 models, and 2,084 client apps in a…
AI Models
JUL '26
No model stays #1: the leader's share of gateway traffic fell from 29% to 8% in eight…
AI Models
JUN '26
Inside Sakana Fugu Ultra: We Reverse Engineered Its Multi Agent Architecture
AI Models
JUN '26
Best AI Coding Model (2026): Benchmarks, Cost, and Real World Performance
AI Models
