Saba
Mistral AI · released Feb 17, 2025
- Type
- Closed
- Input
- $0.20
- Output
- $0.60
- Cached
- $0.020
List price · per 1M tokens · Mistral AI at 33K context · source ↗
Our take
Written Sep 2, 2026Saba is Mistral AI's proprietary text-and-file model with a 32,768-token request limit. Released in early 2025, it offers a standard and a premium throughput tier, though no benchmark scores are available to verify its quality against peers.
Pick this for basic text and file processing where you do not need benchmark leadership, or when you want a throughput boost without switching providers. Skip it if you need measured quality data to justify a choice, or if you want to self-host or fine-tune.
The case for it
- Premium tier delivers nearly triple the throughput of the standard tier for a modest price increase.
- Three current hosted offers give some provider choice without hunting across dozens of sources.
The case against it
- No benchmark scores in our data — chat, reasoning, coding and multilingual performance are all unverified.
- Premium throughput costs more than the standard tier, with no evidence this speed is unusual for the price class.
- Proprietary weights; you cannot download or modify the model.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Where to rent it
Prices checked 4 hours ago — each listing carries its own date.
Mistral AI, through OpenRouter
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts Mistral AI on 33K of context.
- per 1M tokens
- $0.20 in / $0.60 out
- Context served
- 33K
- Throughput
- ~11 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.20 / $0.60checked 4 hours ago | 33K | not measured | Unknown | Unknown | Unknown |
| Mistral AIThrough OpenRouter | $0.20 / $0.60checked 4 hours ago | 33K26K max reply | 11 tok/s | No | Yes30 days | Confirmed |
| Mistral AIeuThrough OpenRouter | $0.22 / $0.66checked 4 hours ago | 33K26K max reply | 50 tok/s | No | Yes30 days | Confirmed |
OpenRouterAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Mistral AIThrough OpenRouter | ✓ | ✓ | ✓ |
| Mistral AIeuThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text and documents in, text out
- Catalogue slug
- mistralai-saba