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

DeepSeek-V3.1

Name: DeepSeek-V3.1
Price: 0.25 USD
Author: deepseek-ai

DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. Compared to the previous version, this upgrade brings improvements in multiple aspects:

Params

684.5 B

Context

163,840

Downloads 30d

258 K

Likes

864

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

Download history

daily snapshots · 106 days

▲ 107 K in the last 30 days (29.3%)

367 K213 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-v3-1
{
  "hf_id": "deepseek-ai/DeepSeek-V3.1",
  "params_b": 684.53,
  "context_length": 163840,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 258184,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 860.6 }
  ],
  "updated_at": "2026-07-28T18:06:46Z"
}

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

Use via API

via OpenRouter · USD per 1M tokens · synced 2026-11-10

$0.25

input / 1M

$0.95

output / 1M

$0.13

cached input / 1M

$1.20

1M in + 1M out

Context window: 163,840 tokens
Max output: 147,456 tokens
Providers: 4
Cheapest provider: DeepInfra · $0.25 / $0.95
Best throughput: —
AA Intelligence / Coding / Agentic: — / — / —

✓ 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: 2025-08-21
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 GLM-5.3 2.0 M DeepSeek-R1 1.6 M DeepSeek-V3 1.5 M GLM-5 1.4 M