anoman

DeepSeek

DeepSeek V3

modeldeepseek-v3
BudgetStabilStreamingToolsBatchLong contextChina

Konteks

128K

Input / 1M token

$0.1400

Output / 1M token

$0.2800

Rumus weighted token

1× provider × 1× tier

Tentang model ini

DeepSeek V3

DeepSeek V3 is a 671B-parameter Mixture-of-Experts model that activates 37B parameters per token. Designed for general-purpose chat, document analysis, and structured output, it punches well above its cost class on coding, reasoning, and long-context comprehension. The MoE architecture means inference is roughly as fast as a dense 37B model while quality matches dense 70B+ flagships.

Rilis

2024-12

Batas data latih

2024-07

Parameter

MoE 671B (37B active)

Paling cocok untuk

Kasus penggunaan

  • Cost-sensitive production chat
  • Long-context document analysis (128K window)
  • Code generation + review
  • Structured-output extraction (JSON, function calls)
  • Multilingual workloads (Chinese, English, code)

Kelebihan

Yang dikerjakan dengan baik

  • Top-tier coding ability for the price (HumanEval 89%)
  • Strong on Chinese-language benchmarks (CMMLU 88.8)
  • Native function calling + JSON mode
  • 128K input + 8K output — fits most agent loops
  • Mixture-of-Experts keeps inference cheap at scale

Keterbatasan

Pahami trade-off-nya

  • !Knowledge cutoff is mid-2024 — agents may need search augmentation for fresh facts
  • !Reasoning depth trails specialist reasoners (use DeepSeek R1 for math-heavy work)
  • !Outputs longer responses than GPT-4o by default — set max_tokens explicitly for cost control

Benchmark

Skor terpublikasi

Skor dari model card resmi dan leaderboard publik. Makin tinggi makin baik kecuali disebutkan lain.

BenchmarkSkorMengukur
MMLU87.1General knowledge across 57 subjects
MMLU-Pro75.9Harder MMLU variant, 10 options per question
HumanEval89.0Python code generation, pass@1
MATH-50089.3Competition mathematics
DROP90.1Reading comprehension + numeric reasoning

Contoh kode

Chat completion dengan DeepSeek V3

from openai import OpenAI

client = OpenAI(
    base_url="https://api.anoman.io/v1",
    api_key="anm-sk-..."
)

response = client.chat.completions.create(
    model="deepseek-v3",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Weighted token

weighted_tokens = raw_tokens × 1 (provider) × 1 (tier)

Paket Pro: 20 jt weighted token/bulan. Multiplier gabungan 1×: 20,000,000 raw token tersedia.

Alternatif

Model serupa di katalog kami

Beban kerja yang cocok dengan DeepSeek V3 sering cocok dengan ini juga. Bandingkan benchmark dan harga sebelum menetapkan default.

Gunakan DeepSeek V3 lewat Anoman.