Context
33K tokens (~16 books)
Input $/1M
$0.20
Output $/1M
$0.60
Type
text
License
Open Source
Benchmarks
0 tested
Data as of
About
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...
No benchmark data available yet.
Links
Research
Documentation
Community
Source Code
BenchGecko API
mistral-saba
Specifications
- Typetext
- Context33K tokens (~16 books)
- ReleasedFeb 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.001
Available On
Learn More
Share & Export
Frequently Asked Questions
Saba is an open-source text AI model by Mistral AI, released in February 2025. Context window: 33K tokens.
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteGemma 3 12B (free) · Google DeepMindQwen3 Next 80B A3B Instruct (free) · Alibaba QwenBenchmarks
Key facts · as of 2026-10-05
- Saba by Mistral AI. Not enough public benchmark scores to rank yet.
- List price $0.20 input · $0.60 output per 1M tokens (as of 2026-10-05).
- Sold by 3 providers (as of 2026-10-05): Mistral $0.20 in / $0.60 out · Mistral $0.20 in / $0.60 out · Mistral $0.22 in / $0.66 out. Every provider
How to cite · data as of 2026-10-05
Saba · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/mistral-saba
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP