Mistral Small 3 24B Instruct
Overview
Overview
Mistral Small 3 is a 24B-parameter LLM licensed under Apache-2.0. It focuses on low-latency, high-efficiency instruction following, maintaining performance comparable to larger models. It provides quick, accurate responses for conversational agents, function calling, and domain-specific fine-tuning. Suitable for local inference when quantized, it rivals models 2–3× its size while using significantly fewer compute resources.
Mistral Small 3 24B Instruct was released on January 30, 2025. API access is available through DeepInfra, Mistral AI.
Performance
Timeline
Specifications
Benchmarks
Benchmarks
Mistral Small 3 24B Instruct Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sat Feb 21 2026Pricing
Pricing
Pricing, performance, and capabilities for Mistral Small 3 24B Instruct across different providers:
| Provider | Input ($/M) | Output ($/M) | Max Input | Max Output | Latency (s) | Throughput | Quantization | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
 DeepInfra | $0.07 | $0.14 | 32.0K | 32.0K | 0.2 | 49.0 c/s | — | Text Image Audio Video | Text Image Audio Video |
Mistral AI | $0.10 | $0.30 | 32.0K | 32.0K | 0.2 | 134.0 c/s | — | Text Image Audio Video | Text Image Audio Video |
Price Comparison for Mistral Small 3 24B Instruct
Price per 1M input tokens (USD), lower is better
llm-stats.com - Sat Feb 21 2026Throughput Comparison for Mistral Small 3 24B Instruct
Tokens per second, higher is better
llm-stats.com - Sat Feb 21 2026Latency Comparison for Mistral Small 3 24B Instruct
Time to first token (s), lower is better
llm-stats.com - Sat Feb 21 2026API Access
API Access Coming Soon
API access for Mistral Small 3 24B Instruct will be available soon through our gateway.
Recent Posts
Recent Reviews
FAQ
Common questions about Mistral Small 3 24B Instruct