LLMOpen weights
Mistral Small 3
Mistral AI
Updated May 21, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error
Specifications
- Type
- LLM
- Access
- Open weights
- Released
- January 30, 2025
- Context window
- 32,768 tokens
- Knowledge cutoff
- October 31, 2023
- Output speed
- 136 tok/s
- Latency (TTFT)
- 0.53s
- Input
- Text
- Output
- Text
- API pricing
- $0.05 in · $0.08 out / 1M tokens
Capabilities
Structured output