DeepSeek-V2
DeepSeek ·
Verified
3 of 3 published values traced to a source2 primary sources, 2 archived
Why this status
Every value this record asserts — date (2024-05-06), context window (128K) and parameter count (236B) — was found in an archived primary source, checked 2026-08-10. Modalities recorded as text-to-text. No image, audio or video capability appears anywhere in the primary sources, which labs advertise prominently when present. Capabilities evidenced from the primary sources: coding: “As illustrated, DeepSeek-V2 demonstrates considerable proficiency in LiveCodeBench, achieving a Pass@1 score that surpasses several other sophisticated models.”.
What these states mean · How records are judged · Has this record changed?
An efficient 236B MoE with 21B active parameters that made DeepSeek a global open-model force.
Details
| Released | May 6, 2024stated in huggingface.coDeepSeek-V2 was released on May 6, 2024.
|
|---|---|
| Company | DeepSeek |
| Family | DeepSeek |
| Lineage | before DeepSeek-V2.5 |
| Era | Multimodal & open weights |
| Type | Language model · LLM |
| Modalities | Text → Text |
| Capabilities | Coding |
| Weights | Open weights |
| Licence | DeepSeek License Agreement 1.0 |
| Context window | 128K tokensstated in arxiv.org, huggingface.coDeepSeek-V2 supports a context window of 128,000 tokens.
|
| Parameters | 236Bstated in arxiv.org, huggingface.coDeepSeek-V2 has 236,000,000,000 parameters.
|
Current information, elsewhere
This record is a historical one: every figure above is traced to a dated primary source. For what is true today — live pricing, current rankings, availability — these are better maintained than anything here could be.
- Current price and providers OpenRouter ↗
- Current benchmark scores Artificial Analysis ↗
- Weights and model card Hugging Face ↗
Sources
Record status: verified · confidence 90/100 · 2 of 2 primary
Every value this record asserts — date (2024-05-06), context window (128K) and parameter count (236B) — was found in an archived primary source, checked 2026-08-10. Modalities recorded as text-to-text. No image, audio or video capability appears anywhere in the primary sources, which labs advertise prominently when present. Capabilities evidenced from the primary sources: coding: “As illustrated, DeepSeek-V2 demonstrates considerable proficiency in LiveCodeBench, achieving a Pass@1 score that surpasses several other sophisticated models.”.
- arxiv.org Technical paper archived
- huggingface.co Model card archived
Primary means published by the organisation that made the model. Verified records require at least one.
DeepSeek family
- DeepSeek-V2 May 6, 2024
- DeepSeek-V2.5 September 5, 2024
- DeepSeek-V3 December 26, 2024
- DeepSeek-R1 January 20, 2025
- DeepSeek-V3.1 August 21, 2025
- DeepSeek V4 Flash April 24, 2026
- DeepSeek-V4.1-Flash September 10, 2026
Compare DeepSeek-V2 with another model →
See DeepSeek-V2 on the interactive timeline →