Publish Catalog & Pricing
Final admin step — make the factory purchasable
Published models
8
Customer deployments
0
Avg price / 1M tokens
$1.64
Regions served
5
Catalog pricing
What the customer will see on the Models page
| Model | Provider | Price / 1M | Latency | Quality | Availability |
|---|---|---|---|---|---|
| gpt-4o | OpenAI | $5.00 | 1.2s | ★ 9.2 | 99.9% |
| claude-3.5-sonnet | Anthropic | $3.00 | 1.8s | ★ 9 | 99.5% |
| llama-3.1-70b | Meta | $0.80 | 2.3s | ★ 8.7 | 99.8% |
| nemotron-ultra-550b | NVIDIA | $2.40 | 1.5s | ★ 9.1 | 99.7% |
| qwen-2.5-72b | Alibaba | $0.50 | 2.5s | ★ 8.1 | 98.7% |
| deepseek-r1 | DeepSeek | $0.70 | 3.2s | ★ 8.4 | 98.5% |
| phi-3-medium | Microsoft | $0.40 | 2.0s | ★ 7.8 | 98.1% |
| stable-diffusion-3 | Stability AI | $0.30 | 4.5s | ★ 7.5 | 97.6% |
Go-live checklist
- Models registered8 models in catalog
- Routing policy savedStrategy: Balanced
- GPU capacity available64 × B300 · 92% utilised, 8 GPUs headroom
- Tenant entitlements setWallet cap, rate limit and guardrails applied