Same open weights, served by 2 providers. Weights: moonshotai/Kimi-K2.7-Code.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2026-09-29 | moonshotai/Kimi-K2.7-Code | standardFP4 | $0.68 | $3.4 | $0.136 | $1.36 | Verified 4h ago · Changed 7h ago More prices
| |
Azure AI Foundry | kimi-k2.7-code | standardglobal endpointQuantization not disclosed | $0.95 | $4.0 | $0.19 | $1.71 | Verified 4h ago · Changed 6h ago | |
Azure AI Foundry | kimi-k2.7-code | standarddata zone (US)Quantization not disclosed | $1.04 | $5.0 | $0.209 | $2.03 | Verified 4h ago · Changed 6h 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 | $136/mo |
| Azure AI Foundry global endpoint | $175/mo |
| Azure AI Foundry data zone (US) | $204.5/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.