Mistral Small 3 24B Instruct: Benchmarks, Pricing & Context Window
Mistral Small 3 24B Instruct is a language model from Mistral, released in January 2025, with a 33K-token context window, and pricing from $0.050/M input and $0.080/M output.
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
Mistral Small 3 24B Instruct benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Mistral Small 3 24B Instruct across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Mistral Small 3 24B Instruct holds up as conversations get longer.
Quality Tracker
Mistral Small 3 24B Instruct Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Thu Oct 08 2026Mistral Small 3 24B Instruct pricing
Providers
Mistral Small 3 24B Instruct starts at $0.0500 per million input tokens and $0.0800 per million output tokens via DeepInfra. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepInfra | $0.0500 | — | $0.0800 | 32.8K/32.8K | — | — | / |
 Mistral AI | $0.100 | — | $0.300 | 32.0K/32.0K | 0.20 | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Mistral Small 3 24B Instruct model size
Mistral Small 3 24B Instruct has 24 billion parameters. See how it compares to other models in the same parameter range.
Mistral Small 3 24B Instruct context window
Input and output token limits for Mistral Small 3 24B Instruct, plus how it ranks on long-context understanding.
Try now
huggleMake it with
Mistral Small 3 24B Instruct.
Mistral Small 3 24B Instruct latency
Mistral Small 3 24B Instruct time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Mistral Small 3 24B Instruct examples
Recent arena outputs from Mistral Small 3 24B Instruct, picked from the highest-ranked matchups.
Mistral Small 3 24B Instruct license
Mistral Small 3 24B Instruct is released under the Apache 2.0 license, which permits commercial use, has 24.0B parameters, has a knowledge cutoff of October 2023.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 24.0B
- Knowledge cutoff
- October 2023
Apache License 2.0 - allows commercial use
Mistral Small 3 24B Instruct resources
Official sources for Mistral Small 3 24B Instruct: provider documentation, official launch post, model weights.
Mistral Small 3 24B Instruct vs other models
The most-compared alternatives to Mistral Small 3 24B Instruct are Claude 3.5 Sonnet, Phi 4 Reasoning, Llama 3.1 70B Instruct. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Mistral Small 3 24B Instruct
Models ranked just above and below Mistral Small 3 24B Instruct by LLM Stats score.
FAQ
Common questions about Mistral Small 3 24B Instruct.