Same model, served by 1 provider.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Azure AI Foundry | grok-code-fast-1 | standardglobal endpointQuantization not disclosed | $0.20 | $1.5 | โ | $0.525 | Verified 12h ago ยท Changed 40d ago | |
Azure AI Foundry | grok-code-fast-1 | standarddata zone (US)Quantization not disclosed | $0.22 | $1.65 | โ | $0.578 | Verified 12h ago ยท Changed 40d ago |
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| Azure AI Foundry global endpoint | $50/mo |
| Azure AI Foundry data zone (US) | $55/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.