All models
Mistral AI
Saba fast
mistral/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...
Input / 1M
$0.20
USD per million tokens
Output / 1M
$0.60
USD per million tokens
Est. cost / token
$0.0000003
$0.30 per 1M, 3:1 mix
Context window
33K
max output 26K
Major features
CachingJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context2
- agentic3
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.20 | $0.60 | $0.020 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.20
- Output
- $0.60
- Cached input
- $0.020
- Blended (3:1)
- $0.30
Details
- Company
- Mistral AI
- Version
- —
- Family
- Mistral
- Released
- 2025-02-17
- Parameters
- Undisclosed
- Max output
- 26K
- Open weights
- No
- Inputs
- file, text
- Last synced
- 31 min ago