anoman

Mistral

Mistral Small

modelmistral-small
BudgetStabilVisionStreamingVisionToolsLong contextEurope

Konteks

262K

Input / 1M token

$0.1500

Output / 1M token

$0.6000

Rumus weighted token

1× provider × 1× tier

Tentang model ini

Mistral Small

Mistral's cost-optimized tier — strong European-language quality at budget pricing. EU data residency by default.

Rilis

2024-09

Batas data latih

2024-07

Parameter

22B (dense)

Paling cocok untuk

Kasus penggunaan

  • Budget-tier European-language chat
  • GDPR-resident workloads
  • Cheap classification + routing

Kelebihan

Yang dikerjakan dengan baik

  • EU data residency by default
  • Strong on French / German / Spanish / Italian
  • Native function calling

Keterbatasan

Pahami trade-off-nya

  • !Reasoning depth limited vs Large
  • !Smaller model — not for hard tasks

Contoh kode

Chat completion dengan Mistral Small

from openai import OpenAI

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

response = client.chat.completions.create(
    model="mistral-small",
    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 Mistral Small sering cocok dengan ini juga. Bandingkan benchmark dan harga sebelum menetapkan default.

Gunakan Mistral Small lewat Anoman.