deepseekmodel

DeepSeek: DeepSeek V3

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

text code cheap long-context

Best for

Code GenerationDebuggingCode ReviewBulk Data Extraction

Try in Playground Compare →

Context Window

131K tokens ≈ 291 pages of text

Input Cost

$0.20/1M

Output Cost

$0.80/1M

Latency p50

—

Pricing Details

Standard Pricing

Input (per 1M tokens)

$0.20

Output (per 1M tokens)

$0.80

Price history

6/10/2026$0.20 in / $0.80 out

6/9/2026$0.20 in / $0.80 out

Run it locally

Local run command

# Refer to provider docs:

Presumptive Specs:

Typical GPU

12–24 GB VRAM

System RAM

16+ GB

Disk

20+ GB free

Runtime

Docker / local runtime

Hallucination Score™ (est.)

Community reliability estimate · not official

Generally reliable

About this score: Community-estimated based on user reports and publicly available benchmark data (e.g. TruthfulQA). This is not an official score from the model provider. Scores may be inaccurate — always verify with the official leaderboard before making production decisions.

Price HistoryPro

Input & output cost per 1M tokens over time

Price history is a Pro feature

Track pricing trends and catch price drops early.

Upgrade to Pro — $19/mo →

Provider

deepseek

Community Prompts

Proven prompts shared by the community for this model

Loading prompts…