Mistral
Mistral Small
model
mistral-smallBudgetStableVisionStreamingVisionToolsLong 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.