Saba

Mistral chattool_use

API ID: mistralai/mistral-saba-2502

Input Price
$0.20
/1M tokens
Output Price
$0.60
/1M tokens

About Saba

Mistral Saba is Mistral AI's specialized model for specific regional or domain applications. The model delivers focused capability for targeted use cases. Mistral Saba demonstrates Mistral's expansion into specialized AI offerings. For developers with specific regional requirements, Mistral Saba offers targeted capability.

💰
Price Ranking
#720 lowest price among 950 Chat models

Model Specifications

Context Length
33k
Max Output
—
Release Date
2025-02-17
Capabilities
chat tool_use
Input Modalities
text
Output Modalities
text

Best For

  • Conversations, content writing, general assistance

Consider Alternatives For

  • Image understanding (needs vision capability)

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Personal AI Assistant
$0.27
/month
50 conversations/day, ~500 tokens each
Customer Service Bot
$8.40
/month
1000 tickets/day, ~800 tokens each

Mistral Model Lineup

Compare all models from Mistral to find the best fit

Model Input Output Context Capabilities
Saba Current Free Free 33k chat tool_use
Pixtral 12B Free Free 4k chat vision
Mistral 7B Instruct v0.3 Free Free 33k chat
Mistral 7B Instruct Free Free 33k chat
Mixtral 8x22B (base) Free Free 66k chat
Mixtral 8x22B (base) Free Free 66k chat

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Allen AI Olmo 3.1 32B Instruct
Input: $0.20
Output: $0.60
Context: 66k
Other UnslopNemo 12B
Input: $0.40
Output: $0.40
Context: 33k
Alibaba Qwen Qwen2.5 VL 32B Instruct
Input: $0.20
Output: $0.60
Context: 128k
Meta Llama 3.1 70B Instruct
Input: $0.40
Output: $0.40
Context: 131k

🚀 Quick Start

Get started with Saba API

OpenAI-compatible SDK
from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="mistralai/mistral-saba-2502",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)