Mistral Small 3
Released
2025-01-30
Last refreshed
2026-06-29
Status
Researched 176d ago
Open sourceCommercial use: permittedAgentsClassificationJSON / Tool use
MistralAI releases · 25 in the last 12 months · this family litChangelog →
Specifications
- Family
- Mistral Small
- Released
- 2025-01-30
- Context
- 32K
- Parameters
- 24B
- Architecture
- Decoder Only
- Knowledge cutoff
- 2023-10
- Specialization
- general
- Openness
- Open source
- License
- Apache 2.0OSI-approvedPermitted
- Weights
- Unknown
- Code
- Unknown
- Training
- Pretrained
Created by
Pricing
Output / 1M
$0.600
Input / 1M
$0.150
Cheapest of 2 routes · Vercel AI Gateway · cache read $0.015
Created by
Pricing
Output / 1M
$0.600
Input / 1M
$0.150
Cheapest of 2 routes · Vercel AI Gateway · cache read $0.015
About
Mistral Small 3 is a 24B-parameter, latency-optimized model that Mistral released on January 30, 2025, as both pretrained and instruction-tuned open-weight checkpoints. Mistral aims it at fast conversational assistants, low-latency function calling, fine-tuning for domain specialists, and local inference; once quantized, it can run on a single RTX 4090 or a MacBook with 32GB of RAM.
Providers(2)
Compare all 2Compare API pricing across 2 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| Vercel AI Gateway | $0.150 | $0.600 | read $0.015 | Serverless |
| OpenRouter | - | - | - | ServerlessPartial |
Deprecated provider routes(1)
| Provider | Status | Catalog ID |
|---|---|---|
| Together AI | DeprecatedRetired April 2, 2026 | mistralai/Mistral-Small-24B-Instruct-2501 |
Available via routers & gateways(1)
Capabilities
JSON / Tool useStructured Outputs
Benchmark peer barsfor Agents
No task-mapped benchmark peers are available for this model yet.
Benchmark scores(1)
Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 1194.0 | text creative_writing 2026-10-22Observed 2026-10-22 | Configuration: Mistral Small 24B Instruct (2501) Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral Small 24B Instruct (2501)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 313 of 416, rating 1194.4 (95% CI 1182.3-1206.5), 2415 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27. | Source Source: LMArena (lmarena.ai), CC BY 4.0 |
Migration checks
No linked migration route is available for this model yet.
Compare Mistral Small 3 with other models
- Mistral Small 3 vs Bielik 11B v2.6 Instruct41
- Mistral Small 3 vs DeepSeek V336
- Mistral Small 3 vs Mistral 7B v0.133
- Mistral Small 3 vs MiMo-V2.5-Pro22
- Mistral Small 3 vs Qwen3.5-9B21
- Mistral Small 3 vs Sarvam-M Multilingual Hybrid20
- Mistral Small 3 vs Nemotron Mini 4B Instruct16
- Mistral Small 3 vs Hunyuan Hy3 Preview15
Comparison and alternatives
Browse all comparisons →Mistral Small 3 vs Bielik 11B v2.6 InstructMistral Small 3 vs DeepSeek V3Mistral Small 3 vs Mistral 7B v0.1Mistral Small 3 vs MiMo-V2.5-ProMistral Small 3 vs Qwen3.5-9BMistral Small 3 vs Sarvam-M Multilingual HybridMistral Small 3 vs Nemotron Mini 4B InstructMistral Small 3 vs Hunyuan Hy3 PreviewMistral Small 3 vs Together AI - Llama 3 8B LiteMistral Small 3 vs Magistral Small 2506Mistral Small 3 vs Llama 3.1 NemoGuard 8B Topic ControlMistral Small 3 vs ELYZA Japanese Llama 2 13BMistral Small 3 vs Llama 2 7B ChatMistral Small 3 vs Falcon 3 7B InstructMistral Small 3 vs Llama 3.1 NemoGuard 8B Content SafetyMistral Small 3 vs Llama 2 7B
Show all 36 popular comparisonssorted by 7-day search impressions
Mistral Small 3 vs Mistral Medium 36Mistral Small 3 vs Seed-OSS 36B Instruct6Mistral Small 3 vs Hunyuan Turbo S5Mistral Small 3 vs Together AI - Gemma 3n-e4B5Mistral Small 3 vs Aquila 2 34B4Mistral Small 3 vs Phi-4 Mini Flash Reasoning4Mistral Small 3 vs Codex 14Mistral Small 3 vs text-davinci4Mistral Small 3 vs Aquila 2 7B4Mistral Small 3 vs Llama 3.1 Nemotron Nano 4B v1.13Mistral Small 3 vs ELYZA Japanese Llama 2 7B3Mistral Small 3 vs Llama 3.1 Swallow 8B Instruct3Mistral Small 3 vs MiniCPM 2B3Mistral Small 3 vs Llama 3.3 Nemotron Super 49B v13Mistral Small 3 vs GPT-43Mistral Small 3 vs GPT-23Mistral Small 3 vs Mistral Large 3 675B Instruct2Mistral Small 3 vs GPT-12Mistral Small 3 vs Granite Guardian 3.0 8B2Mistral Small 3 vs Gemma 2 9B SahabatAI Instruct1Mistral Small 3 vs Llama 3.1 Nemotron Nano VL 8B v11Mistral Small 3 vs Dracarys Llama 3.1 70B Instruct1Mistral Small 3 vs Italia 10B Instruct1Mistral Small 3 vs Llama 3 Taiwan 70B Instruct1Mistral Small 3 vs Marin 8B Instruct1Mistral Small 3 vs Claude Instant1Mistral Small 3 vs ShieldGemma 9B1Mistral Small 3 vs Stockmark 2 100B Instruct1Mistral Small 3 vs Claude Instant 1.11Mistral Small 3 vs Llama Guard 7B1Mistral Small 3 vs MiMo-V2.51Mistral Small 3 vs Nemotron Mini Hindi 4B Instruct1Mistral Small 3 vs GPT-2 Medium1Mistral Small 3 vs Qwen2-7B-Instruct1Mistral Small 3 vs Xiaomi MiMo-V2-Pro1Mistral Small 3 vs Llama 3.1 Nemotron 70B Reward1