← Model list
Pro/deepseek-ai/DeepSeek-V3
deepseek·deepseek/deepseek-v3-3·GA·Closed·deepseek series
Flagship DeepSeek model for coding, reasoning, and agentic work
At a glance
Reference price$0.25 / $1.00 per 1M
Cache read — · SiliconFlow (China)
Lowest paid$0.25 / $1.00
SiliconFlow (China) Cloud
Context164,000
Output limit164,000
Capabilities
Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text
Knowledge cutoff—
Released / updated2024-12-26 / 2025-11-25
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 1 providers1 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| SiliconFlow (China) Pro/deepseek-ai/DeepSeek-V3 | Cloud | $0.25 | $1.00 | — | — | 164,000 | 164,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1SiliconFlow (China)$100.00
The cheapest paid channel is the only channel.
Related models
DeepSeek V4 Flash Latestsame series$0.14 / $0.28DeepSeek V3.2 TEEsame series$1.00 / $1.00DeepSeek V4 Flash 0423same series$0.138 / $0.275Qwen3-Next 80B-A3B Instructcheaper alternative$0.144 / $0.574Llama-3.1-8B-Instructcheaper alternative$0.15 / $0.45Qwen3 Coder Flashcheaper alternative$0.144 / $0.574Llama 3.2 3B Instructcheaper alternative$0.10 / $0.335
Price historyone sample accumulated per data sync
Input listOutput listMin blended