Pro
deepseek-ai/DeepSeek-V3
Flagship DeepSeek model for coding, reasoning, and agentic work
Cheapest input
$0.25
$/MTok · models.dev
Cheapest output
$1
$/MTok
Context
164K
tokens
Offers
5
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.devcheapestPro/deepseek-ai/DeepSeek-V3 | SiliconFlow (China) | $0.25 | $1 | $0 | 164K |
| models.devdeepseek-ai/DeepSeek-V3 | SiliconFlow | $0.25 | $1 | $0 | 164K |
| LiteLLMdeepseek-ai/DeepSeek-V3 | — | $0.38 | $0.89 | $0.038 | — |
| models.devdeepseek-ai/DeepSeek-V3 | Together AI | $1.25 | $1.25 | $0 | 131K |
| LiteLLMdeepseek-ai/deepseek-v3 | — | $1.45 | $1.45 | $0.145 | — |
Capabilities
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Knowledge cutoff: 2024-07Released: 2024-12-26Family: deepseek