Model
Model
deepseek
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
| Provider | Quantization | Input / M tokens | Output / M tokens |
|---|---|---|---|
| GMICloudgmicloud/fp8 | fp8 | $0.2088 | $0.3096 |
| SiliconFlowsiliconflow/fp8 | fp8 | $0.259 | $0.80 |
| AtlasCloudatlas-cloud/fp8 | fp8 | $0.26 | $0.38 |
| DeepInfradeepinfra/fp4 | fp4 | $0.26 | $0.38 |
| Venicevenice | — | $0.26829 | $0.39024 |
| Baidubaidu/fp8 | fp8 | $0.28 | $0.42 |
| DigitalOceandigitalocean | — | $0.30 | $0.96 |
| Friendlifriendli | — | $0.50 | $1.50 |
| Googlegoogle-vertex | — | $0.56 | $1.68 |
| Phalaphala | — | $1.00 | $1.00 |
| Maramara | — | $3.00 | $4.50 |
| SambaNovasambanova | — | $3.00 | $4.50 |
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.