Ministral 3 14B API Pricing: The Largest Ministral at Symmetric $0.20/M

Ministral 3 14B is the top of the Ministral line — symmetric pricing at $0.20/$0.20 with the best reasoning, most capable small model from Mistral. Approaches larger model quality at budget pricing.

Updated Aug 15, 2026 · 94 models tracked across 11 providers

TL;DR

Price: $0.20/M input, $0.20/M output — symmetric pricing, same cost for both
Context: 128K tokens — same as 3B and 8B
Size: 14B parameters — largest in the Ministral family, best reasoning
Provider: Mistral API (api.mistral.ai) or self-host via Hugging Face
Best for: Agentic workflows, complex reasoning, code generation, deep analysis
Trade-off: 33% more than 8B — but significantly better at complex tasks

Symmetric Pricing: Most AI models charge 2–10x more for output than input. Ministral 3 14B charges the same rate ($0.20/M) for both. This makes it especially cost-effective for agentic workflows and output-heavy tasks like code generation, analysis, and content creation — where you generate significant output relative to input.

Ministral 3 14B Pricing Breakdown

At $0.20 per million tokens for both input and output, here's how the costs scale:

Monthly Volume	Input Cost	Output Cost	Total Cost
1M tokens	$0.20	$0.20	$0.40
10M tokens	$2.00	$2.00	$4.00
100M tokens	$20.00	$20.00	$40.00
1B tokens	$200.00	$200.00	$400.00

Compare to Ministral 3 8B at $0.15/$0.15: the 14B costs 33% more but delivers significantly better reasoning on complex tasks. For demanding workloads like agentic workflows and deep analysis, the quality improvement justifies the price increase. Compared to 3B ($0.10/$0.10), the 14B is 2x more expensive but offers substantially better quality across the board.

Why Symmetric Pricing Matters

Most AI providers charge significantly more for output tokens than input. This penalizes tasks that generate lots of text — exactly the workloads where the 14B excels. Here's how Ministral 3 14B's symmetric pricing compares for output-heavy workloads:

Model	Input $/M	Output $/M	Output:Input Ratio	Cost at 70% Output
Ministral 3 14B	$0.20	$0.20	1:1	$20.00
Ministral 3 8B	$0.15	$0.15	1:1	$15.00
Ministral 3 3B	$0.10	$0.10	1:1	$10.00
GPT-5 nano	$0.05	$0.40	8:1	$16.50
Gemini 2.5 Flash-Lite	$0.10	$0.40	4:1	$16.00
DeepSeek V4 Flash	$0.14	$0.28	2:1	$12.60

At 100M tokens/month with 70% output, Ministral 3 14B ($20) is competitive with GPT-5 nano ($16.50) and Gemini 2.5 Flash-Lite ($16) — but with significantly better reasoning on complex tasks. The symmetric pricing means you don't pay a premium for generating the detailed outputs that agentic workflows require.

Ministral 3 14B vs Other Budget Models

Model	Input $/M	Output $/M	Context	Size	Provider
Qwen 3.7 Flash	$0.03	$0.13	1M	—	Alibaba
GPT-5 nano	$0.05	$0.40	128K	—	OpenAI
Ministral 3 3B	$0.10	$0.10	128K	3B	Mistral
Gemini 2.5 Flash-Lite	$0.10	$0.40	1M	—	Google
DeepSeek V4 Flash	$0.14	$0.28	1M	—	DeepSeek
Ministral 3 8B	$0.15	$0.15	128K	8B	Mistral
Ministral 3 14B	$0.20	$0.20	128K	14B	Mistral

Among Mistral models, the Ministral family offers 3 tiers: 3B ($0.10/$0.10), 8B ($0.15/$0.15), and 14B ($0.20/$0.20). All have symmetric pricing. The 14B is the top of the line — the best reasoning, most capable small model from Mistral, approaching larger model quality at a fraction of the cost.

The Ministral Family: 3B vs 8B vs 14B

Model	Input $/M	Output $/M	Context	Best For
Ministral 3 3B	$0.10	$0.10	128K	Simple classification, extraction, edge
Ministral 3 8B	$0.15	$0.15	128K	Moderate reasoning, code, analysis
Ministral 3 14B	$0.20	$0.20	128K	Complex tasks, agentic workflows

All three Ministral models share symmetric pricing and 128K context. The difference is capability: 3B handles simple tasks, 8B adds moderate reasoning and code generation, and 14B is the top of the line with the best reasoning for complex tasks and agentic workflows. The 14B approaches larger model quality — making it the best choice when quality matters more than minimizing cost.

