DeepSeek
DeepSeek V3.2
deepseek/deepseek-v3.2
Input
$0.28
per 1M tokens
Output
$0.42
per 1M tokens
Gecachete input
$0.028
per 1M tokens
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...
De onderstaande beschrijving is overgenomen van OpenRouter en is in het Engels.
- Uitgebracht
- Context window
- 164K tokens
- Max. output
- 66K tokens
- Input
- tekst
- Output
- tekst
- Reasoning
- Ja
Prijshistorie
Geen prijswijzigingen sinds het begin van onze metingen op .
Aanbieders op OpenRouter
9 endpoints bieden dit model aan. Uptime is het aandeel geslaagde verzoeken via OpenRouter; prijzen per 1M tokens.
| Aanbieder | Input | Output | Context window | Uptime 30 min | Uptime 24 uur |
|---|---|---|---|---|---|
| GMICloudfp8 | $0.209 | $0.31 | 164K | 100% | 99.38% |
| DeepInfrafp4 | $0.26 | $0.38 | 164K | 100% | 99.51% |
| AtlasCloudfp8 | $0.26 | $0.38 | 164K | 80.0% | 98.3% |
| Baidufp8 | $0.28 | $0.42 | 131K | 100% | 99.84% |
| SiliconFlowfp8 | $0.259 | $0.80 | 164K | 100% | 99.79% |
| DigitalOcean | $0.30 | $0.96 | 164K | 86.7% | 97.3% |
| Phala | $1.00 | $1.00 | 164K | — | 100% |
| Mara | $3.00 | $4.50 | 33K | — | 100% |
| SambaNova | $3.00 | $4.50 | 33K | 96.4% | 89.5% |