DeepSeek: DeepSeek V3deepseek
Bottom Line
DeepSeek: DeepSeek V3: $0.26/1M input, $1.03/1M output, 164K context. DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...
API Pricing (per 1M tokens)
| Input | $0.26 |
| Output | $1.03 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.45 |
Specs & Performance
| Context Length | 164K |
| Max Output | 16K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text → text |
More from deepseek
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the DeepSeek: DeepSeek V3 API cost?
DeepSeek: DeepSeek V3 costs $0.26/1M input tokens and $1.03/1M output tokens. Blended cost at a 3:1 ratio is about $0.45/1M tokens.
What is the context window of DeepSeek: DeepSeek V3?
DeepSeek: DeepSeek V3 supports a 164K token context window with up to 16K output tokens.
Is DeepSeek: DeepSeek V3 worth it?
DeepSeek: DeepSeek V3 has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.