Context Window
32,768
Input tokens
Full-context input ≈ $0.01
Model Cost Profile
Developer: mistralai· Tokenizer: Mistral · Quantization: unknown
Canonical ID: mistralai/mistral-saba-2502
Pricing updated Apr 24, 2026
Live Pricing
Input: $0.2000
Output: $0.6000
Last synced Apr 24, 2026 · MMLU score via public benchmark data
Mistral: Saba, developed by mistralai, offers a substantial context window of 32,768 tokens, making it ideal for applications requiring extensive text analysis, such as legal document review and large-scale content generation. With an input price of $0.20 per million tokens and an output price of $0.60 per million tokens, teams can efficiently manage costs while leveraging the model for complex tasks like conversational AI and data summarization. This pricing structure allows organizations to scale their usage according to project demands without compromising on performance or budget.
Context Window
32,768
Input tokens
Full-context input ≈ $0.01
Max Output
—
Not specified
Input Price / 1M
$0.2000
Prompt tokens
Output Price / 1M
$0.6000
Completion tokens
Top Benchmark
61.1
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for Mistral: Saba. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.2000
Current Output / 1M
$0.6000
Performance History
Not enough data yet. Performance tracking started recently — check back in a few days.
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.2000 |
| Output (Completion) | $0.6000 |
| Cache Read | $0.0200 |
Estimate monthly spend for Mistral: Saba based on your workload.
Estimated Monthly Cost
$12
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.