Model
Model
deepseek
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...
| Provider | Quantization | Input / M tokens | Output / M tokens |
|---|---|---|---|
| OpenInferenceopen-inference/fp4 | fp4 | $0.049 | $0.375 |
| Relacerelace | — | $0.07 | $0.50 |
| DeepInfradeepinfra/fp8/flex | fp8 | $0.0784 | $0.2352 |
| InferenceNetinference-net/fp8 | fp8 | $0.08 | $0.50 |
| InferenceNetinference-net/us | fp8 | $0.08 | $0.50 |
| Decartdecart/fp4 | fp4 | $0.09 | $0.18 |
| DeepInfradeepinfra/fp8 | fp8 | $0.098 | $0.294 |
| Cloudflarecloudflare | — | $0.10 | $0.60 |
| DeepInfradeepinfra/fp8/priority | fp8 | $0.147 | $0.441 |
| DeepSeekdeepseek | — | $0.15 | $0.60 |
| Rekareka | — | $0.15 | $0.60 |
| Waferwafer/mxfp4 | mxfp4 | $0.16 | $0.50 |
| AtlasCloudatlas-cloud/fp8 | fp8 | $0.195 | $0.78 |
| Morphmorph/fp8 | fp8 | $0.228 | $0.60 |
| Crusoecrusoe/fp8 | fp8 | $0.29 | $1.20 |
| BaseTenbaseten | — | $0.30 | $1.20 |
| Fireworksfireworks | — | $0.30 | $1.20 |
| GMICloudgmicloud/fp8 | fp8 | $0.30 | $1.20 |
| Ionstreamionstream | — | $0.30 | $1.20 |
| Novitanovita/fp8 | fp8 | $0.30 | $1.20 |
| Parasailparasail/fp8 | fp8 | $0.30 | $1.20 |
| Phalaphala | — | $0.30 | $1.20 |
| PrimeIntellectprimeintellect | — | $0.30 | $1.20 |
| SiliconFlowsiliconflow/fp8 | fp8 | $0.30 | $1.20 |
| Togethertogether | — | $0.30 | $1.20 |
| Alibabaalibaba | — | $0.33 | $1.32 |
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.