Models/Mistral/Mistral Small 3

Mistral Small 3

Mistral · Open weights · Released Jan 30, 2025 · mistralai/mistral-small-24b-instruct-2501
Best $0.05 in / $0.08 out via DeepInfra · fp8
CompareEstimate cost
33K contextStructured outputOpen weights
Available from 1 providerUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 16 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
PROVIDERINPUTOUTPUTCACHECONTEXTQUANTTTFTTPSUPTIME
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 16 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
About

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...

Specifications
Context window32,768
Max output16,384
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedJan 30, 2025
Knowledge cutoff2023-10-31
TokenizerMistral
Open weights
Downloads61.6K
Likes970
Licenseapache-2.0
safetensors
Embed badge
Mistral Small 3 price and speed badge
[![Mistral Small 3](https://modelindex.ai/badge/mistralai/mistral-small-24b-instruct-2501)](https://modelindex.ai/models/mistralai/mistral-small-24b-instruct-2501)
Sources
OpenRouter API23 minutes ago
AGGREGATOR
Hugging Face23 minutes ago
COMMUNITY
ModelIndex benchmarks16 days ago
MEASURED
Verified 23 minutes ago · list prices, not negotiated rates.