DEPLOY

Open-source LLM · DeepSeek

DeepSeek R1

671 B parameters (37 B active per token) · 128K context · MIT · released 2025-01-20 by DeepSeek.

DeepSeek R1 needs about 1342 GB at FP16: no single GPU can hold it. Serving requires an 8-GPU HGX baseboard (INT8/INT4) or a full rack (NVL72, TPU pod) at FP16.

Where this model sits

The reasoning variant of V3. Long chain-of-thought traces mean actual token cost per query is 5-20x V3's, but quality on math + code jumps into o1 territory.

What runs it (production serving)

Datacenter GPUs and rack designs sized for DeepSeek R1. Consumer cards are not practical at this size.

Memory at different context lengths

Weights are fixed. The KV cache grows linearly with context length and can rival the weights at full window. Most guides only quote weights, then hand-wave a 15% overhead, which is only true at short context.

ContextFP16 totalINT8 totalINT4 total
4K (short chat)1342 + 15.3 = 1357.3 GB671 + 7.6 = 678.6 GB336 + 7.6 = 343.1 GB
32K (typical RAG)1342 + 122.0 = 1464.0 GB671 + 61.0 = 732.0 GB336 + 61.0 = 396.5 GB
128K (full window)1342 + 488.0 = 1830.0 GB671 + 244.0 = 915.0 GB336 + 244.0 = 579.5 GB

KV bytes per token = 2 × 61 layers × 128 KV heads × 128 head-dim × precision bytes. INT4 rows keep the KV cache at INT8 (typical serving default).

Quality benchmarks

Vendor-reported scores from the release blog or tech report. Every row cites its source.

BenchmarkScoreSourceDate
MMLU (5-shot)90.8DeepSeek R1 tech report2025-01-20
MATH (AIME 2024, pass@1)79.8DeepSeek R1 tech report2025-01-20
GPQA (Diamond)71.5DeepSeek R1 tech report2025-01-20
Codeforces (Elo)2029.0DeepSeek R1 tech report2025-01-20

Speed and cost to serve

What cloud providers currently charge to serve DeepSeek R1. Tokens per second is what the provider publishes on their own page. Batch size, prompt length, and inference engine can shift these numbers a lot; treat as directional.

ProviderHardwareSpeed$/M in$/M outAs of
DeepSeek APIH800—$0.55$2.192025-08-01
Together AIH100 nodes—$3.00$7.002025-08-01
Fireworks AIH100 nodes—$3.00$8.002025-08-01

Cheapest option in this list for output-heavy workloads: DeepSeek API at $2.19/M out. Fastest published: not enough data.

License and variants

License
MIT
The gotcha
Same MIT + DeepSeek use-case restrictions as V3.
Variants
Reasoning · Distills (Llama, Qwen)
Context window
131,072 tokens (128K)
Architecture
MoE (671B total, 37B active per token)

Compare with

Model card: https://huggingface.co/deepseek-ai/DeepSeek-R1 · Release: DeepSeek announcement

See also: every open-source LLM we track · all AI chips · rack designs.