DeepSeek V3.2
DeepSeek chat model for instruction following, coding, and analysis
Cheapest input
$0.26
$/MTok · models.dev
Cheapest output
$0.38
$/MTok
Context
164K
tokens
Offers
9
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestdeepseek-ai/DeepSeek-V3.2 | DeepInfra | $0.26 | $0.38 | $0.13 | 164K |
| models.devdeepseek-ai/DeepSeek-V3.2 | Meganova | $0.26 | $0.38 | $0 | 164K |
| models.devdeepseek-ai/DeepSeek-V3.2 | Abacus | $0.27 | $0.4 | $0 | 128K |
| models.devdeepseek-ai/DeepSeek-V3.2 | SiliconFlow (China) | $0.27 | $0.42 | $0 | 164K |
| models.devdeepseek-ai/DeepSeek-V3.2 | SiliconFlow | $0.27 | $0.42 | $0 | 164K |
| models.devdeepseek-ai/DeepSeek-V3.2 | Hugging Face | $0.28 | $0.4 | $0 | 164K |
| LiteLLMdeepseek-ai/DeepSeek-V3.2 | — | $0.28 | $0.4 | $0.028 | — |
| models.devdeepseek-ai/DeepSeek-V3.2 | Nebius | $0.3 | $0.45 | $0.03 | 163K |
| models.devdeepseek-ai/DeepSeek-V3.2 | Friendli | $0.5 | $1.50 | $0.25 | 164K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Knowledge cutoff: 2024-12Released: 2025-06-15Family: deepseek
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence32
- AA coding44.2
- AA agentic18.3
Sources: Arena AI, Artificial Analysis. See /benchmarks.