anoman

Mistral

Mistral Small

modelmistral-small
BudgetStableVisionStreamingVisionToolsLong contextEurope

Context

262K

Input / 1M tokens

$0.1500

Output / 1M tokens

$0.6000

Weighted tokens formula

1× provider × 1× tier

About this model

Mistral Small

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

Released

2024-09

Training cutoff

2024-07

Parameters

22B (dense)

Best for

Use cases

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

Strengths

What it does well

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

Limitations

Know the trade-offs

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

Code example

Chat completion with 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 tokens

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

Pro plan: 20M weighted tokens/month. Combined multiplier 1×: 20,000,000 raw tokens available.

Alternatives

Similar models in our catalog

Workloads that fit Mistral Small often fit these too. Compare benchmarks and pricing before locking in a default.

Use Mistral Small through Anoman.