← Back to LLM Wiki
LLM Wiki · Open Weights · Self-Hostable

DeepSeek

The open-weights reasoning family — DeepSeek-V3 and DeepSeek-R1. MIT-licensed weights and aggressive hosted pricing.
DeepSeek-R1 was the first open-weights model to match o1-class reasoning performance, released with MIT-licensed weights and a paper describing the pure-RL training approach. The hosted API sits well below frontier pricing. For reasoning-heavy workloads that need to be self-hostable, DeepSeek is the current default.
DeepSeek Open Weights Reasoning MIT License Low Cost

Quick Facts

Vendor
DeepSeek (Hangzhou)
Released
DeepSeek LLM (2023); DeepSeek-R1 (January 2025)
Current line
DeepSeek-V3 · DeepSeek-R1 · DeepSeek-Coder
License
MIT (weights); DeepSeek License for some variants
Hosting
DeepSeek API, Together, Fireworks, self-hosted via vLLM
Context window
128K tokens
Modalities
Text; DeepSeek-VL for vision
Architecture
Mixture-of-experts with multi-head latent attention

Summary

DeepSeek is a Chinese research lab spun out of the High-Flyer quant hedge fund. It rose to global attention in January 2025 with DeepSeek-R1 — the first open-weights model to match OpenAI's o1 on reasoning benchmarks. The paper documented a pure reinforcement-learning approach to reasoning (no supervised fine-tuning on chain-of-thought traces) that reshaped the research conversation about how reasoning emerges.

Beyond the reasoning story, DeepSeek-V3 is a strong general model at roughly one-tenth the hosted price of US frontier labs. The combination of MIT-licensed weights and cheap API access has made DeepSeek the pragmatic choice for teams that want reasoning capability either in-house or at scale without frontier pricing.

Model Lineup

Where DeepSeek Fits

DeepSeek is the default when reasoning quality matters and self-hosting or low-cost API access is a requirement. The distilled variants (R1-Distill-Qwen-32B, R1-Distill-Llama-70B) are particularly useful for edge deployments that need reasoning without the operational weight of running V3 / R1 at full scale. For teams that are API-bound but price-sensitive, DeepSeek's hosted tier is often a 5–10x cost reduction vs. frontier US labs.

Tradeoffs

Deployment Notes

Within the Claw ecosystem, DeepSeek R1 distilled variants are deployed for reasoning-heavy interior loops — planning, hard refactoring, complex test failure diagnosis. Qwen3-Coder handles most interactive coding; DeepSeek steps in when the task needs deliberation. For hosted API access, DeepSeek is integrated into the provider arbitrage layer as a cost-optimized fallback.

References

  1. DeepSeek
  2. DeepSeek on GitHub
  3. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
  4. The Agent Infrastructure Stack — Organized AI