Mistral: Saba
micromistralai/mistral-saba
Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...
AA INDEX6.5
CONTEXT33K
MODALITYtext+file->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED18 min ago
Input
$0.20 /M
Output
$0.60 /M
Blended (40/60)
$0.44 /M
Cost / IQ
$2.7077 /M
Cost / IQ = Blended Price ÷ (AA Intelligence Score ÷ 40). Normalises price by model intelligence so you can compare value across tiers. Lower = better value per unit of intelligence. Not a transactional price.
24h0%
7d0%
Price History
30-day view, daily close
Low: $0.44/M
High: $0.44/M
Average: $0.44/M
Pricing Variants
Cached Input
$0.02/M
90% cheaper than standard
Provider Comparison
1 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓Mistral | $0.20 | $0.60 | $0.44 | median |
Blended price = 40% input + 60% output. Median price shown in header is the reference price for this model.
Cost / IQ Comparison
Cost / IQ (quality-adjusted $/M)$2.7077/M
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
At or below SIT TPI
Value Ranking (by Cost / IQ)
Rank #494 of 521 micro models
← YOU ARE HERE | Mistral: Saba
Data Sources
Source
Aggregator
1 source · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/mistralai/mistral-saba
# Response (truncated)
{ "model_id": "mistralai/mistral-saba", "name": "Mistral: Saba", "blended_price_per_m": 0.44, "sit_adjusted_price": 2.707692 }