Model
Model
deepseek
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
| Provider | Quantization | Input / M tokens | Output / M tokens |
|---|---|---|---|
| OpenInferenceopen-inference/fp4 | fp4 | $0.03423 | $0.375 |
| Baidubaidu/fp8 | fp8 | $0.0489 | $0.1956 |
| Relacerelace | — | $0.07 | $0.50 |
| Decartdecart/fp4 | fp4 | $0.09 | $0.18 |
| Sail Researchsail-research/fp4 | fp4 | $0.101 | $0.15 |
| Sail Researchsail-research/fp4/us | fp4 | $0.101 | $0.15 |
| InferenceNetinference-net/fp8 | fp8 | $0.103 | $0.715 |
| InferenceNetinference-net/us | fp8 | $0.103 | $0.715 |
| DeepInfradeepinfra/fp8/flex | fp8 | $0.112 | $0.336 |
| AtlasCloudatlas-cloud/fp8 | fp8 | $0.135 | $0.54 |
| DeepInfradeepinfra/fp8 | fp8 | $0.14 | $0.42 |
| StreamLakestreamlake/fp8 | fp8 | $0.147 | $0.588 |
| CoreWeavecoreweave/fp8 | fp8 | $0.15 | $0.65 |
| GMICloudgmicloud/fp8 | fp8 | $0.18 | $0.72 |
| Waferwafer/mxfp4 | mxfp4 | $0.19 | $0.65 |
| Novitanovita/fp8 | fp8 | $0.195 | $0.78 |
| DeepInfradeepinfra/fp8/priority | fp8 | $0.21 | $0.63 |
| Fireworksfireworks/spot | — | $0.21 | $0.84 |
| Phalaphala | — | $0.21 | $0.84 |
| DigitalOceandigitalocean | — | $0.225 | $0.90 |
| Morphmorph/fp8 | fp8 | $0.228 | $0.60 |
| Makoramakora/fp8 | fp8 | $0.26 | $1.17 |
| Crusoecrusoe/fp8 | fp8 | $0.29 | $1.20 |
| BaseTenbaseten | — | $0.30 | $1.20 |
| BaseTenbaseten/us | — | $0.30 | $1.20 |
| Fireworksfireworks | — | $0.30 | $1.20 |
| Googlegoogle-vertex/global | — | $0.30 | $1.20 |
| Ionstreamionstream | — | $0.30 | $1.20 |
| Modalmodal | — | $0.30 | $1.20 |
| Nebiusnebius/fp8 | fp8 | $0.30 | $1.20 |
| Parasailparasail/fp8 | fp8 | $0.30 | $1.20 |
| PrimeIntellectprimeintellect | — | $0.30 | $1.20 |
| SiliconFlowsiliconflow/fp8 | fp8 | $0.30 | $1.20 |
| Togethertogether | — | $0.30 | $1.20 |
| Venicevenice/fp8 | fp8 | $0.30 | $1.20 |
| Alibabaalibaba | — | $0.33 | $1.32 |
| Fireworksfireworks/us | — | $0.45 | $1.80 |
| BaseTenbaseten/fast | — | $0.60 | $2.40 |
Prices are what the Provider charges, synced 2026-10-21. Amber adds its platform fee to each Trial’s total; see pricing.
Amber has no curated Model Configuration for this Model yet. Create a custom one in your Workspace to evaluate it.