Fine-tuning - verified October 18, 2026

Mistral AI fine-tuning: status, methods and prices

Deprecated. Fine-tuning API marked deprecated (no date given). 1 offering recorded: SFT. Training is priced fixed fees: per job or per month, in Mistral AI's own units. Weight export: Not stated.

Recorded as: Mistral AI (La Plateforme / AI Studio).

Read from docs.mistral.ai, mistral.ai. Compare every fine-tuning API

Status: Deprecated
Offerings: 1
Methods: SFT
Export weights: Not stated

Status

Is Mistral AI fine-tuning still available?

Deprecated

Fine-tuning API marked deprecated (no date given).

“This feature is deprecated and is no longer actively supported.”

Docs - docs.mistral.ai

The offering

Prices are in the provider's own unit, as written. Not stated means the page we checked does not say.

SFTDeprecated

Text and vision fine-tuning (legacy API)

Supervised fine-tuning

Status: Deprecated
“This feature is deprecated and is no longer actively supported.”
docs.mistral.ai
Tunable base models: open-mistral-7b
mistral-small-latest
codestral-latest
open-mistral-nemo
mistral-large-latest
ministral-8b-latest
ministral-3b-latest
“open-mistral-7b”
docs.mistral.ai
“mistral-small-latest”
docs.mistral.ai
“codestral-latest”
docs.mistral.ai
“open-mistral-nemo”
docs.mistral.ai
“mistral-large-latest”
docs.mistral.ai
“ministral-8b-latest”
docs.mistral.ai
“ministral-3b-latest”
docs.mistral.ai
Training price: Text and vision fine-tuning (legacy API) training prices in Mistral AI (La Plateforme / AI Studio)'s own units
Model Price Unit Quote
all models $4 minimum fee per fine-tuning job “Every fine-tuning job comes with a minimum fee of $4, and there's a monthly storage fee of $2 for each model.”docs.mistral.ai
Tuned-model inference: all fine-tuned models: $2 (storage per model per month)
“Every fine-tuning job comes with a minimum fee of $4, and there's a monthly storage fee of $2 for each model.”
docs.mistral.ai
Hosting requirement: Not stated
Export weights: Not stated
Data limits: Not stated
Notes: Per-token training rates are not on the current pricing page. Classifier Factory (classifier fine-tuning) is in the same deprecated section.

Text and vision fine-tuning (legacy API) training prices in Mistral AI (La Plateforme / AI Studio)'s own units
Model	Price	Unit	Quote
all models	$4	minimum fee per fine-tuning job	“Every fine-tuning job comes with a minimum fee of $4, and there's a monthly storage fee of $2 for each model.”docs.mistral.ai

Research notes

The fine-tuning docs moved under 'Deprecated features' and are marked deprecated and no longer actively supported. The current mistral.ai/pricing page shows no fine-tuning rates.

Plain language

The methods, explained

SFTSupervised fine-tuning: You show the model example prompts with the answers you want, and it learns to answer like that. The default method almost everywhere.
DPODirect preference optimization (preference tuning): You give pairs of answers to the same prompt, one preferred and one not, and the model learns to lean toward the preferred kind. Good for tone and style.
RFTReinforcement fine-tuning: The model attempts tasks and a grader (your code, or another model) scores each attempt; training pushes it toward higher-scoring answers. Often billed by training hour, plus the grader's tokens.
Vision SFTVision fine-tuning: Supervised fine-tuning where the examples include images, so the model gets better at a visual task.
DistillationDistillation: A large teacher model writes answers that are used to fine-tune a smaller, cheaper student model. You pay for the teacher's calls as well as the training.
LoRALoRA (adapter) fine-tuning: Trains a small set of extra weights, an adapter, on top of the frozen base model. Cheaper and faster than full fine-tuning; the adapter is served alongside the base model.
FullFull-parameter fine-tuning: Updates every weight in the model. Costs more than LoRA and produces a complete copy of the model.
CPTContinued pre-training: Keeps training the model on a large body of raw, unlabeled text from your domain, so it absorbs vocabulary and facts before any instruction tuning.

FAQ

Does Mistral AI offer fine-tuning?

Deprecated or no longer maintained. Fine-tuning API marked deprecated (no date given). The source says: "This feature is deprecated and is no longer actively supported."

How much does Mistral AI fine-tuning cost?

Fixed fees: per job or per month: all models $4. Prices are in Mistral AI's own units and are not converted.

Can you download a model you fine-tune on Mistral AI?

Not stated. The pages we checked do not say whether tuned weights can be exported.

Sources

Last verified 2026-10-18. This is a directory of what each provider's own pages say, not a quality ranking. Prices are copied in the provider's own unit and never converted, so rows in different units are not comparable.

Newsletter

One email per week. New model releases, deprecations and pricing changes, and what they mean for what you build.