LANGUAGE MODEL DeepSeek Last updated:

DeepSeek LLM 67B Chat (V1)

DeepSeek LLM 67B Chat (V1) is an API model from DeepSeek. It’s positioned for general text tasks—work that benefits from iteration, not just one-shot answers.

Context
4K
Up to 4,096 tokens

Core Capabilities

Long Documents
Handles entire codebases, books, and multi-doc RAG.

Context Window

4k tokens
≈ short doc
4k This model 本模型
32k Long docs 长文档
128k Books 整本书
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
Context / memory
Context window size · log-scaled
6.0
9.0
1.0
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

  • Earlier DeepSeek 67B — historical baseline.
  • First DeepSeek model that the wider OSS community took seriously — 236B MoE with only 21B active per token
  • Saved 42.5% training cost vs DeepSeek 67B, reduced KV cache 93.3%, boosted max throughput 5.76x
  • DeepSeekMoE architecture (fine-grained experts + shared expert isolation) became the template

Best use cases

  • Self-hosted Chinese / multilingual deployments where API access was politically risky
  • Cost-sensitive bulk inference via budget providers
  • MoE-architecture research and KV-cache optimisation experiments

Tools to try

Not ideal for

  • Frontier reasoning by 2025 — superseded by V3 / V3.1 / V4 generations
  • Edge / single-GPU deployments (236B MoE still demands multi-GPU serving)