DeepSeek V3
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 reveal that the model outperforms other open-source models and rivals leading closed-source models. For model details, please visit [the DeepSeek-V3 repo](https://github.com/deepseek-ai/DeepSeek-V3) for more information, or see the [launch announcement](https://api-docs.deepseek.com/news/news1226).
Specifications
Modalities
Supported Parameters
Max Output Tokens
163,840Data policy
- Prompt retention
- Unknown — we could not confirm
- Training
- Unknown — not declared
"Unknown" does not mean "safe". It means we could not confirm it.
Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.
Frequently asked questions
- Is DeepSeek V3 available on FastMetal?
- Not at the moment. DeepSeek V4.1 Flash, from the same lab, is available on the FastMetal API today.
- What is the context window of DeepSeek V3?
- 163,840 tokens, shared between the prompt and the response.
- How does DeepSeek V3 rank?
- #181 on the public arena's Japanese board (ELO 1,287). Ranks move as the leaderboard is updated.
Leaderboard
Rankings: LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, snapshot 2026-10-22; category names mapped and ratings rounded by FastMetal.