AI model
mistralai/mistral-saba
Mistral: Saba is a 32,768-token model served on Composite at $0.250 per million tokens in and $0.750 per million tokens out.
Try in Playground| Model ID | mistralai/mistral-saba |
|---|---|
| Provider | cv11 |
| Context window | 32,768 tokens |
| Accepts | text, file |
| Returns | text |
| Input price | $0.250 per million tokens |
| Output price | $0.750 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Moderated | No |
| Cost on a monthly plan | About 2.2 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 2 (base plus 1 routing variant) |
Make a Composite API key and type mistralai/mistral-saba as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1. It runs on credits, a plan, or your own provider key.
JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
This model has not carried enough traffic on Composite yet to publish a success rate, a latency figure or a traffic rank. The numbers appear here once it has.
The same model behind 1 alternative endpoint. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| cheapThink | mistralai/mistral-saba:cheapThink |
cv11 | $0.250 per million tokens input · $0.750 per million tokens output |
$0.250 per million tokens input · $0.750 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 2.2 plan credits, at the provider's own price.
cv11
Mistral models are compact and fast, a good fit when reply speed matters more than maximum context length.
Its 32,768-token context window covers most single-session roleplay threads comfortably. For campaigns that run over many sessions, expect older messages to eventually drop out of context.
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
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...
Supplied by cv11, not written by Composite.
Mistral: Mistral Large 4 · Mistral: Mistral Medium 3.5 · Mistral: Mistral Small 4