DeepSeek
DeepSeek V3.2
Released 2025-12-01
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...
You send / 1M
$0.280
tokens in
It replies / 1M
$0.420
tokens out
Memory
164K
tokens it can read at once
Typical request
$0.0006
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · fp4 | $0.260 | $0.380 | 99% | Read |
| Venice | $0.268 | $0.390 | 99% | Read |
| SiliconFlow · fp8 | $0.259 | $0.800 | 100% | Read |
| DigitalOcean | $0.300 | $0.960 | 99% | Read |
| Phala | $1.00 | $1.00 | 100% | Read |
| $0.560 | $1.68 | 0% | Read | |
| Mara | $3.00 | $4.50 | 100% | Read |
| SambaNova | $3.00 | $4.50 | 81% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 66K tokens
- Repeated text is billed at $0.028 per 1M (prompt caching)
- Intelligence score: 21.5 / 100 (Artificial Analysis)
Similar models
- DeepSeek V3.2 ExpDeepSeek · $0.270 in / $0.410 out per 1M
- GLM 4.7 FlashZ.ai · $0.060 in / $0.400 out per 1M
- Nemotron 3 SuperNVIDIA · $0.080 in / $0.450 out per 1M
- LFM2.5-2.6BLiquid · $0.350 in / $0.500 out per 1M
- Qwen3 30B A3BQwen · $0.120 in / $0.500 out per 1M
- Mercury 3Inception · $0.100 in / $0.350 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap AI ModelsTop No-Training Zero Data Retention Reasoning AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Cheap AI ModelsTop No-Training Cheap Reasoning AI ModelsTop No-Training Cheap Tool-Calling AI Models