92
/ 100 APIVault Score
// At a glance
Free Tier
5M tokens free · then $0.14/M input · no card
Category
LLM
Credit Card
Not required
Last Verified
2m ago
// Free tier details
Available Models
DeepSeek-V3DeepSeek-R1
Monthly Tokens
5M tokens free, then $0.14/M input
No credit card needed
No phone verification
// Quick start
300">"text-purple-400">from openai 300">"text-purple-400">import OpenAI
client = OpenAI(
api_key=300">"YOUR_DEEPSEEK_KEY",
base_url=300">"https://api.deepseek.com/v1",
)
response = client.chat.completions.create(
model=300">"deepseek-chat",
messages=[{300">"role": 300">"user", 300">"content": 300">"Solve: 2 + 2 * 3"}],
)
print(response.choices[0].message.content)// Overview
DeepSeek-V3 and R1 match top closed models on benchmarks, with the cheapest API pricing in the industry. Open weights also available for self-hosting.
// Pros
- Top-tier reasoning at lowest price
- $0.14/M input is industry-low
- Open weights available
// Cons
- Server sometimes overloaded
- Limited multimodal support
// Score breakdown
Reliability (35%) (from 2m ago health check)100/100
Free Tier Generosity (30%) (computed from quota, no-CC, no-phone fields)85/100
Documentation (20%) (human rating)88/100
Popularity (15%) (GitHub stars (log-normalised), or manual baseline)95/100
Methodology: apivault.dev/methodology
// Best for
Reasoning tasksCode generationCost-sensitive apps
// Recent changes
May 20, 2026DeepSeek-V3.5 releasedadded