DeepSeek has launched a newer model, DeepSeek-V2.5, we suggest considering this model instead.
For more information, see Comparison of DeepSeek-V2.5 to other models and API provider benchmarks for DeepSeek-V2.5.
DeepSeek Coder V2 Lite Instruct Intelligence, Performance & Price Analysis
Model summary
Intelligence
Artificial Analysis Intelligence Index
Speed
Output tokens per second
Input Price
USD per 1M tokens
Output Price
USD per 1M tokens
Verbosity
Output tokens from Intelligence Index
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
| Reasoning | No This page shows the non-reasoning version of this model. A reasoning variant may also exist. |
|---|---|
| Input modality | Supports: This information is still being updated |
| Output modality | This information is still being updated |
| Context window | 128k ~192 A4 pages of size 12 Arial font |
| Total parameters | 16B |
| Active parameters | 2.4B Number of parameters active per token during inference |
| License | DEEPSEEK LICENSE AGREEMENT |
| Model weights | Hugging Face |
DeepSeek Coder V2 Lite Instruct is among the least intelligent models, but well priced when comparing to other open weight non-reasoning models of similar size. The model has a 128k tokens context window.
DeepSeek Coder V2 Lite Instruct scores 8 on the Artificial Analysis Intelligence Index, placing it at the lower end among comparable models (averaging 12). When evaluating the Intelligence Index, it generated 1.9M tokens, which is very concise in comparison to the average of 5.3M.
Pricing for DeepSeek Coder V2 Lite Instruct is $0.00 per 1M input tokens (competitively priced, average: $0.10) and $0.00 per 1M output tokens (competitively priced, average: $0.20). In total, it cost $0.00 to evaluate DeepSeek Coder V2 Lite Instruct on the Intelligence Index.
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Evaluations
Openness
Artificial Analysis Openness Index: Results
Intelligence Index Comparisons
Intelligence vs. Price
Intelligence Index Token Use & Cost
Output Tokens Used to Run Artificial Analysis Intelligence Index
Cost to Run Artificial Analysis Intelligence Index
Context Window
Context Window
Pricing
Pricing: Input and Output Prices
Intelligence vs. Price (Log Scale)
Pricing Comparison of DeepSeek Coder V2 Lite Instruct API Providers
Speed
Measured by Output Speed (tokens per second)
Output Speed
Output Speed vs. Price
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 Tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Frequently Asked Questions
Common questions about DeepSeek Coder V2 Lite Instruct
DeepSeek Coder V2 Lite Instruct was released on June 17, 2024.
DeepSeek Coder V2 Lite Instruct was created by DeepSeek.
DeepSeek Coder V2 Lite Instruct scores 8 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 12).
When evaluated on the Intelligence Index, DeepSeek Coder V2 Lite Instruct generated 1.9M output tokens, which is very competitive compared to other open weight non-reasoning models of similar size (median: 5.3M).
No, DeepSeek Coder V2 Lite Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
DeepSeek Coder V2 Lite Instruct supports text only input.
DeepSeek Coder V2 Lite Instruct supports text only output.
No, DeepSeek Coder V2 Lite Instruct does not support image input. It can only process text.
No, DeepSeek Coder V2 Lite Instruct is not multimodal. It only supports text only input.
DeepSeek Coder V2 Lite Instruct has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, DeepSeek Coder V2 Lite Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
DeepSeek Coder V2 Lite Instruct has 16 billion parameters (2.4 billion active).
DeepSeek Coder V2 Lite Instruct is a Mixture of Experts (MoE) model with 16 billion total parameters, but only 2.4 billion active parameters are used during inference.
DeepSeek Coder V2 Lite Instruct is released under the DEEPSEEK LICENSE AGREEMENT license. This license allows commercial use. View license
DeepSeek Coder V2 Lite Instruct achieves a score of 8 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
DeepSeek Coder V2 Lite Instruct is an open weights model that can be self-hosted. View providers
DeepSeek Coder V2 Lite Instruct is an open weights model that can be downloaded and self-hosted. Compare providers