Mistral logo Retired Dec 2025 Open weights · Apache 2.0

Pixtral 12B

Mistral AI's first multimodal model, built on the Mistral NeMo 12B backbone and released September 2024 under Apache 2.0, processing images at native resolution.

Jump to: Specs Pricing Self-hosting FAQ More from Mistral
Visit website Compare vs other LLMs →

Key Specifications

Context window
128K tokens
Max output
33K tokens
Released
Parameters
12.4B
Inputs
Text, image

Hosted API pricing

Provider Input / 1M tokens Output / 1M tokens Cost at 10M in + 2M out
Mistral logo Mistral Creator Open weights, no hosted price View

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

Pixtral 12B needs about 11 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 1× RTX 4060 Ti at about $79 a month.

Fits on 1 Single node ≤ 8
Precision Memory Cheapest fit (32K context) Cost / mo
4-bitINT4 / FP4
11 GB
Nvidia logo 1× RTX 4060 Ti
$79
8-bitFP8 / INT8
20 GB
Nvidia logo 2× RTX 3060
$86
16-bitFP16 / BF16
32 GB
Nvidia logo 4× RTX 3060
$173

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Packet·ai Logo Packet·ai
Our sponsor
B200 @ $3.75/h on demand
No contract, no spot interrupts, no cluster minimums
Full root SSH, web dashboard, CI/CD ready
Reserve Now

Frequently Asked Questions

What is Pixtral 12B good for?

Self-hosted image understanding, reading images at native resolution. Apache 2.0 weights, small enough for a single consumer GPU.

When is Pixtral 12B not a good fit?

Hosted use: Mistral retired it from its API in December 2025. No function calling or structured output, and its maximum output caps long single responses.

What is the cheapest way to run Pixtral 12B?

No provider we track hosts it; self-hosting on the cheapest rental that fits (1x RTX 4060 Ti, $0.11 per hour) costs about $79 a month.

Can I self-host Pixtral 12B?

Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 11 GB of GPU memory, which starts at roughly $79 a month on the cheapest rental that fits.

More from Mistral

Model Context Input / 1M Output / 1M
Mistral Ministral 3 14B Open weights 256K $0.20 $0.20
Mistral Ministral 3 3B Open weights 256K $0.10 $0.10
Mistral Ministral 3 8B Open weights 256K $0.15 $0.15
Mistral Mistral Large 3 Open weights 256K $0.50 $1.50
Mistral Mistral Medium 3.5 Open weights 256K $1.50 $7.50
Mistral Mistral Small 4 Open weights 256K $0.15 $0.60
Mistral Codestral 128K $0.30 $0.90
Mistral Devstral Medium 128K