Capabilities
7-day heat trend
−23.6%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 28% of tracked models
- Faster than 51% of tracked models
- Efficiency rank: #887 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About 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 cura...
mistral-saba is a Text model from Mistral AI (US). HotON.ai tracks it at $0.20 per 1M input tokens and $0.60 per 1M output tokens, with a 33K-token context window, ~148 tokens/sec throughput and 100.0% availability. Its composite efficiency score is 88/100 at an estimated $0.001 per successful task.
Compare mistral-saba
Related market news
Frequently asked questions
How much does mistral-saba cost per 1M tokens?+
mistral-saba is tracked at $0.20 per 1M input tokens and $0.60 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.50 per 1M tokens. Figures are illustrative demo data.
What is mistral-saba best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is mistral-saba?+
mistral-saba delivers about 148 tokens/sec with 100.0% tracked availability, suitable for latency-sensitive, real-time applications.
Is mistral-saba cheaper than other AI models?+
Within the HotON.ai tracked set, mistral-saba is cheaper than 28% of models on input price and ranks #887 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.