TokenRate

Saba Pricing

Fast

Mistral · 33K tokens context

Saba from Mistral costs $0.200 per 1 million input tokens and $0.600 per 1 million output tokens as of June 2026 (live OpenRouter data). The model supports a 32,768-token context window (approximately 24,576 words) with a 8K-token maximum output. A typical 1,000-token request costs $0.0002 in input charges; a 10,000-token request costs $0.0020.

Saba pricing and capability summary
Input price$0.200 / 1M tokens
Output price$0.600 / 1M tokens
Output / input ratio3.0×
Context window32,768 tokens (~24,576 words)
Maximum output8,192 tokens
Cost per 1K tokens (input)$0.0002
TierFast
Last verified

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...

Live pricing from OpenRouter

Input Price

$0.200

per 1 million tokens

Output Price

$0.600

per 1 million tokens

Context Window

33K tokens

max 8K output

Cost Examples

Request TypeTokensInput CostOutput Cost
1,000 word article1,333$0.000267$0.00024
10-page document (2,500 words)3,333$0.000667$0.0006
1,000 lines of code5,000$0.001$0.0009
100K token document100,000$0.02$0.018

Output cost estimated at 30% of input token count. Use the calculator for exact figures.

Strengths

  • Extremely cheap at $0.200/1M input tokens
  • Low latency for high-throughput workloads
  • Cost-effective at scale

Limitations

  • Less capable than flagship models on complex reasoning
  • Smaller 33K-token context limits long-document use

Best Use Cases

High-volume classification
Text extraction and summarization
Simple chat and Q&A
Cost-sensitive pipelines

Calculate Saba Costs

Use the TokenRate calculator to convert any budget, token count, or text into exact Saba costs — and compare across all models.

Open Calculator →

Saba — FAQ

Related Models

Related Guides