DeepSeek-V2.5
by DeepSeek
DeepSeek-V2.5 is a model from DeepSeek, released on May 8, 2024. It has a 8K-token context window and can generate up to 8K output tokens. API pricing is $0.14 per 1M input tokens and $0.28 per 1M output tokens.
DeepSeek-V2.5 is an upgraded version that combines DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct, integrating general and coding abilities. It better aligns with human preferences and has been optimized in various aspects, including writing and instruction following.
Key specs
| Provider | DeepSeek |
|---|---|
| Release date | 2024-05-08 |
| License | open weights |
| Context window | 8K tokens |
| Max output | 8K tokens |
| Input price | $0.14 / 1M tokens |
| Output price | $0.28 / 1M tokens |
| Intelligence Score | 8.1 |
| Coding index | 6.3 |
Quick answers
What is the context window of DeepSeek-V2.5?
DeepSeek-V2.5 has a context window of 8K tokens, with a maximum output of 8K tokens per response.
How much does DeepSeek-V2.5 cost?
DeepSeek-V2.5 costs $0.14 per 1M input tokens and $0.28 per 1M output tokens through the API.
Is DeepSeek-V2.5 open source?
Yes. DeepSeek-V2.5 is an open model released under the open weights license.
When was DeepSeek-V2.5 released?
DeepSeek released DeepSeek-V2.5 on May 8, 2024.
Compare on the AI leaderboard · All AI models
More models from DeepSeek
- DeepSeek-V4.1-Flash (Reasoning) — DeepSeek
- DeepSeek-V4-Pro-0813 (Reasoning) — DeepSeek
- DeepSeek-V4-Flash-Vision-Exp (Reasoning) — DeepSeek
- DeepSeek-V4-Flash-0423 (Reasoning) — DeepSeek
- DeepSeek-V3.2 (Thinking) (Reasoning) — DeepSeek
- DeepSeek-R1-0528 — DeepSeek