Mistral Large is an API-access large language model from Mistralai priced at $2.00/1M input tokens and $6.00/1M output tokens with a 128k context window. Context caching reduces input costs to $1.00/1M for cache reads.
Economics (OpenRouter)
Input / 1M
$2.00
Output / 1M
$6.00
Est. Monthly Cost
$102.60
Based on current usage settings
Cache Read$1.00
Cache Write$2.50
Capabilities (models.dev)
ReasoningNo
Tool CallNo
Audio InNo
Audio OutNo
Modalitytext
Context Window128k
Benchmarks (AA)
Intelligence Index
General reasoning and knowledge
—
Coding Index
Code generation & debugging
—
Math Index
Mathematical reasoning
—
Performance
—tokens/sec
* Median output throughput
Model ID: mistralai/mistral-large • Data Sources: OpenRouter, Artificial Analysis, models.dev