BroadRouter

Ministral 3 14B API pricing

Updated

Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), 3 tie for the lowest blended standard price for Ministral 3 14B; Mistral AI charges USD 0.20 per 1M input tokens and USD 0.20 per 1M output tokens. The median across 3 standard prices is USD 0.20 / USD 0.20. That is Mistral AI's own API.

Mistral AI · slug ministral-14b-2512 · up to 262,144 tokens of context · 3 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index.

What does Mistral AI charge for Ministral 3 14B?

Input
USD 0.20
Cached input
USD 0.02
Output
USD 0.20
Blended 3:1
USD 0.20

USD per 1M tokens on Mistral AI, model ministral-14b-2512, standard tier. Source, checked 2026-11-14.

Other Mistral AI tiers: batch USD 0.10 / USD 0.10 · priority USD 0.35 / USD 0.35.

Is a host cheaper than Mistral AI? They tie. Amazon Bedrock and Mistral AI's own API both work out at USD 0.20 per 1M tokens on the 3:1 blend.

Ministral 3 14B price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 0% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Ministral 3 14B API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1Mistral AI tied cheapest maker
ministral-14b-2512
Notes and source quote

Context from the docs model card.

“Ministral 3 14B ↗ $0.2 $0.02 $0.2”
USD 0.20USD 0.02USD 0.20USD 0.20262,144not statedMistral AI page
checked 2026-11-14
re-checked 2026-11-16
2Amazon Bedrock tied cheapest
Notes and source quote

Table headed "Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)".

“Ministral 14B 3.0 $ 0.20 $ 0.20”
USD 0.20not publishedUSD 0.20USD 0.20not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
3DigitalOcean tied cheapest
Notes and source quote

DigitalOcean-hosted.

“Ministral 3 14B Instruct — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.20$0.20$0.04”
USD 0.20USD 0.04USD 0.20USD 0.20not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16
—Mistral AI maker batch
ministral-14b-2512
Notes and source quote

Context from the docs model card.

“Ministral 3 14B ↗ $0.1 $0.01 $0.1 (Batch tab, "Batch (-50%)")”
USD 0.10USD 0.01USD 0.10USD 0.10262,144not statedMistral AI page
checked 2026-11-14
re-checked 2026-11-16
—Mistral AI maker priority
ministral-14b-2512
Notes and source quote

Context from the docs model card.

“Ministral 3 14B ↗ $0.35 $0.035 $0.35 (Priority tab, "Priority (+75%)")”
USD 0.35USD 0.035USD 0.35USD 0.35262,144not statedMistral AI page
checked 2026-11-15
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does Ministral 3 14B cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on Ministral 3 14B, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
Mistral AI (maker)USD 11.88USD 38.04USD 102.60
Amazon BedrockUSD 21.60USD 51.00USD 378.00
DigitalOceanUSD 12.96USD 39.48USD 133.20

For the support chatbot, the cheapest price (Mistral AI, USD 11.88 a month) saves USD 1.08 against the median (USD 12.96). For the coding agent the gap is USD 30.60 a month (23% lower).

Which Ministral 3 14B provider is cheapest for your traffic?

All 3 providers charge the same standard price, USD 0.20 input and USD 0.20 output per 1M tokens, so the per-token price does not decide between them: compare the cache and context lines below.

Ministral 3 14B: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
Mistral AI (maker)USD 0.20 cheapestUSD 0.1325 cheapestUSD 0.0785 cheapest
Amazon Bedrock (no cache price)USD 0.20 cheapestUSD 0.20USD 0.20
DigitalOceanUSD 0.20 cheapestUSD 0.14USD 0.092

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

2 of 3 providers publish a cached-input price below the input price: Mistral AI (90% off), DigitalOcean (80% off). Amazon Bedrock publishes none, so cached tokens there bill at the input price.

Mistral AI states a context window of 262,144 tokens; Amazon Bedrock and DigitalOcean do not state one.

What does Ministral 3 14B cost in other languages?

The same text needs a different number of tokens in each language. With the Ministral 3 14B tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for Ministral 3 14B:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.044Amazon Bedrock
Arabic MSAUSD 0.060Amazon Bedrock
HindiUSD 0.076Amazon Bedrock
ChineseUSD 0.180Amazon Bedrock
CodeUSD 0.054Amazon Bedrock

From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.

Estimate your own bill

The Mistral AI models whose cheapest standard price is closest to Ministral 3 14B's (USD 0.20 blended):

Mistral AI models priced closest to Ministral 3 14B
ModelCheapest inputCheapest outputMax contextProviders
Mistral Small 3.1 24B InstructUSD 0.10USD 0.3032,7684
Ministral 3 8BUSD 0.15USD 0.15262,1442
Mistral Small 3.2 24B InstructUSD 0.075USD 0.20256,0004
Ministral 3 3BUSD 0.10USD 0.10262,1442
Mistral-Small-24B-Instruct-2501USD 0.05USD 0.0832,7682
Mistral Large 3USD 0.50USD 1.50—3

Priced closest from other makers: Claude Haiku 5.5 (Anthropic, USD 0.20) · DeepSeek R1 Distill Qwen 14B (DeepSeek, USD 0.20) · GPT-6 Luna (OpenAI, USD 0.20).

Compare Ministral 3 14B with

Also compared: vs Ministral 3 8B.

Every Ministral 3 14B price comparison · All model-vs-model price comparisons

All 431 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the Ministral 3 14B API cost per token?

From USD 0.20 per 1M input tokens (USD 0.0000002 per token) and USD 0.20 per 1M output tokens (USD 0.0000002 per token) at the lowest standard prices we found. The median of 3 standard prices is USD 0.20 input and USD 0.20 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for Ministral 3 14B?

Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), 3 are tied for the lowest price: Mistral AI, Amazon Bedrock and DigitalOcean, each USD 0.20 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 0.20 (Mistral AI and 2 others, tied); for output alone, USD 0.20 (Mistral AI and 2 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is Ministral 3 14B cheaper from a host than from Mistral AI?

They tie. Amazon Bedrock and Mistral AI's own API both work out at USD 0.20 per 1M tokens on the 3:1 blend.

Does Ministral 3 14B have cached input pricing?

2 of 3 standard prices include one. The lowest is USD 0.02 per 1M at Mistral AI; the median is USD 0.03. Providers without one bill cached input at the input price. What cached input means.

What is the Ministral 3 14B context window?

262,144 tokens on every provider that states it.

How much does a coding agent cost per month on Ministral 3 14B?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 102.60 a month at Mistral AI, USD 133.20 at the median price and USD 378.00 at Amazon Bedrock. Try your own numbers.

Is there a batch, flex or priority price for Ministral 3 14B?

Yes: batch from Mistral AI at USD 0.10 / USD 0.10; priority from Mistral AI at USD 0.35 / USD 0.35 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

Is Ministral 3 14B free to use through an API?

No provider in our data lists a free price for Ministral 3 14B as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity