none · high
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / MISTRAL AI
Efficient open-weight multimodal Mistral model combining instruct, reasoning and coding capabilities for production and agentic workloads.
PRIMARY-SOURCE VERIFIED
Mistral AI documents a 256,000-token context window. Input modalities: text + image. Output: text. Pricing status: Official paid API.
CAPABILITY CONTRACT
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
Input modalities come from the cited official model documentation.
Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.
PRICING STATUS
$0.15 input · $0.015 cached · $0.60 output / MTok.
Only provider-published Standard paid token rates enter the SXF calculator. Partner hosting prices, negotiated rates and self-hosting costs are not substituted for a missing provider rate.
CAVEATS
Mistral publishes the context window as 256k tokens; SXF stores this as 256,000 for normalized numeric filtering.
No separate max-output token cap or knowledge cutoff is published in the cited model card, so those fields remain unknown.
Mistral Small 4 is GA and released under Apache 2.0 as open weights.
EXPLORE
OFFICIAL SOURCES
WHAT CHANGED
No post-baseline factual changes recorded for Mistral Small 4 since 2026-10-06.
VERIFIED CHANGE HISTORY
Baseline verified: 256,000 context · Not published max output · $0.15 input / $0.60 output per MTok
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head 2ea333e862b9…