Model Tracker
DeepSeek-V2
DeepSeek-V2 is an AI model made by DeepSeek AI. DeepSeek AI released it on 6 May 2024. It takes text and returns text. Its context window is 128,000 tokens.
DeepSeek-V2 is an AI model made by DeepSeek AI. DeepSeek AI released it on 6 May 2024. It takes text and returns text. Its context window is 128,000 tokens. Its weights are open.
- Released
- 6 May 2024 — github.com, read 16 October 2026
- Status
- Not confirmed: two readings disagree: ga and retired
- Takes
- Text — huggingface.co, read 16 October 2026
- Returns
- Text — huggingface.co, read 16 October 2026
- Open weights
- Yes — github.com, read 16 October 2026
- Licence
- Not confirmed: two readings disagree: DEEPSEEK LICENSE AGREEMENT and MIT License (code); Model License (weights)
- Context window
- 128,000 tokens — github.com, read 16 October 2026
- Longest answer
- Not confirmed: The maker's pages reviewed do not print a standard maximum output-token limit for DeepSeek-V2.
- Knowledge cutoff
- Not confirmed: The maker's pages reviewed do not state a knowledge-cutoff date for DeepSeek-V2.
- API price, input
- Not confirmed: The maker's current pricing page does not list a standard API input price for DeepSeek-V2.
- API price, output
- Not confirmed: The maker's current pricing page does not list a standard API output price for DeepSeek-V2.
- Where
- Downloadable weights — github.com, read 16 October 2026
- Parameters
- 236,000,000,000 — github.com, read 16 October 2026
- Model card
- https://huggingface.co/deepseek-ai/DeepSeek-V2 — huggingface.co, read 16 October 2026
Questions
When was DeepSeek-V2 released?
DeepSeek AI released DeepSeek-V2 on 6 May 2024.
What is the context window of DeepSeek-V2?
The context window of DeepSeek-V2 is 128,000 tokens, as DeepSeek AI prints it.
Are the weights of DeepSeek-V2 open?
Yes: DeepSeek AI publishes the weights of DeepSeek-V2 for download.
What does DeepSeek-V2 take and return?
DeepSeek-V2 takes text and returns text.
How many parameters does DeepSeek-V2 have?
DeepSeek-V2 has 236,000,000,000 parameters, as DeepSeek AI publishes it.
More from DeepSeek AI
- DeepSeek Coder
- DeepSeek LLM
- DeepSeek V4 Pro
- DeepSeek-Coder-V2
- DeepSeek-Coder-V2-Lite
- DeepSeek-Math-V2
- DeepSeek-OCR
- DeepSeek-OCR2
- DeepSeek-Prover-V1
- DeepSeek-Prover-V1.5
- DeepSeek-Prover-V2
- DeepSeek-R1
- DeepSeek-V2-Lite
- DeepSeek-V2.5
- DeepSeek-V3
- DeepSeek-V3.1
- DeepSeek-V3.1-Terminus
- DeepSeek-V3.2-Exp
- DeepSeek-V4-Flash
- DeepSeek-V4-Flash-Vision-Exp
- DeepSeek-V4.1-Flash
- DeepSeek-VL
- DeepSeek-VL2
- DeepSeek-VL2-Small
Sources
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model (read 16 October 2026)
- LICENSE-MODEL (read 16 October 2026)
- deepseek-ai/DeepSeek-V2 (read 16 October 2026)
- Change Log (read 16 October 2026)
- Models & Pricing (read 16 October 2026)