deepseek-reasoner (legacy alias → V4-Flash thinking) NEW
deepseek-reasoner (legacy alias → V4-Flash thinking) is an API model from DeepSeek. It’s positioned for hard reasoning and planning—work that benefits from iteration, not just one-shot answers.
Core Capabilities
Long Documents
Handles entire codebases, books, and multi-doc RAG.
Reasoning
Solves complex math, logic, and planning tasks.
Context Window
Context window not disclosed.
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 What it feels like
- Production reasoning surface for DeepSeek's R1-class model.
- First open-weights reasoning model that genuinely competes with o1 — broke the closed-source moat
- ~90% on advanced math benchmarks vs ~83% for GPT-4o; the chain-of-thought is fully visible
- Trained for ~$5.5M on 2,048 H800s — proof you don't need $100M training runs to reach the frontier
Best use cases
- Math proofs, logic puzzles, and step-by-step derivations where explicit reasoning helps
- Coding and engineering tasks that benefit from chain-of-thought
- On-prem / air-gapped deployments where API models can't go
Tools to try
Not ideal for
- Casual chat, tone, or creative writing — ChatGPT/Claude feel more polished
- Multimodal tasks (image / vision) — text-only model