Same open weights, served by 4 providers. Weights: deepseek-ai/DeepSeek-R1.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2025-12-11 | deepseek-ai/DeepSeek-R1 | standardFP4 | $0.70 | $2.4 | — | $1.13 | Verified 5h ago · Changed 7h ago | |
DeepInfra Deprecated, 2025-12-11 | deepseek-ai/DeepSeek-R1-Turbo | standardFP4Reduced context (41k of 128k) | $1.0 | $3.0 | — | $1.5 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | deepseek-r1 | standardglobal endpointQuantization not disclosed | $1.35 | $5.4 | — | $2.36 | Verified 5h ago · Changed 7h ago | |
AWS Bedrock | deepseek.r1-v1:0 | standardQuantization not disclosed | $1.35 | $5.4 | — | $2.36 | Verified 7h ago · Changed 7h ago | |
AWS Bedrock | us.deepseek.r1-v1:0 | standardQuantization not disclosed | $1.35 | $5.4 | — | $2.36 | Verified 7h ago · Changed 7h ago | |
Azure AI Foundry | deepseek-r1 | standardeastusQuantization not disclosed | $1.49 | $5.94 | — | $2.6 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | deepseek-r1 | standarddata zone (US)Quantization not disclosed | $1.49 | $5.94 | — | $2.6 | Verified 5h ago · Changed 7h ago | |
Together AI Deprecated | deepseek-ai/DeepSeek-R1 | standardQuantization not disclosed | $3.0 | $7.0 | — | $4.0 | 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 | $118/mo |
| DeepInfra fp4 | $160/mo |
| Azure AI Foundry global endpoint | $243/mo |
| AWS Bedrock | $243/mo |
| AWS Bedrock | $243/mo |
| Azure AI Foundry eastus | $267.3/mo |
| Azure AI Foundry data zone (US) | $267.3/mo |
| Together AI | $440/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.