deepseek-ai / text-generation Open weights Also via API updated 1 year ago

DeepSeek-R1

Name: DeepSeek-R1
Price: 0.7 USD
Author: deepseek-ai

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero encounters chall...

Params

684.5 B

Context

163,840

Downloads 30d

1.6 M

Likes

14,443

Commercial use: allowed mit Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 502 K in the last 30 days (44.9%)

9.9 M649 K

Jul 28Sep 1Oct 6Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f8_e4m3	688.6 GB	860.6 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 160K ctx	688.6 GB	2,811.5 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/deepseek-r1
{
  "hf_id": "deepseek-ai/DeepSeek-R1",
  "params_b": 684.53,
  "context_length": 163840,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 1618845,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 860.6 }
  ],
  "updated_at": "2026-07-28T17:06:34Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

No longer on OpenRouter — last known API prices below.

Use via API

via OpenRouter · USD per 1M tokens · synced 2026-10-19

$0.70

input / 1M

$2.50

output / 1M

—

cached input / 1M

$3.20

1M in + 1M out

Context window: 64,000 tokens
Max output: 16,000 tokens
Providers: —
Cheapest provider: —
Best throughput: —
AA Intelligence / Coding / Agentic: 11.4 / 24.6 / 1.1

✓ Tool calling ✓ Reasoning ✓ Structured outputs ✗ Image input ✗ File input ✗ Audio input ✗ Prompt caching

Specifications

Architecture: DeepseekV3ForCausalLM
Parameters: 684.5 B
Tensor type: F8_E4M3
Context length: 163,840
Vocabulary: 129,280
Layers / heads: 61 / 128
Licence: mit
First seen on the Hub: 2025-01-20
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with any text-generation model

Popular comparisons

DeepSeek-V3.2 7.6 M DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF 3.3 M DeepSeek-V4-Flash-0731 2.7 M GLM-5.3 2.0 M DeepSeek-V3 1.5 M GLM-5 1.4 M