When to Use Ministral 3 14B

🤖 Agentic Workflows

Multi-step tool use, planning, and decision-making. The 14B parameters provide the reasoning depth needed for reliable autonomous agents.

🧠 Complex Reasoning

Tasks that require multi-hop logic, analysis, and synthesis. The 14B handles nuance and complexity that smaller models struggle with.

💻 Code Generation

Generate complex functions, debug issues, and write production-quality code. The 14B produces more reliable output than 8B on harder programming tasks.

📊 Deep Analysis

Analyze documents, extract insights, and synthesize findings. 14B parameters provide the best analytical capability in the Ministral family.

📝 Output-Heavy Tasks

Summarization, translation, content generation. Symmetric pricing means you don't pay a premium for generating detailed text output.

🔄 High-Volume Pipelines

Process complex items at scale. Budget pricing with top-tier Ministral quality makes high-volume complex processing affordable.

Real-World Cost: 25,000 Complex Analysis Tasks/Month

Suppose you're building an analysis service that handles 25,000 complex tasks per month, averaging 1,000 input tokens and 2,000 output tokens per task — the kind of heavier workloads where the 14B model's extra capability pays off:

Model	Input Cost	Output Cost	Monthly Total
Ministral 3 14B	$5.00	$10.00	$15.00
Ministral 3 8B	$3.75	$7.50	$11.25
Ministral 3 3B	$2.50	$5.00	$7.50
GPT-5 nano	$1.25	$20.00	$21.25
Gemini 2.5 Flash-Lite	$2.50	$20.00	$22.50
DeepSeek V4 Flash	$3.50	$14.00	$17.50

For this output-heavy workload (67% output), Ministral 3 14B at $15/month delivers the best quality in the Ministral family while remaining cheaper than GPT-5 nano ($21.25) or Gemini Flash-Lite ($22.50). The 33% premium over 8B buys significantly better reasoning on complex tasks — and symmetric pricing keeps costs predictable.

Compare 94 AI Models Side by Side

Ministral 3 14B is one of 94 models tracked on APIpulse. Compare pricing, context windows, and features across 11 providers.

Compare Models Cost Calculator

Frequently Asked Questions

How much does Ministral 3 14B cost?

Ministral 3 14B costs $0.20 per million input tokens and $0.20 per million output tokens. This symmetric pricing means input and output cost the same — unusual in the AI industry where output is typically 2-10x more expensive.

What is the context window of Ministral 3 14B?

Ministral 3 14B has a 128K token context window. This is the same as the 3B and 8B models in the Ministral family — sufficient for most chat, analysis, and agentic workflow tasks.

How does Ministral 3 14B compare to 8B?

Ministral 3 14B costs $0.20/$0.20 vs 8B's $0.15/$0.15 — a 33% price increase. In return, 14B offers significantly better reasoning on complex tasks, stronger code generation, and more reliable agentic workflows. For demanding production workloads, 14B is worth the premium.

Is Ministral 3 14B good for agentic workflows?

Yes. Ministral 3 14B is the best choice in the Ministral family for agentic workflows. Its 14B parameters provide the reasoning depth needed for multi-step tool use, planning, and complex decision-making — approaching larger model quality at a budget price point.

Can I self-host Ministral 3 14B?

Yes. Ministral 3 14B is available through Mistral's API (api.mistral.ai) and can also be self-hosted via Hugging Face. Self-hosting eliminates per-token costs but requires GPU infrastructure (a single high-end consumer GPU or professional GPU can run 14B models).

Ministral 3 8B Pricing — Cheaper at $0.15/$0.15, best value for moderate tasks
Ministral 3 3B Pricing — Cheapest at $0.10/$0.10 for simple tasks
GPT-5 nano Pricing — OpenAI's cheapest at $0.05/$0.40
Gemini 2.5 Flash-Lite Pricing — Google's cheapest at $0.10/$0.40
Full Model Rankings — All 94 models ranked by price