LANGUAGE MODEL DeepSeek Last updated:

DeepSeek Coder V2 Lite Instruct

DeepSeek Coder V2 Lite Instruct is an API model from DeepSeek. It’s positioned for general text tasks—work that benefits from iteration, not just one-shot answers.

Try DeepSeek API Docs ↗
Intelligence
Below avg
Context
128K
Up to 128,000 tokens
How are Intelligence, Speed & Cost bucketed?
Intelligence and Speed buckets are percentile ranks on Artificial Analysis. Cost buckets are fixed dollar thresholds keyed off output-token price ($/M out).
Intelligence
  • Top 1%≤ 1%
  • Top 5%≤ 5%
  • Top 10%≤ 10%
  • Good≤ 25%
  • Medium≤ 50%
  • Below avg> 50%
Speed
  • Top 1%≥ 345 tok/s
  • Top 5%≥ 237 tok/s
  • Top 10%≥ 196 tok/s
  • Good≥ 146 tok/s
  • Medium≥ 90 tok/s
  • Slow< 90 tok/s
Cost
  • Freeopen weights · self-host
  • Low< $1 / M out
  • Moderate$1–5 / M out
  • High≥ $5 / M out
Official ↗ Artificial Analysis ↗ Hugging Face ↗

Core Capabilities

Coding
Strong real-world software engineering.
Long Documents
Handles entire codebases, books, and multi-doc RAG.

Context Window

128k tokens
≈ 98 pages
4k Chat 聊天
32k Long docs 长文档
128k This model 本模型
400k Multi-doc 多文档
1M Codebase 整个代码库
10M

Availability

API
Available
Product / App
Not available
Open Source
Not released
Enterprise
Contact sales

Pricing Model

Pay per token
Input and output billed separately.
Pay-per-token

Capability / Performance

Where this model sits relative to the middle 60% of models in the tree. All scores are 0–10 (higher is better).

Lower 20% Upper 80% This model
Reasoning
AA Intelligence Index · scaled to 10
1.7
5.6
1.2
Coding
SciCode · scaled to 10
1.8
4.3
1.4
Agentic tasks
Terminal-Bench Hard · scaled to 10
0.2
3.6
3.6
Context / memory
Context window size · log-scaled
6.0
9.0
6.0
Lower 20% 20th percentile — 20% of models score below this This model Where the current model lands Upper 80% 80th percentile — only 20% of models score above this Percentile boundaries are computed across every model in the tree that reports the underlying benchmark for each capability.

What it feels like

  • Lite variant — 16B with 2.4B active for single-GPU coding.
  • First open-weights coding model to beat GPT-4 Turbo, Claude 3 Opus, and Gemini 1.5 Pro on code + math
  • 236B MoE / 21B active — derived from DeepSeek-V2 with 6T extra tokens of code/math pre-training
  • HumanEval 90.2%, MBPP 76.2%, LiveCodeBench 43.4%, MATH 75.7% — frontier coding numbers at OSS price
Reviews: DeepSeek-Coder-V2 paper (arXiv) ↗ · GitHub — DeepSeek-Coder-V2 ↗ · Artificial Analysis — DeepSeek-Coder-V2 ↗

Best use cases

  • Self-hosted code-completion engines and IDE integrations
  • Repository-level QA and refactor pipelines using open weights
  • Multilingual code (338 languages) including niche legacy ones

Tools to try

DeepSeek Chat Cursor Hugging Face Ollama

Not ideal for

  • Frontier coding by mid-2025 — Claude Opus 4.5 / Sonnet 4.5 / DeepSeek V4 lead by wide margins
  • Edge / single-consumer-GPU deployments at the 236B scale (use Lite)