Compute Comparison
RouterPlus/MinistralBudget

ministral-3b-2512

ministral-3b-2512 Pricing per 1M tokens
Input$0.100
Output$0.100
Cached input$0.010
View RouterPlus
Context Window
131K
tokens
About ministral-3b-2512

ministral-3b-2512 is a budget-tier language model from RouterPlus. ministral-3b-2512 is a proprietary model available exclusively through RouterPlus's API. The Ministral family is RouterPlus's model series for this capability tier.

ministral-3b-2512 is priced at $0.1/1M input tokens and $0.1/1M output tokens. Output tokens are 1× more expensive than input tokens — this ratio reflects the sequential nature of autoregressive generation, which requires a separate forward pass per output token versus parallel processing of all input tokens simultaneously. At a typical usage pattern of 1,000 input tokens and 500 output tokens per call, ministral-3b-2512 costs approximately $0.15 per 1,000 API calls. Prompt caching reduces repeated input tokens to $0.01/1M — a 90% discount that compounds significantly for applications with long shared system prompts, multi-turn conversations, or document Q&A where the same context is reused across many queries.

Its 131K-token context window handles most long-document tasks — roughly 75,000 words or a full novel — without requiring chunking or retrieval augmentation.

ministral-3b-2512 is best suited to general language tasks. Supported capabilities include function calling / tool use for agentic workflows, streaming token output for real-time UIs. Function calling support makes it suitable for building AI agents, structured data extraction pipelines, and any workflow requiring the model to invoke external APIs or return typed JSON. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how ministral-3b-2512 compares to similar models across these dimensions.

ministral-3b-2512 sits in the budget tier — the most cost-efficient models, best for high-volume simple tasks, classification, extraction, and applications where cost per call is the primary constraint. Unlike open-weights alternatives, ministral-3b-2512 is only available via RouterPlus's API — there is no self-hosted option, which simplifies deployment but creates vendor dependency. When comparing ministral-3b-2512 to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (N/A/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.

ministral-3b-2512 Pricing vs Budget Tier
CheapestThis modelMost expensive
$0.020$0.100$0.500

Input price vs 119 budget models tracked. Avg: $0.110/1M.

ministral-3b-2512 Capabilities
Vision / Images✗
Function Calling✓
Streaming✓
Prompt Caching✓
Reasoning / CoT✗
Open Weights✗
Computer Use✗
Web Search✗
ministral-3b-2512 Full Specifications
Model IDministral-3b-2512
ProviderRouterPlus
Model FamilyMinistral
TierBudget
Context Window131,072 tokens (131K)
Max Output Tokens—
Input Price$0.1 / 1M tokens
Output Price$0.1 / 1M tokens
Cached Input Price$0.01 / 1M tokens
Throughput—
Latency (P50)—
Intelligence Score—
LiveBench Score—
Cost per Task (LiveBench)—
Data Confidence—
HLE Score—
GPQA Diamond—
SWE-bench Score—
OSWorld Score—
BrowseComp Score—
Terminal-Bench Score—
AutoBench Score—
Parameters—
Vision SupportNo
Function CallingYes
StreamingYes
Reasoning ModelNo
Open WeightsNo
Data SourceLive API
Last Updated2026-11-01
ministral-3b-2512 Frequently Asked Questions