/

/

Mistral AI

MODEL PROVIDER

Mistral AI

Mistral AI’s models through the Mistral API, from small Ministral models to Mistral Large, plus Magistral for reasoning and Codestral and Devstral for code.

Mistral AI has 18 models available in SteelEngine with pricing, context window, and capability details.

MODELS

18

DEFAULT MODEL

Mistral Large Latest

PRICING

USD PER 1M TOKENS

MODELS

Mistral AI models in SteelEngine.

Recommended models come first. Open any model for its full price sheet, limits, and supported capabilities.

Mistral AI

Mistral Large Latest

Higher-priced model for demanding generation and analysis. Handles 262k tokens of context. Alias that tracks the provider’s newest release of this model.

IN / 1M

$0.5

OUT / 1M

$1.5

CONTEXT

262k

Mistral AI

Mistral Large 2512

Higher-priced model for demanding generation and analysis. Handles 262k tokens of context. Pinned snapshot 2512 for reproducible behavior.

IN / 1M

$0.5

OUT / 1M

$1.5

CONTEXT

262k

Mistral AI

Mistral Small 2603

Mid-priced, latency-focused model for chat, drafting, and tool calling. Handles 262k tokens of context. Pinned snapshot 2603 for reproducible behavior.

IN / 1M

$0.15

OUT / 1M

$0.6

CONTEXT

262k

Mistral AI

Mistral Medium Latest

Among the highest-priced models in the Mistral AI lineup, for the hardest generation and analysis work. Handles 262k tokens of context.

IN / 1M

$1.5

OUT / 1M

$7.5

CONTEXT

262k

Mistral AI

Mistral Small Latest

Mid-priced, latency-focused model for chat, drafting, and tool calling. Handles 262k tokens of context. Alias that tracks the provider’s newest release of this model.

IN / 1M

$0.15

OUT / 1M

$0.6

CONTEXT

262k

Mistral AI

Ministral 14B 2512

Fast, lower-priced model for high-volume classification, extraction, and routing. Handles 262k tokens of context. 14B-parameter size in its family.

IN / 1M

$0.2

OUT / 1M

$0.2

CONTEXT

262k

Mistral AI

Ministral 8B Latest

Fast, lower-priced model for high-volume classification, extraction, and routing. Handles 262k tokens of context. Alias that tracks the provider’s newest release of this model.

IN / 1M

$0.15

OUT / 1M

$0.15

CONTEXT

262k

Mistral AI

Ministral 8B 2512

Fast, lower-priced model for high-volume classification, extraction, and routing. Handles 262k tokens of context. 8B-parameter size in its family.

IN / 1M

$0.15

OUT / 1M

$0.15

CONTEXT

262k

Mistral AI

Mistral Medium 3.5

Among the highest-priced models in the Mistral AI lineup, for the hardest generation and analysis work. Handles 256k tokens of context.

IN / 1M

$1.5

OUT / 1M

$7.5

CONTEXT

256k

Mistral AI

Devstral Latest

Coding model for writing, reviewing, and refactoring code in agent workflows. Handles 256k tokens of context.

IN / 1M

$0.4

OUT / 1M

$2

CONTEXT

256k

Mistral AI

Devstral Small Latest

Lower-priced coding model for completions, small edits, and code-aware tool calls. Handles 256k tokens of context.

IN / 1M

$0.1

OUT / 1M

$0.3

CONTEXT

256k

Mistral AI

Ministral 14B Latest

Fast, lower-priced model for high-volume classification, extraction, and routing. Handles 256k tokens of context.

IN / 1M

$0.2

OUT / 1M

$0.2

CONTEXT

256k

Mistral AI

Ministral 3B Latest

Among the lowest-cost models in the Mistral AI lineup, for high-volume classification, extraction, and routing. Handles 131k tokens of context. Alias that tracks the provider’s newest release of this model.

IN / 1M

$0.1

OUT / 1M

$0.1

CONTEXT

131k

Mistral AI

Ministral 3B 2512

Among the lowest-cost models in the Mistral AI lineup, for high-volume classification, extraction, and routing. Handles 131k tokens of context. Pinned snapshot 2512 for reproducible behavior.

IN / 1M

$0.1

OUT / 1M

$0.1

CONTEXT

131k

Mistral AI

Magistral Medium Latest

Higher-priced reasoning model for complex planning and multi-step agent work. Handles 128k tokens of context. The medium size in its family.

IN / 1M

$2

OUT / 1M

$5

CONTEXT

128k

Mistral AI

Magistral Small Latest

Higher-priced reasoning model for complex planning and multi-step agent work. Handles 128k tokens of context. The small size in its family.

IN / 1M

$0.5

OUT / 1M

$1.5

CONTEXT

128k

Mistral AI

Codestral Latest

Coding model for writing, reviewing, and refactoring code in agent workflows. Handles 128k tokens of context. Alias that tracks the provider’s newest release of this model.

IN / 1M

$0.3

OUT / 1M

$0.9

CONTEXT

128k

Mistral AI

Codestral 2508

Coding model for writing, reviewing, and refactoring code in agent workflows. Handles 128k tokens of context. Pinned snapshot 2508 for reproducible behavior.

IN / 1M

$0.3

OUT / 1M

$0.9

CONTEXT

128k

BUILD WITH STEELENGINE

Put Mistral AI models to work.

Use these models in deterministic workflow steps or production agents, with approvals, guardrails, and a full audit trail around every call.