Same open weights, served by 3 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | deepseek-ai/DeepSeek-V3.2 | standardFP4 | $0.26 | $0.38 | $0.13 | $0.29 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | deepseek-v3.2 | standardglobal endpointQuantization not disclosed | $0.58 | $1.68 | — | $0.855 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry Fireworks on Azure | deepseek-v3.2 | standarddata zone (US)Quantization not disclosed | $0.62 | $1.85 | — | $0.927 | Verified 5h ago · Changed 7h ago | |
AWS Bedrock | deepseek.v3.2 | standardQuantization not disclosed | $0.62 | $1.85 | — | $0.927 | Verified 7h 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 | $33.6/mo |
| Azure AI Foundry global endpoint | $91.6/mo |
| Azure AI Foundry data zone (US) | $99/mo |
| AWS Bedrock | $99/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.