Same open weights, served by 1 provider.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | deepseek-ai/DeepSeek-R1-0528 | standardFP4 | $0.50 | $2.15 | $0.35 | $0.912 | Verified 4h ago · Changed 7h ago | |
DeepInfra Deprecated, 2026-05-21 | deepseek-ai/DeepSeek-R1-0528-Turbo | standardFP4Reduced context (33k of 164k) | $1.0 | $3.0 | — | $1.5 | Verified 4h 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 | $93/mo |
| DeepInfra fp4 | $160/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.