Same open weights, served by 3 providers. Weights: deepseek-ai/DeepSeek-V4.1-Flash-1017.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Promo pricing | deepseek-ai/DeepSeek-V4.1-Flash-1017 | flexFP80.8× standard | $0.16 | $0.48 | $0.0048 | $0.24 | Verified 12h ago · Changed 36d ago | |
Fireworks AI | accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot | standardQuantization not disclosed | $0.15 | $0.60 | $0.0030 | $0.262 | Verified 12h ago · Changed 47h ago | |
DeepInfra Promo pricing | deepseek-ai/DeepSeek-V4.1-Flash-1017 | standardFP8 | $0.20 | $0.60 | $0.0060 | $0.30 | Verified 12h ago · Changed 36d ago | |
DeepInfra Promo pricing | deepseek-ai/DeepSeek-V4.1-Flash-1017 | priorityFP81.5× standard | $0.30 | $0.90 | $0.0090 | $0.45 | Verified 12h ago · Changed 36d ago | |
Fireworks AI | accounts/fireworks/models/deepseek-v4p1-flash-1017 | standardQuantization not disclosed | $0.30 | $1.2 | $0.0060 | $0.525 | Verified 12h ago · Changed 35d ago | |
Mistral | deepseek-v4-1-flash-1017 | standardQuantization not disclosed | $0.30 | $1.2 | $0.0070 | $0.525 | Verified 12h ago · Changed 24d ago | |
Fireworks AI | accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast | standardQuantization not disclosed | $1.2 | $4.8 | $0.024 | $2.1 | Verified 12h ago · Changed 47h 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.
| Fireworks AI | $27/mo |
| DeepInfra fp8 | $32/mo |
| Fireworks AI | $54/mo |
| Mistral | $54/mo |
| Fireworks AI | $216/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.