DeepSeek: DeepSeek V3 0324
by DeepSeekDeepSeek: DeepSeek V3 0324 is a large language model from DeepSeek. It costs $0.250 per million input tokens and $1.00 per million output tokens. Its context window is 164K tokens.
- Input / 1M tokens
- $0.250
- Output / 1M tokens
- $1.00
- Cached input / 1M
- -
- Context window
- 164K
Not supported
tokens
Who serves it cheapest
4 hosts serve DeepSeek V3 0324. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| DeepInfraCheapestfp4 | $0.240 | $0.900 | 164K | - | 84.0% |
| SiliconFlowfp8 | $0.250 | $1.00 | 164K | - | 99.0% |
| GMICloudfp8 | $0.290 | $1.14 | 164K | - | 98.5% |
| Crusoebf16 | $0.500 | $1.50 | 164K | - | 100.0% |
The spread between DeepInfra and Crusoe is 1.9× for identical weights. Quantization and context limits differ, so check both columns before switching.
Benchmarks
Independent scores published alongside the catalogue.
- Intelligence index
- 9.7
- Coding index
- 21.2
- Agentic index
- 0.8
About DeepSeek V3 0324
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...
Specifications
| Model ID | deepseek/deepseek-chat-v3-0324 |
|---|---|
| Provider | DeepSeek |
| Context window | 164K tokens |
| Max output | 147K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | 2024-07-31 |
| Open weights | Yes - deepseek-ai/DeepSeek-V3-0324 |
| Released | March 24, 2025 |
Cheaper alternatives
Models that cost less than DeepSeek V3 0324 while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does DeepSeek: DeepSeek V3 0324 cost?
$0.250 per million input tokens and $1.00 per million output tokens.
What is the context window of DeepSeek: DeepSeek V3 0324?
164K tokens, with up to 147K tokens of output per request.
Which provider serves DeepSeek: DeepSeek V3 0324 cheapest?
DeepInfra at $0.240 per million input tokens - 1.9× cheaper than Crusoe, the most expensive of the 4 hosts serving it.
Confirm against the source: DeepSeek official pricing.