Start free trial

Mistral: Saba

mistralai/mistral-saba
CompareAPITry this model

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.

Modalities
In / out per 1M$0.20 / $0.60
Context32K
ReleasedFeb 17, 2025

Providers

3 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Mistral$0.20$0.60$0.020.52s119 tps100%
Mistral$0.20$0.60$0.020.44s115 tps100%
Mistraleu$0.22$0.66$0.02———

Market-wide measurements, refreshed every 15 minutes. They describe who serves Saba in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Saba costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.20
per 1M tokens
Output
$0.60
per 1M tokens
Cache read
$0.02
per 1M cached tokens
Included in every pass
Saba is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s1.0s2.0s3.0s4.0s
Oct 29, 12 AMOct 29, 5 PMNov 1, 2 AM
Mistral Mistral
0 tok/s25 tok/s50 tok/s75 tok/s100 tok/s
Oct 29, 12 AMOct 29, 5 PMNov 1, 2 AM
Mistral

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.93%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 99.88%
100% 97% 93% 90%
Oct 31, 6:10 PMNow

Apps

Tools that most often run Saba, by tokens this week.

Wiggli Parser42.7% of tokens3.6MHello HavenPersonal Agent · 23.8% of tokens2.0MChat MRlin14.7% of tokens1.3MSillyTavernRoleplay · 11.6% of tokens988.4KDocfu7% of tokens597.1K

Activity

40.2M tokens processed market-wide in the last month.

02.0M4.0M6.0M8.0M
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens

FAQ

Which model id do I use for Saba?
mistralai/mistral-saba. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does Saba hold?
32,768 tokens per request, of which up to 26,214 can be the response.
What can it accept and return?
Input: text, file. Output: text.
What does Saba cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.20 per 1M input tokens and $0.60 per 1M output tokens.
How current is its knowledge?
Training data runs to Sep 2024. Anything later has to come from your prompt or a tool call.
Who built Saba?
Mistral, in the Saba family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion