DeepSeek-R1
DeepSeek-R1 is a previous January 2025 DeepSeek reasoning snapshot, not the live DeepSeek flagship. Rechecked 2026-08-18: leftover copy still called the 671B open-weight reasoner the latest model approaching OpenAI o1. The current DeepSeek path on this site is DeepSeek V4 Flash ($0.14/$0.28) and DeepSeek V4 Pro. api-docs.deepseek.com lists deepseek-v4-flash / deepseek-v4-pro. Drop leftover latest open reasoner / AIME 79.8% / HumanEval 98% as a 2026 census.
Compare leftover DeepSeek V3 if you wanted the leftover general twin, leftover OpenAI o1-preview if you wanted the leftover o1 snapshot this page used to chase, and DeepSeek V4 Pro if you wanted the live flagship.
Key Features
- Previous 671B reasoner: Leftover copy described RL training, visible chain-of-thought, and distilled 32B / 14B / 8B / 1.5B twins. Recheck a first-party card before you hard-code those as live.
- Not the 2026 DeepSeek lead: Live API rows are V4 Flash and V4 Pro.
- Not a live o1 replacement: Leftover o1-mini / o1-preview pages on this site are previous snapshots too.
- No invented bench: AIME 79.8%, MATH-500 97.3%, Codeforces 96.3%, and HumanEval 98% stay off the table unless you re-run a first-party card.
Use Cases
- People with a DeepSeek-R1 bookmark who need the catalog corrected.
- People comparing leftover R1 vs leftover V3 vs live V4.
- People who were about to paste o1-level AIME into a 2026 deck.
Limitation: We did not re-run AIME / MATH-500 or invent a 2026 R1 dollar row.
Pricing
First-party pages on 2026-08-18.
| Piece | Price | Notes |
|---|---|---|
| DeepSeek-R1 | Previous snapshot | Recheck leftover hosts / Hugging Face. |
| Live DeepSeek path | Recheck V4 Flash / V4 Pro | Flash $0.14/$0.28; Pro is the live flagship on this site. |
If a leftover blog still calls R1 the current open DeepSeek reasoner, treat this page as the correction.
Getting Started
- Open api-docs.deepseek.com only to confirm live IDs.
- Recheck DeepSeek V4 Flash and DeepSeek V4 Pro before you buy a 2026 seat.
- Recheck leftover DeepSeek V3 if you wanted the leftover general twin.
- Do not paste "approaching o1" into a 2026 deck.
Frequently Asked Questions
Is R1 still the DeepSeek reasoning flagship?
No. The live path on this site is V4 Flash and V4 Pro.
Same as DeepSeek V3?
No. DeepSeek V3 is the leftover general snapshot.
Did it score 79.8% AIME as a 2026 census?
That leftover score stays off the table unless you re-run a first-party card.
Alternatives
- DeepSeek V4 Flash: Live small DeepSeek agent model.
- DeepSeek V4 Pro: Live DeepSeek flagship.
- OpenAI o1-preview: Leftover o1 snapshot this page used to chase.
Tips
- Call R1 a January 2025 reasoning snapshot.
- Point new DeepSeek work at V4 Flash / V4 Pro.
- Recheck the API page before you invent an R1 token price.
Conclusion
DeepSeek-R1 is a leftover 2025 reasoning snapshot, not the 2026 DeepSeek flagship and not an o1 census. Start at DeepSeek V4 Flash or DeepSeek V4 Pro, then decide whether this page is only a historical bookmark.
Comments
No comments yet. Be the first to comment!
Related Tools
DeepSeek V2.5
www.deepseek.com
Previous DeepSeek V2.5 snapshot. Rechecked: live path is V4 Flash/Pro. Not a 2026 chat+coder default.
deepseek-vl-7b-base
huggingface.co/deepseek-ai/deepseek-vl-7b-base
Previous DeepSeek-VL 7B Base snapshot. Rechecked: live path is V4 Flash/Pro. Not a 2026 VL default.
OpenAI: o1-mini
developers.openai.com/api/docs/models/o1-mini
Previous o1-mini snapshot. Rechecked: still $1.10/$4.40; dated twin deprecated. Not the 2026 reasoning default.
