Mistral Small 3
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...
Updated 1 h ago · first seen 11 Sept 2026
model_01M294WWKHXX15VKK583700RHM
- Context
- 32K tokens
- T2 · 1 h ago
- Released
- 30 Jan 2025
- T2 · 3 h ago
- Knowledge cutoff
- Oct 2023
- T2 · 3 h ago
Specification
- Release date
- 30 Jan 2025
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Status
- deprecated
Source:Artificial AnalysisT2observed 1 h agomedium
- Openness
- open-weights
Source:Artificial AnalysisT2observed 1 h agomedium
- Context window
- 32K tokens
Source:Artificial AnalysisT2observed 1 h agomedium
- Max output
- 16.4K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Knowledge cutoff
- Oct 2023
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Modalities
- text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Input modalities
- text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Tokenizer
- Mistral
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Hugging Face repo
- mistralai/Mistral-Small-24B-Instruct-2501
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Aa median output tokens per second
- 143.8
Source:Artificial AnalysisT2observed 1 h agomedium
- Openrouter id
- mistralai/mistral-small-24b-instruct-2501
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Supported parameters
- frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_p
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
18
Source tiers
T218
Freshest observation
1 h ago
Conflicts
None
Modalities
- Modalities
- text
- Input
- text
- Output
- text
Capabilities
Tool calling
No
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
No
Artificial Analysis · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 32K tokens
Source:Artificial AnalysisT2observed 1 h agomedium
- Max output
- 16.4K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Knowledge cutoff
- Oct 2023
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Tokenizer
- Mistral
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| τ²-bench | 19.59% | pass^1 | aa_slug=mistral-small-3 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Artificial Analysis Intelligence Index | 6.67 | index | aa_slug=mistral-small-3 · version=4.3 · estimated=true | — | artificialanalysis.aiT2 |
| GPQA | 46.16% | accuracy | aa_slug=mistral-small-3 · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 3.76% | accuracy | aa_slug=mistral-small-3 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| IFBench | 26.39% | accuracy | aa_slug=mistral-small-3 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| Mistral AI La Plateformemistralai/mistral-small-24b-instruct-2501 | $0.05 | $0.08 | — | — | 32.8K | 1 h ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- Mistral AI La Plateforme
No hardware estimate available
No lineage recorded
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Modalities
Modalitiesmodalities1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Mistral Small 3 scores 19.59% on τ²-bench
artificial_analysisMistral Small 3 scores 26.39% on IFBench
artificial_analysisMistral Small 3 scores 3.76% on Humanity's Last Exam
artificial_analysisMistral Small 3 scores 46.16% on GPQA
artificial_analysisMistral Small 3 scores 6.67 on Artificial Analysis Intelligence Index
artificial_analysisMistral Small 3: context length changed from 32768 to 32000
Context window32.8K tokens→32K tokensartificial_analysisMistral AI La Plateforme lists Mistral Small 3 at $0.05 in / $0.08 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 1 h ago | 1 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 1 h ago | 2 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.