Same open weights, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | moonshotai/Kimi-K2.6 | flexFP40.8× standard | $0.60 | $2.8 | $0.12 | $1.15 | Verified 4h ago · Changed 7h ago | |
DeepInfra | moonshotai/Kimi-K2.6 | standardFP4 | $0.75 | $3.5 | $0.15 | $1.44 | Verified 4h ago · Changed 7h ago | |
Azure AI Foundry Fireworks on Azure | kimi-k2.6 | standarddata zone (US)Quantization not disclosed | $1.04 | $4.4 | $0.176 | $1.88 | Verified 4h ago · Changed 7h ago | |
DeepInfra | moonshotai/Kimi-K2.6 | priorityFP41.5× standard | $1.13 | $5.25 | $0.225 | $2.16 | Verified 4h ago · Changed 7h 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.
| DeepInfra fp4 | $145/mo |
| Azure AI Foundry data zone (US) | $192.5/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.