---
title: "Ministral 3 14B vs Ministral 3 8B API pricing compared"
description: "Ministral 3 14B vs Ministral 3 8B API price per 1M tokens: USD 0.20 / USD 0.20 vs USD 0.15 / USD 0.15 input/output, from providers' own pricing pages."
url: https://broadrouter.com/llm-api-pricing/compare/ministral-14b-2512-vs-ministral-8b-2512/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Ministral 3 14B vs Ministral 3 8B API pricing

Updated 2026-11-15

Ministral 3 14B: USD 0.20 input, USD 0.20 output per 1M tokens (Mistral AI and 2 others). Ministral 3 8B: USD 0.15 input, USD 0.15 output per 1M tokens (Mistral AI and 1 other). At 3 input tokens per output token, Ministral 3 14B costs 33% more than Ministral 3 8B (USD 0.20 vs USD 0.15 per 1M).

Ministral 3 14B and Ministral 3 8B are neighbouring sizes of the same Mistral AI generation (14B and 8B parameters, by name). **Price only**: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

## How do Ministral 3 14B and Ministral 3 8B differ on price?

-   Cheapest input price: Ministral 3 8B USD 0.15 against USD 0.20 per 1M tokens, so Ministral 3 14B costs 1.33× as much (33% more).
-   Cheapest output price: Ministral 3 8B USD 0.15 against USD 0.20 per 1M tokens, so Ministral 3 14B costs 1.33× as much (33% more).
-   Among the 201 indexed models, Ministral 3 14B ranks 56th cheapest and Ministral 3 8B 40th on the 3:1 blend.
-   No input:output mix changes the answer: Ministral 3 8B is cheaper at every mix before cache discounts.
-   Both list cached-input discounts: Ministral 3 14B at 2 standard prices of 3, from USD 0.02 (Mistral AI, 90% below that provider's input price); Ministral 3 8B at 1 standard price of 2, from USD 0.015 (Mistral AI, 90% below that provider's input price).
-   Both state a context window of up to 262,144 tokens.
-   Ministral 3 14B has 3 providers with a standard price, 1 more than Ministral 3 8B; 2 providers sell both (Amazon Bedrock and Mistral AI).
-   On one account, Amazon Bedrock charges USD 0.20 for Ministral 3 14B (its cheapest price) and USD 0.15 for Ministral 3 8B (its cheapest price) at 3:1, tied with 1 other provider for the lowest combined price among the providers that sell both.
-   Shopping around matters equally: on both, the dearest standard price is 1× the cheapest.
-   Mistral AI's own API is one of 3 providers tied for the lowest standard price we found for Ministral 3 14B, USD 0.20 at 3:1.
-   Mistral AI's own API is one of 2 providers tied for the lowest standard price we found for Ministral 3 8B, USD 0.15 at 3:1.
-   Ministral 3 14B has a batch price at 1 provider, from USD 0.10 at 3:1 (Mistral AI); Ministral 3 8B has a batch price at 1 provider, from USD 0.075 at 3:1 (Mistral AI).
-   For the one-developer coding agent preset, the gap is USD 307.80 a year in Ministral 3 8B's favour (Ministral 3 14B USD 102.60 a month, Ministral 3 8B USD 76.95).
-   Per character of input, Ministral 3 14B costs 1.33× as much as Ministral 3 8B in every measured language, because both use the Ministral 3 14B tokenizer.

