Same open weights, served by 2 providers. Weights: deepseek-ai/DeepSeek-V3.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | deepseek-ai/DeepSeek-V3 | standardFP4 | $0.32 | $0.89 | — | $0.463 | Verified 5h ago · Changed 7h ago | |
Together AI Deprecated | deepseek-ai/DeepSeek-V3 | standardQuantization not disclosedReduced context (131k of 164k) | $1.25 | $1.25 | — | $1.25 | 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 | $49.8/mo |
| Together AI | $150/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.