mistralai
Mistral: 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...
Quality Score
64/100
composite of price, context, capability
Input Price
$0.05
per 1M tokens
Output Price
$0.08
per 1M tokens
Context Window
32,768
tokens
- Model ID
- mistralai/mistral-small-24b-instruct-2501
- Vendor
- mistralai
- Tokenizer
- Mistral
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 16,384 tokens
- Tool Calling
- not supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- text only
- Audio
- no
- Moderated
- no
Similar models
mistralai
Mistral: Mistral Small Creative
$0.10 in / $0.30 out
32,768 ctx
68
mistralai
Mistral: Mistral 7B Instruct v0.1
$0.11 in / $0.19 out
2,824 ctx
55
mistralai
Mistral: Mixtral 8x7B Instruct
$0.54 in / $0.54 out
32,768 ctx
73
mistralai
Mistral: Saba
$0.20 in / $0.60 out
32,768 ctx
73
mistralai
Mistral: Mixtral 8x22B Instruct
$2.00 in / $6.00 out
65,536 ctx
74
mistralai
Mistral: Mistral Small 3.1 24B
$0.35 in / $0.56 out
128,000 ctx
75