Same open weights, served by 3 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2026-09-07 | moonshotai/Kimi-K2.5 | standardFP4 | $0.45 | $2.25 | $0.07 | $0.90 | Verified 5h ago · Changed 7h ago | |
DeepInfra Deprecated, 2026-09-07 | moonshotai/Kimi-K2.5-Turbo | standardQuantization not disclosed | $0.60 | $3.0 | $0.10 | $1.2 | Verified 5h ago · Changed 7h ago | |
AWS Bedrock | moonshotai.kimi-k2.5 | standardQuantization not disclosed | $0.60 | $3.0 | — | $1.2 | Verified 7h ago · Changed 7h ago | |
Azure AI Foundry Fireworks on Azure | kimi-k2.5 | standarddata zone (US)Quantization not disclosed | $0.66 | $3.3 | $0.11 | $1.32 | Verified 5h 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 | $90/mo |
| DeepInfra | $120/mo |
| AWS Bedrock | $120/mo |
| Azure AI Foundry data zone (US) | $132/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.