DDeepSeek · Released Mar 24, 2025
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...
- Released
- Mar 24 2025
- Context window
- 164K 115K out
- Input / 1M tokens
- $0.29 from $0.25
- Output / 1M tokens
- $1.14 from $1.00
Where to run it
2 providers compared
Cheapest: SiliconFlow at $0.25 / $1.00 per 1M input / output tokens — 13% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| SiliconFlowFP8 | $0.25 | $1.00 | — | 164K | 147K | 100%24h | Cheapest |
| GMICloudFP8 · no tool calling | $0.29 | $1.14 | $0.11 | 128K | 115K | 98.3%24h | +15% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated DeepSeek V3 0324. Scores appear here automatically once it does.
Specs
Details
- Model ID
deepseek/deepseek-chat-v3-0324- Developer
- DeepSeek
- Release date
- Mar 24, 2025 ·
- Context window
- 163,840 tokens
- Max output
- 115,200 tokens
- API price
- $0.29 / $1.14 per 1M input / output tokens
- Providers
- 2
- Input types
- text
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.