Back to models
Model · ministral-3b-latest

Ministral 3B

This supply profile is generated from Mistral AI's active provider model rate card because no explicit offering version exists for the model yet.

standard
confidential
responses
128k ctx
1 provider

Lane pricing

Provider rates, live status, and capability fit for this model.

input $0.05, output $0.05 per 1M tokens from currently available batch provider base rates.

Capabilities

Catalog model

Runtime

No advanced runtime capability has been declared.

Hosted tools

No provider-hosted web search, code execution, retrieval, or other tools declared.

Why use this model

Batch-ready workload fit

Use it for responses jobs where cost, routing auditability, and async delivery matter more than single-request latency.

Known context envelope

The catalog declares a 128k context window, which helps reject lanes that cannot fit large batch items before dispatch.

Privacy tier awareness

Available privacy tiers include standard, confidential, so routing can enforce buyer constraints.

Readable route economics

Per-lane input, cached-input, and output rates are shown in the page instead of buried in a raw JSON payload.

Providers
1
Best p50
Context
128k

Providers serving this model

View rankings →
  • mi
    mistral
    mistral
    Active
    No refresh
    No heartbeat

Route a batch to Ministral 3B

Cost estimate in <200ms. Final charge follows delivered token usage.

Start free