Same open weights, served by 2 providers. Weights: deepseek-ai/DeepSeek-V3-0324.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2026-09-29 | deepseek-ai/DeepSeek-V3-0324 | standardFP4 | $0.24 | $0.90 | $0.135 | $0.405 | Verified 5h ago · Changed 7h ago | |
DeepInfra Deprecated, 2026-09-29 | deepseek-ai/DeepSeek-V3-0324-Turbo | standardFP4Reduced context (33k of 164k) | $1.0 | $3.0 | — | $1.5 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | deepseek-v3-0324 | standardglobal endpointQuantization not disclosed | $1.14 | $4.56 | — | $1.99 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | deepseek-v3-0324 | standarddata zone (US)Quantization not disclosed | $1.25 | $5.0 | — | $2.19 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | deepseek-v3-0324 | standardeastusQuantization not disclosed | $1.25 | $5.0 | — | $2.19 | 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 | $42/mo |
| DeepInfra fp4 | $160/mo |
| Azure AI Foundry global endpoint | $205.2/mo |
| Azure AI Foundry data zone (US) | $225/mo |
| Azure AI Foundry eastus | $225/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.