Mistral logo Retired May 2026 Open weights · Mistral Research License

Mistral Large

Mistral AI's 123B flagship general-purpose dense model, released July 2024, with broad multilingual coverage and support for many programming languages.

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

Key Specifications

Context window
128K tokens
Max output
33K tokens
Released
Parameters
123B
Inputs
Text
Capabilities Show details
Function calling Connect to external tools, APIs, and systems. Structured output Return responses in structured formats like JSON.

Estimated cost to self-host

Mistral Large needs about 81 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 8× RTX 3060 at about $346 a month.

Single node ≤ 8
Precision Memory Cheapest fit (32K context) Cost /mo
4-bitINT4 / FP4
81 GB
Nvidia logo 8× RTX 3060
$346
8-bitFP8 / INT8
137 GB
Nvidia logo 8× RTX 3090
$979
16-bitFP16 / BF16
260 GB
Nvidia logo 8× RTX A6000
$3,168

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.

Frequently Asked Questions

What is Mistral Large good for?

General text work with broad multilingual coverage and many programming languages. Dense open weights under the Mistral Research License, servable on a single high-memory GPU.

When is Mistral Large not a good fit?

Any hosted use: Mistral retired it from its API in May 2026. Text only, and the Mistral Research License is not a commercial licence, so check its terms before self-hosting for a business.

What is the cheapest way to run Mistral Large?

No provider we track hosts it; self-hosting on the cheapest rental that fits (8x RTX 3060, $0.48 per hour) costs about $346 a month.

Can I self-host Mistral Large?

Yes. The weights are released under the Mistral Research License. At 4-bit it needs about 81 GB of GPU memory, which starts at roughly $346 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