AI Model Intelligence

Mistral: Saba

kilo/saba

By kilo · released 2025-02-17

⚠ This is a community fine-tune or derivative — not an official vendor release.

$0.200
Input / 1M tokens
$0.600
Output / 1M tokens
33K
Context window
33K
Max output

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Capabilities

Tool callingReasoning? Structured outputAttachmentsOpen weightsTemperature control
Modalities: input text · output text

Model fit scores

0–100 · higher is better

These scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.

Coding41
  • Tool calling40/40
  • Structured output0/20
  • Reasoning0/10
  • Context window (100K → 1M)0/20
  • Provider availability1/10
Agents51
  • Tool calling35/35
  • Structured output0/25
  • Reasoning0/15
  • Output token limit15/15
  • Provider availability1/10
JSON / structured output48
  • Structured output / JSON mode0/50
  • Tool calling20/20
  • Temperature control10/10
  • Price-friendly for high-volume18/20
Cost efficiency65
  • Headline price (log-scaled)65/95
  • Has prompt-cache pricing0/5
Long context0
  • Context ≥ 100K0/100
Production-readiness50
  • Number of independent providers5/40
  • Has published per-token price20/20
  • Context window ≥ 8K15/15
  • No data inconsistencies across providers10/10
  • Official model (not derivative)0/15

Cost Efficiency Index

Open full calculator →

Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.

ScenarioCostAssumption
RAG answer
per 1,000 RAG answers
$1.30
< $0.01 per request
5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot.
Support ticket triage
per 10,000 tickets
$2.60
< $0.01 per request
1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support.
Data extraction
per 1,000 documents
$0.70
< $0.01 per request
2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines.
Code review
per 1,000 PRs
$2.20
< $0.01 per request
8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads.
Agent step
per 1,000 steps
$2.76
< $0.01 per request
12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step.

Pricing detail

Recommended pricing from kilo · mistralai/mistral-saba

$0.200
Input
$0.600
Output

Available on 1 providers

ProviderProvider model idInput / 1MOutput / 1MContextReleased
Kilo Gateway
kilo
mistralai/mistral-saba$0.200$0.60033K2025-02-17

Frequently asked questions

How much does Mistral: Saba cost?

Mistral: Saba costs $0.200 per 1M input tokens and $0.600 per 1M output tokens, sourced from kilo. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.

What is the context window of Mistral: Saba?

Mistral: Saba has a context window of 33K tokens, with a max output of 33K tokens per reply. This is the total combined size of prompt + completion.

Does Mistral: Saba support tool calling?

Yes. Mistral: Saba supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.

Does Mistral: Saba support structured output / JSON mode?

Support for structured output / JSON-schema-constrained decoding is not reported for Mistral: Saba in our data source. Verify with kilo's official documentation before relying on it in production.

Can Mistral: Saba accept image input?

No. Mistral: Saba only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.

Is Mistral: Saba open-weight?

Yes. Mistral: Saba's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.

What are the best alternatives to Mistral: Saba?

If Mistral: Saba doesn't fit, consider Free Models Router, Reka Edge, Reka Flash 3. Each one targets the same use case — see the Related links below for direct head-to-head pages.

Where does this data come from?

All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.

More kilo models

Capability lists this model is in

Last updated:

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.