Ministral 3 14B
Open weights · Apache 2.0
The largest of the Ministral 3 family, a 14B dense model (13.5B language model plus a 0.4B vision encoder) under Apache 2.0, built for local and edge deployment.
- Input
- $0.20 / 1M tokens
- Output
- $0.20 / 1M tokens
About $2.40 for 10M input and 2M output tokens. Estimate yours
1 provider
Key Specifications
- Context window
- 256K tokens
- Inputs
- Text, Image Outputs: Text
Ministral 3 14B pricing by provider
| Provider | Input / 1M tokens | Output / 1M tokens | Cost at 10M in + 2M out | |
|---|---|---|---|---|
|
Mistral
Creator
|
$0.20 | $0.20 | $2.40 | View |
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning. LLM rates are base-tier, on-demand prices per 1M tokens; cached-input, batch and long-context tiers are not included.
Compare every model at this volume in the LLM cost calculator.
Capabilities
Function calling
Connect to external tools, APIs, and systems.
Structured output
Return responses in structured formats like JSON.
Estimated cost to self-host Ministral 3 14B
Ministral 3 14B has 13.9B parameters. At 4-bit it needs about 8 GB of GPU memory, at 8-bit 17 GB and at BF16 33 GB, counting 20% on top of the weights for KV cache and runtime overhead.
| Precision | Memory needed | Cheapest rentals that fit | Per month, 24/7 |
|---|---|---|---|
| 4-bit | 8 GB |
RTX 3060
($0.07/hr)
RTX 2080 Ti
($0.08/hr)
|
$50 |
| 8-bit | 17 GB |
RTX 3090
($0.13/hr)
RTX 3090 Ti
($0.19/hr)
|
$94 |
| BF16 | 33 GB |
RTX A6000
($0.56/hr)
A40
($0.74/hr)
|
$403 |
$0.07 an hour (RTX 3060) buys about 350K tokens an hour at the cheapest hosted rate we track ($0.20 in / $0.20 out per 1M tokens on Mistral, 5:1 input to output); below that volume the API is cheaper, before idle time. Compare hosted costs.
Memory is parameters × bytes per weight at each precision, plus 20% for KV cache and runtime overhead. Rentals are the cheapest cards that hold it, at provider-weighted median on-demand prices for the week of August 17, 2026, consumer cards included, in nodes of up to 8 GPUs; a fit with under 15% headroom is marked tight. A month is 720 hours. See the best-value GPUs guide for the same table across models, and cloud GPU pricing for every card.
More from Mistral
| Model | Context | Input / 1M | Output / 1M |
|---|---|---|---|
|
Ministral 3 8B
Open weights
|
256K | $0.15 | $0.15 |
|
Mistral Small 4
Open weights
|
256K | $0.15 | $0.60 |
|
Codestral
|
128K | $0.30 | $0.90 |
|
Ministral 3 3B
Open weights
|
256K | $0.10 | $0.10 |
|
Mistral Large 3
Open weights
|
256K | $0.50 | $1.50 |
|
Mistral NeMo
Open weights
|
128K | $0.04 | $0.17 |
|
Mistral Medium 3.5
Open weights
|
256K | $1.50 | $7.50 |
|
Devstral Medium
|
128K | ||
Models near this price
The models nearest this one by input rate, five each way, at each one's cheapest listed provider.
Frequently Asked Questions
How much does Ministral 3 14B cost?
Ministral 3 14B costs $0.20 per 1M input tokens and $0.20 per 1M output tokens via Mistral. Mistral publishes the weights, so it can also be run on your own hardware.
What does Ministral 3 14B cost for 10M input and 2M output tokens?
At Mistral's rates, 10M input tokens and 2M output tokens cost about $2.40: $2.00 for input and $0.40 for output. Input is prompts and context, output is what the model writes back; a workload that generates more than it reads shifts the cost toward the output rate of $0.20 per 1M tokens.
Which providers offer Ministral 3 14B?
One provider lists Ministral 3 14B: Mistral ($0.20 in / $0.20 out).
What is Ministral 3 14B's context window?
Ministral 3 14B accepts up to 256K tokens of input per request. The context window is the prompt plus any documents, conversation history and tool results sent with it; every token in it is billed at the input rate.
What inputs and outputs does Ministral 3 14B support?
Ministral 3 14B accepts text and images as input and produces text. Its listed capabilities are function calling and structured output.
Can I self-host Ministral 3 14B?
Yes. Mistral publishes Ministral 3 14B's weights under the Apache 2.0 license. At 4-bit it needs about 8 GB of GPU memory; the cheapest rental that holds it is RTX 3060 at $0.07 per hour, about $50 a month. $0.07 an hour (RTX 3060) buys about 350K tokens an hour at the cheapest hosted rate we track ($0.20 in / $0.20 out per 1M tokens on Mistral, 5:1 input to output); below that volume the API is cheaper, before idle time. The estimate above prices 8-bit and BF16 too.
How does Ministral 3 14B compare with Ministral 3 8B?
Ministral 3 14B costs $0.20 per 1M input tokens against Ministral 3 8B's $0.15, 1.3x more expensive ($0.20 vs $0.15 per 1M output tokens). Both have a 256K-token context window.
What are cheaper alternatives to Ministral 3 14B?
Models from other creators with a lower input rate and at least Ministral 3 14B's 256K-token context window: Llama 4 Scout at $0.17 per 1M input tokens (10M context), GLM-5.3-Flash at $0.15 per 1M input tokens (1M context) and Qwen3-Next-80B-A3B Instruct at $0.15 per 1M input tokens (262K context). Rates are the cheapest listed provider for each; whether the quality holds for a given task is a separate question.
Cheaper alternatives to Ministral 3 14B
Llama 4 Scout
$0.17 per 1M input tokens and $0.65 per 1M output tokens via Replicate, 10M-token context, by Meta.
GLM-5.3-Flash
$0.15 per 1M input tokens and $0.50 per 1M output tokens via Z.AI, 1M-token context, by Z.AI.
Qwen3-Next-80B-A3B Instruct
$0.15 per 1M input tokens and $1.50 per 1M output tokens via Novita, 262K-token context, by Alibaba Cloud.