Ministral 3B 2512
Ministral 3B 2512 is a Mistral AI model available in SteelEngine. It supports a 131k token context window. Pricing starts at $0.1/1M input tokens and $0.1/1M output tokens. Key capabilities include Temperature 0-1, Tool choice, Structured outputs.
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.
INPUT / 1M
$0.1
CACHED INPUT / 1M
$0.01
OUTPUT / 1M
$0.1
CONTEXT WINDOW
131k
MAX OUTPUT
Not published
PRICING
What Ministral 3B 2512 costs to run.
List prices in USD per 1M tokens. Cached input applies when a request reuses a prompt the provider has already cached.
01 / INPUT
$0.1
per 1M input tokens
02 / CACHED INPUT
$0.01
per 1M cached input tokens
03 / OUTPUT
$0.1
per 1M output tokens
LONG CONTEXT
SUPPORTED CAPABILITIES
What Ministral 3B 2512 supports.
Capabilities show up as model settings on SteelEngine workflow blocks and agents, so teams can tune each step without changing providers.
CAPABILITIES
Temperature 0-1, Tool choice, Structured outputs
CONTEXT WINDOW
131k
MAX OUTPUT TOKENS
Not published
MODEL ID
ministral-3b-2512
PROVIDER
Mistral AI
MORE MODELS
More from Mistral AI
Compare nearby options from the same provider before you pick a default for your workflow.
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
BUILD WITH STEELENGINE
Put Ministral 3B 2512 to work.
Use this model in deterministic workflow steps or production agents, with approvals, guardrails, and a full audit trail around every call.