## Ministral 3 14B and Ministral 3 8B prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

Ministral 3 14B and Ministral 3 8B API prices compared
| Price | Ministral 3 14B | Ministral 3 8B |
| --- | --- | --- |
| Model page | [Ministral 3 14B](https://broadrouter.com/llm-api-pricing/ministral-14b-2512/) · Mistral AI · 3 providers | [Ministral 3 8B](https://broadrouter.com/llm-api-pricing/ministral-8b-2512/) · Mistral AI · 2 providers |
| Cheapest standard price, blended 3:1 | USD 0.20 · USD 0.20 in / USD 0.20 out at Mistral AI and 2 others · [Mistral AI page](https://docs.mistral.ai/inference/pricing) checked 2026-11-14 | USD 0.15 lower · USD 0.15 in / USD 0.15 out at Mistral AI and 1 other · [Mistral AI page](https://docs.mistral.ai/inference/pricing) checked 2026-11-14 |
| Cheapest input | USD 0.20 · Mistral AI [source](https://docs.mistral.ai/inference/pricing) | USD 0.15 lower · Mistral AI [source](https://docs.mistral.ai/inference/pricing) |
| Cheapest cached input | USD 0.02 · Mistral AI [source](https://docs.mistral.ai/inference/pricing) | USD 0.015 lower · Mistral AI [source](https://docs.mistral.ai/inference/pricing) |
| Cheapest output | USD 0.20 · Mistral AI [source](https://docs.mistral.ai/inference/pricing) | USD 0.15 lower · Mistral AI [source](https://docs.mistral.ai/inference/pricing) |
| Maker's own API | USD 0.20 / USD 0.20 · Mistral AI [source](https://docs.mistral.ai/inference/pricing) | USD 0.15 / USD 0.15 · Mistral AI [source](https://docs.mistral.ai/inference/pricing) |
| Median standard price | USD 0.20 / USD 0.20 · input / output, 3 prices | USD 0.15 / USD 0.15 · input / output, 2 prices |
| Context window | 262,144 tokens, largest stated | 262,144 tokens, largest stated |
| Providers with a standard price | 3 | 2 |

-   **Lower** marks the lower price on a line; **tie**, equal prices. Other tiers and free rows are on the model pages.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20Ministral%203%2014B%20vs%20Ministral%203%208B%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fcompare%2Fministral-14b-2512-vs-ministral-8b-2512%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What do Ministral 3 14B and Ministral 3 8B cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the [cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/?model=ministral-14b-2512,ministral-8b-2512); cached input at the cached price where listed).

Monthly cost of three workloads on Ministral 3 14B and Ministral 3 8B
| Workload | Ministral 3 14B | Ministral 3 8B | Difference |
| --- | --- | --- | --- |
| **Support chatbot** · 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 11.88 · Mistral AI | USD 8.91 · Mistral AI | USD 2.97 · Ministral 3 8B lower |
| **RAG over documents** · 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 38.04 · Mistral AI | USD 28.53 · Mistral AI | USD 9.51 · Ministral 3 8B lower |
| **Coding agent (one developer)** · 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 102.60 · Mistral AI | USD 76.95 · Mistral AI | USD 25.65 · Ministral 3 8B lower |

Ministral 3 8B is cheaper on all three workloads. The widest gap is on Support chatbot: the dearer model costs 33% more than the cheaper one.

## Does the cheaper model change with your input:output ratio?

Ministral 3 8B is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Ministral 3 14B's, so the input:output ratio never changes the answer.

Price per 1M tokens of Ministral 3 14B and Ministral 3 8B at different input:output mixes
| Input : output tokens | Ministral 3 14B | Ministral 3 8B |
| --- | --- | --- |
| **1 : 3** (long answers) | USD 0.20 · Mistral AI | USD 0.15 lower · Mistral AI |
| **1 : 1** | USD 0.20 · Mistral AI | USD 0.15 lower · Mistral AI |
| **3 : 1** (the site’s blend) | USD 0.20 · Mistral AI | USD 0.15 lower · Mistral AI |
| **10 : 1** (retrieval, long prompts) | USD 0.20 · Mistral AI | USD 0.15 lower · Mistral AI |
| **30 : 1** (agents, big contexts) | USD 0.20 · Mistral AI | USD 0.15 lower · Mistral AI |

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

## What do Ministral 3 14B and Ministral 3 8B cost per character in other languages?

Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the Ministral 3 14B tokenizer for Ministral 3 14B (the same one for both, so the gap equals the price gap):

Input cost per 1M characters by language, Ministral 3 14B and Ministral 3 8B
| Content | Ministral 3 14B | Ministral 3 8B |
| --- | --- | --- |
| **English** | USD 0.044 · Amazon Bedrock | USD 0.033 lower · Amazon Bedrock |
| **Arabic MSA** | USD 0.060 · Amazon Bedrock | USD 0.045 lower · Amazon Bedrock |
| **Egyptian Arabic** | USD 0.063 · Amazon Bedrock | USD 0.047 lower · Amazon Bedrock |
| **Hindi** | USD 0.076 · Amazon Bedrock | USD 0.057 lower · Amazon Bedrock |
| **Chinese** | USD 0.180 · Amazon Bedrock | USD 0.135 lower · Amazon Bedrock |
| **Spanish** | USD 0.047 · Amazon Bedrock | USD 0.035 lower · Amazon Bedrock |
| **Code** | USD 0.054 · Amazon Bedrock | USD 0.040 lower · Amazon Bedrock |

From the [real cost by language dataset](https://broadrouter.com/data/real-cost-by-language/) (measured tokens per character on FLORES-200 and other texts). Your own text will differ.

