MODEL PROOF

Saba

NOT INDEPENDENTLY RATED

No independent LMArena score is published for this model.

$0.300 / 1M tokens Balanced · 3 tokens in per 1 out
Independent LMArena score
Not independently rated
Context window
32.77K
Maximum output
26.21K
Input modalities
text, file
Output modalities
text
Published input price
$0.200 / 1M tokens
Published output price
$0.600 / 1M tokens
Pricing kind
fixed

Inspect complete billing conditions and endpoint terms below.

Price from Mistral: the cheapest offer that is serving, at standard delivery and at the maker’s precision or better, at its standard rate.

Every price dimension · USD per million tokens
Input$0.200/M
Output$0.600/M
Cached input$0.020/M
Cache writeUnknown/M
Cache write 1hUnknown/M
ReasoningUnknown/M

Who sells it

The same weights, different shops. Cheapest is not like-for-like when serving precision differs.

3 provider offers · rates, limits and conditions

Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test.

SellerInputOutputPrecisionUptime (1d)
Mistralmistral/zdr
Endpoint terms
Cached input /M
$0.020
Context limit
32,768 tokens
Output limit
26,214 tokens
Tools
Listed by endpoint
Reasoning
Not listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
Unknown
$0.200 $0.600 undeclared 100.00%
Mistralmistral
Endpoint terms
Cached input /M
$0.020
Context limit
32,768 tokens
Output limit
26,214 tokens
Tools
Listed by endpoint
Reasoning
Not listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
Unknown
$0.200 $0.600 undeclared 100.00%
Mistralmistral/eu
Endpoint terms
Cached input /M
$0.022
Context limit
32,768 tokens
Output limit
26,214 tokens
Tools
Listed by endpoint
Reasoning
Not listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
Unknown
$0.220 $0.660 undeclared —

Independent scores

No independent benchmark has measured this model. Unrated is not a score of zero.

Capability

Context window32K
Max output26K
Input modestext, file
Tool useyes
Reasoningno
Knowledge cutoff2024-09-30
Open weightsUnknown

Provenance

Price sourceopenrouter.ai
Fetched2026-10-06
Quality dataunrated

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...

Questions this page answers

What does Saba cost?

$0.200/M in, $0.600/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.

Does Saba have an independent quality score?

Saba has no independent quality score in this catalogue. Unrated is not a score of zero.

What beats Saba?

Saba has no independent quality score. Unrated is not a score of zero.

Does this page use Artificial Analysis scores for Saba?

No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.

Does a missing score mean Saba scored zero?

Unrated is not a score of zero.

MODEL MONUMENT

Save or share this proof

Badge

The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not.

Saba — Undominated.ai dominance verdict

Markdown
[![Saba — Undominated.ai dominance verdict](https://undominated.ai/badge/mistralai__mistral-saba.svg)](https://undominated.ai/models/mistralai__mistral-saba/)
HTML
<a href="https://undominated.ai/models/mistralai__mistral-saba/"><img src="https://undominated.ai/badge/mistralai__mistral-saba.svg" alt="Saba — Undominated.ai dominance verdict" height="36"></a>

Direct file: https://undominated.ai/badge/mistralai__mistral-saba.svg — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never older than the last deploy.

Evidence & Ask