Code & developer
Cloud & AI models benchmark
Cloud pricing, AI models and model marketplaces. Every cloud & AI models provider in Alexandria, compared on quality, speed and cost from real agent calls, so your agent can pick the right one.
- Providers
- 7
- 5 with enough calls to rank
- Calls
- 1.3K
- Last 24 hours
- Top quality
- 100%
- Ollama model library
- Fastest
- 798 ms
- Ollama model library
Leaderboard
Ranked by quality on cloud & AI models tools only, not each provider as a whole.
| # | Provider | Quality | Speed | Cost | Calls |
|---|---|---|---|---|---|
| 1 | 100% | 798 ms | 5 credits | 69 | |
| 2 | 99.4% | 1.1 s | 5 credits | 335 | |
| 3 | 99% | 14.7 s | 5 credits | 516 | |
| 4 | 98.6% | 30.5 s | 5 credits | 221 | |
| 5 | 95.9% | 1.2 s | 5 credits | 121 |
Fewer than 20 calls to rank yet: Oracle Cloud Infrastructure price list (apexapps.oracle.com), IBM Cloud Global Catalog pricing (globalcatalog.cloud.ibm.com).
Tools in this benchmark
The endpoints agents call for cloud & AI models, busiest first.
| Tool | Provider | Quality | Speed | Calls |
|---|---|---|---|---|
| Search models | Artificial Analysis | 99.1% | 617 ms | 316 |
| Search | Google Cloud SKU list prices | 98.6% | 30.5 s | 221 |
| Model | Hugging Face | 99.4% | 264 ms | 164 |
| Get model | Artificial Analysis | 98.8% | 45.5 s | 162 |
| Models | Hugging Face | 99.2% | 205 ms | 119 |
| Card | Hugging Face | 100% | 5.9 s | 52 |
| Search models | OpenRouter | 92.2% | 1.9 s | 51 |
| Get model | OpenRouter | 100% | 717 ms | 46 |
| Model tags | Ollama model library | 100% | 1.1 s | 45 |
| List model providers | Artificial Analysis | 100% | 531 ms | 38 |
| Model | Ollama model library | 100% | 186 ms | 24 |
| Get model endpoints | OpenRouter | 95.8% | 393 ms | 24 |
How we measure
- Quality
- Calls answered without a tool error, on this use case's tools.
- Speed
- P95 latency: 95% of successful calls finish faster.
- Cost
- Firecrawl credits per call, from the catalogue.
Measured over last 24 hours of calls through Alexandria by every user. A provider needs at least 20 calls on these tools to rank; the rest are listed under the table.
More Code & developer benchmarks
- Code & packages5 providers · 7.2K calls
- Apps3 providers · 1.8K calls
- Developer docs14 providers · 1.3K calls
- Security & vulnerabilities5 providers · 209 calls
See every use case on the benchmarks and rankings pages.
//
Get started
//
Start building with Alexandria.
Give your AI agent direct access to the sources it needs.
Are you an AI agent? See setup options