## Check it on your own traffic

-   [Ministral 3 14B API pricing](https://broadrouter.com/llm-api-pricing/ministral-14b-2512/): all 3 providers and other tiers.
-   [Ministral 3 8B API pricing](https://broadrouter.com/llm-api-pricing/ministral-8b-2512/): all 2 providers and other tiers.
-   [Cost calculator with Ministral 3 14B and Ministral 3 8B preloaded](https://broadrouter.com/tools/llm-api-cost-calculator/?model=ministral-14b-2512,ministral-8b-2512)
-   [Ministral 3 token counter](https://broadrouter.com/tools/ministral-token-counter/)
-   [Prompt caching calculator](https://broadrouter.com/tools/prompt-caching-calculator/)

## Questions

### Is Ministral 3 14B cheaper than Ministral 3 8B?

No. On a blend of 3 input tokens to 1 output token, Ministral 3 8B costs USD 0.15 per 1M tokens and Ministral 3 14B USD 0.20, at each model's cheapest standard price. For input alone, Ministral 3 8B is cheaper (USD 0.15 against USD 0.20 per 1M); for output alone, Ministral 3 8B is (USD 0.15 against USD 0.20). This compares price only, not quality.

### What do Ministral 3 14B and Ministral 3 8B cost per 1M tokens?

Ministral 3 14B: from USD 0.20 input and USD 0.20 output at Mistral AI and 2 others; Mistral AI's own API charges USD 0.20 / USD 0.20; median of 3 standard prices USD 0.20 / USD 0.20. Ministral 3 8B: from USD 0.15 input and USD 0.15 output at Mistral AI and 1 other; Mistral AI's own API charges USD 0.15 / USD 0.15; median of 2 standard prices USD 0.15 / USD 0.15. Each price is read from the provider's own pricing page; the source is linked in the table.

### Which providers sell both Ministral 3 14B and Ministral 3 8B?

2 providers have a standard price for both: Amazon Bedrock (USD 0.20 and USD 0.15 at 3:1), Mistral AI (USD 0.20 and USD 0.15 at 3:1). The first 2 tie for the lowest combined price. Buying each model from its own cheapest provider costs USD 0.20 and USD 0.15.

### Which is cheaper for a coding agent or a chatbot, Ministral 3 14B or Ministral 3 8B?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 102.60 a month on Ministral 3 14B (Mistral AI) against USD 76.95 on Ministral 3 8B (Mistral AI), a difference of USD 25.65. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 11.88 a month on Ministral 3 14B (Mistral AI) against USD 8.91 on Ministral 3 8B (Mistral AI), a difference of USD 2.97. Each uses the cheapest standard price for that workload, cached input included. [Try your own numbers](https://broadrouter.com/tools/llm-api-cost-calculator/?model=ministral-14b-2512,ministral-8b-2512).

### At what input:output ratio does the cheaper of Ministral 3 14B and Ministral 3 8B change?

Ministral 3 8B is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Ministral 3 14B's, so the input:output ratio never changes the answer.

### Do Ministral 3 14B and Ministral 3 8B have cached input pricing?

Ministral 3 14B from USD 0.02 per 1M cached input tokens (Mistral AI; 2 of 3 standard prices list a discount). Ministral 3 8B from USD 0.015 per 1M cached input tokens (Mistral AI; 1 of 2 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

### Which has the larger context window, Ministral 3 14B or Ministral 3 8B?

Both go up to 262,144 tokens on the providers that state it.

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-compare-ministral-14b-2512-vs-ministral-8b-2512&utm_content=page-cta) ·

**Sources**

-   [Mistral AI: own API pricing (checked 2026-11-14)](https://docs.mistral.ai/inference/pricing)
-   [Amazon Bedrock: pricing (checked 2026-11-14)](https://aws.amazon.com/bedrock/pricing/)
-   [DigitalOcean: pricing (checked 2026-11-14)](https://docs.digitalocean.com/products/inference/details/pricing/)
