Mistral AI

Flagship open-weight general-purpose multimodal MoE model (41B active / 675B total params), 256k context, $0.5/$1.5 per M tokens. Primary source: docs.mistral.ai model card (https://docs.mistral.ai/models/model-cards/mistral-large-3-25-12) — verbatim: "Mistral Large 3, is a state-of-the-art, open-we

262K

Context

$0.50

In $/M

$1.50

Out $/M

—

Cutoff

Frontier-class multimodal model optimized for agentic and coding use cases; headline model on the pricing page at $1.5/$7.5 per M tokens, 256k context, open weights under Modified MIT. Primary source: docs.mistral.ai model card (https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04) —

262K

Context

$1.50

In $/M

$7.50

Out $/M

November 1, 2024

Cutoff

Current small/open-weight model (v26.03); hybrid model unifying instruct, reasoning, and coding in one model, 119B params with 6.5B active. Primary source: docs.mistral.ai model card (https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03) — verbatim: "Our powerful hybrid model unifying

262K

Context

$0.15

In $/M

$0.60

Out $/M

—

Cutoff

Current code-specialist model for code completion / fill-in-the-middle and generation; named as the non-deprecated replacement for older Codestral versions in the models overview table. Primary source: docs.mistral.ai model card (https://docs.mistral.ai/models/model-cards/codestral-25-08) — verbatim

131K

Context

$0.30

In $/M

$0.90

Out $/M

—

Cutoff