Ministral 3 8B
Open weights · Apache 2.0
The mid-size Ministral 3 model between the 3B and 14B variants, an 8B dense model with a vision encoder under Apache 2.0, built for edge deployment in base, instruct and reasoning variants.
- Input
- $0.15 / 1M tokens
- Output
- $0.15 / 1M tokens
About $1.80 for 10M input and 2M output tokens. Estimate yours
1 provider
Key Specifications
- Context window
- 256K tokens
- Inputs
- Text, Image Outputs: Text
Ministral 3 8B pricing by provider
| Provider | Input / 1M tokens | Output / 1M tokens | Cost at 10M in + 2M out | |
|---|---|---|---|---|
|
Mistral
Creator
|
$0.15 | $0.15 | $1.80 | 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 8B
Ministral 3 8B has 8.8B parameters. At 4-bit it needs about 5 GB of GPU memory, at 8-bit 11 GB and at BF16 21 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 | 5 GB |
GTX 1070
($0.05/hr)
GTX 1660 Super
($0.05/hr, tight)
|
$36 |
| 8-bit | 11 GB |
RTX 3060
($0.07/hr, tight)
RTX 2080 Ti
($0.08/hr, tight)
|
$50 |
| BF16 | 21 GB |
RTX 3090
($0.13/hr, tight)
RTX 3090 Ti
($0.19/hr, tight)
|
$94 |
$0.05 an hour (GTX 1070) buys about 333K tokens an hour at the cheapest hosted rate we track ($0.15 in / $0.15 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 |
|---|---|---|---|
|
Mistral Small 4
Open weights
|
256K | $0.15 | $0.60 |
|
Ministral 3 14B
Open weights
|
256K | $0.20 | $0.20 |
|
Ministral 3 3B
Open weights
|
256K | $0.10 | $0.10 |
|
Codestral
|
128K | $0.30 | $0.90 |
|
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 8B cost?
Ministral 3 8B costs $0.15 per 1M input tokens and $0.15 per 1M output tokens via Mistral. Mistral publishes the weights, so it can also be run on your own hardware.
What does Ministral 3 8B cost for 10M input and 2M output tokens?
At Mistral's rates, 10M input tokens and 2M output tokens cost about $1.80: $1.50 for input and $0.30 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 $0.15 per 1M tokens.
Which providers offer Ministral 3 8B?
One provider lists Ministral 3 8B: Mistral ($0.15 in / $0.15 out).
What is Ministral 3 8B's context window?
Ministral 3 8B 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 8B support?
Ministral 3 8B accepts text and images as input and produces text. Its listed capabilities are function calling and structured output.
Can I self-host Ministral 3 8B?
Yes. Mistral publishes Ministral 3 8B's weights under the Apache 2.0 license. At 4-bit it needs about 5 GB of GPU memory; the cheapest rental that holds it is GTX 1070 at $0.05 per hour, about $36 a month. $0.05 an hour (GTX 1070) buys about 333K tokens an hour at the cheapest hosted rate we track ($0.15 in / $0.15 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 8B compare with Mistral Small 4?
Ministral 3 8B and Mistral Small 4 both cost $0.15 per 1M input tokens ($0.15 vs $0.60 per 1M output tokens). Both have a 256K-token context window.
What are cheaper alternatives to Ministral 3 8B?
Models from other creators with a lower input rate and at least Ministral 3 8B's 256K-token context window: DeepSeek V4 Flash at $0.14 per 1M input tokens (1M context), Hy3 at $0.14 per 1M input tokens (262K context) and Gemma 4 26B A4B at $0.13 per 1M input tokens (256K 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 8B
DeepSeek V4 Flash
$0.14 per 1M input tokens and $0.28 per 1M output tokens via Novita, 1M-token context, by DeepSeek.
Hy3
$0.14 per 1M input tokens and $0.56 per 1M output tokens via GPUhub, 262K-token context, by Tencent.
Gemma 4 26B A4B
$0.13 per 1M input tokens and $0.40 per 1M output tokens via Novita, 256K-token context, by Google Cloud.