Not published
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / MISTRAL AI
GA code-completion specialist optimized for low-latency, high-frequency FIM and code generation.
PRIMARY-SOURCE VERIFIED
Mistral AI documents a 128,000-token context window. Input modalities: text. 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Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.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
$0.30 input · $0.03 cached · $0.90 output per 1 million tokens.
SXF preserves the provider-published native billing basis. Only calculator-eligible generative token models enter token-cost arithmetic; specialist units and input-only embeddings remain visible without forced conversion.
CAVEATS
Codestral v25.08 is the current GA Premier code-completion model; the older v25.01 model is retired.
Mistral publishes a 128k context window and Standard rates of $0.30 input, $0.03 cached input, and $0.90 output per million tokens.
No separate max-output limit or knowledge cutoff is published in the cited model card.
EXPLORE
OFFICIAL SOURCES
WHAT CHANGED
No post-baseline factual changes recorded for Codestral since 2026-10-06.
VERIFIED CHANGE HISTORY
Baseline verified: 128,000 context · Not published max output · $0.30 input / $0.03 cached / $0.90 output per 1 million tokens
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head c70e6cd5a809…