LLMOpen weights
Mistral Small 3 24B Instruct
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
- License
- apache 2 0
- Parameters
- 24000000000
- Context window
- 32,000 tokens
- Knowledge cutoff
- October 1, 2023
- Output speed
- 134 tok/s
- Latency (TTFT)
- 0.2s
- API pricing
- $0.10 in · $0.30 out / 1M tokens
Capabilities
Function callingStructured output