Mistral: mistral-saba
mistral-saba
mistral-saba appears to be a deployment- or provider-specific variant built on top of Mistral’s model family (from Mistral AI), rather than a distinct, widely documented base model itself. In practice, such labeled variants usually wrap one of Mistral’s mid‑ to high‑capability generative text models (like Mistral 7B/8x7B–class or Mixtral‑class) and expose it through a particular platform or API configuration, often tuned for balanced quality, latency, and cost. You can generally expect strong general‑purpose capabilities—code assistance, chat, content generation, and analysis—on par with other contemporary open or semi‑open Mistral‑based offerings, though exact size, context window, and training details are typically inherited from the underlying Mistral base model. It is primarily intended for application developers who want performant, versatile LLM behavior with predictable operational characteristics on that specific hosting provider.
Pricing
Current price per 1,000,000 tokens. Every request is billed automatically from its exact usage.
These are the last known prices before this model was removed from the catalog.
Included in plans
This model is not included in any plan yet.
Statistics
Live performance and usage of this model, aggregated across all users.
Detailed statistics appear here as soon as this model starts receiving requests.
Frequently asked questions
What is mistral-saba?
mistral-saba appears to be a deployment- or provider-specific variant built on top of Mistral’s model family (from Mistral AI), rather than a distinct, widely documented base model itself. In practice, such labeled variants usually wrap one of Mistral’s mid‑ to high‑capability generative text models (like Mistral 7B/8x7B–class or Mixtral‑class) and expose it through a particular platform or API configuration, often tuned for balanced quality, latency, and cost. You can generally expect strong general‑purpose capabilities—code assistance, chat, content generation, and analysis—on par with other contemporary open or semi‑open Mistral‑based offerings, though exact size, context window, and training details are typically inherited from the underlying Mistral base model. It is primarily intended for application developers who want performant, versatile LLM behavior with predictable operational characteristics on that specific hosting provider.
What is the context length of mistral-saba?
mistral-saba supports a context window of up to 32,768 tokens.
Does mistral-saba support image input?
mistral-saba currently accepts text input only.
Which provider is mistral-saba from?
mistral-saba is developed by Mistral and made available on this gateway through our routing infrastructure.
When was mistral-saba added to this gateway?
mistral-saba has been available on this gateway since September 23, 2026.
Is mistral-saba currently available?
mistral-saba is not currently offered on this gateway. This page is kept for reference and may be reactivated in the future.
