DE
DeepSeek V2.5 - 236B
Release date: 2024-09-05Updated: 2024-11-23 18:18:231,086
Parameters
236B
Context length
128K
Chinese support
Supported
Reasoning ability
DeepSeek V2.5 - 236B is an AI model published by DeepSeek-AI, released on 2024-09-05, for Foundation model, with 236B parameters, and 128K context length, requiring about 133GB storage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
DeepSeek V2.5
Model basics
Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
No data
Model type
Foundation model
Modality (in / out)
No data
Release date
2024-09-05
Model file size
133GB
MoE architecture
No
Total params / Active params
236B / N/A
Knowledge cutoff
No data
DeepSeek V2.5
Open source & experience
Code license
Weights license
DeepSeek License Agreement- Commercial use permitted
GitHub repo
Hugging Face
Live demo
No live demo
DeepSeek V2.5
Official resources
Paper
DataLearnerAI blog
No blog post yet
DeepSeek V2.5
API details
API speed
No data
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $0.140/ 1M | $0.280/ 1M |
Cache PricingPrompt Cache
| Type | TTL | Write | Read |
|---|---|---|---|
| Text | - | $0.140/ 1M | $0.014/ 1M |
DeepSeek V2.5
Benchmark Results
No benchmark data to show.
Compare with other models
No curated comparisons for this model yet.
Want a custom combination? Open the compare tool
DeepSeek V2.5
Publisher
DeepSeek-AI
View publisher details DeepSeek V2.5 - 236B
Model Overview
DeepSeek V2.5 - 236B is an AI model published by DeepSeek-AI, released on 2024-09-05, for Foundation model, with 236B parameters, and 128K context length, requiring about 133GB storage.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
