Not published
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / MISTRAL AI
GA code-embedding specialist for semantic representations used in code retrieval, search, clustering and similarity workflows.
PRIMARY-SOURCE VERIFIED
Mistral AI documents a 8,000-token context window. Input modalities: text. Output: embedding. 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Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.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 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 Embed is GA Premier v25.05 with an 8k context window and an embeddings API endpoint.
Mistral publishes $0.15 per million input tokens and $0.015 per million cached input tokens with no output-token rate.
The model is excluded from the generative token calculator because embeddings have no output-token price dimension.
EXPLORE
OFFICIAL SOURCES
WHAT CHANGED
No post-baseline factual changes recorded for Codestral Embed since 2026-10-06.
VERIFIED CHANGE HISTORY
Baseline verified: 8,000 context · Not published max output · $0.15 input / $0.015 cached per 1 million tokens
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head c70e6cd5a809…