Mistral AI · Official-source model record
Voxtral-Mini-3B-2507
Voxtral · Version 25.07
Publisher-sourced inventory. Specifications come from official documentation and model cards. “Not documented” means we have no verified value. This inventory is separate from our editorial reviews.
Coverage & sources ↗Current catalog answers
What to know about Voxtral-Mini-3B-2507
AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026.
Which Voxtral-Mini-3B-2507 does this page describe?
Voxtral-Mini-3B-2507 is a model record from Mistral AI in the Voxtral family. Source
The recorded model identifier or checkpoint is 25.07. Use that exact identifier when checking documentation or a provider listing. Source
How can you access Voxtral-Mini-3B-2507?
The catalog documents API and Open weights access for Voxtral-Mini-3B-2507. Source
As of the catalog check, this version was marked deprecated. Source Check the linked lifecycle information before starting a new integration.
For API use, confirm the exact model identifier, your account and region, and the endpoint's current limits in the linked documentation. An API listing does not establish access through a consumer subscription.
Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement. This record documents API access separately.
What are Voxtral-Mini-3B-2507's context and output limits?
The documented context window is 32,000 tokens. Source
A separate maximum-output value is not established in this record. The context or input figure should not be used as an output allowance.
Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity.
What dates are documented for Voxtral-Mini-3B-2507?
Release date: July 15, 2025. Source This is a release milestone, not a knowledge or training cutoff. The source labels this “Release date on Mistral model specification.”
Neither a knowledge cutoff nor a training-data cutoff is established here. A release date, repository upload or filename cannot supply those missing dates.
What can Voxtral-Mini-3B-2507 receive and generate?
Documented inputs: text and audio. Source
Documented outputs: text. Source
Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation.
What license is recorded for Voxtral-Mini-3B-2507?
The recorded license label is Apache 2.0. Source
Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service.
What is documented about the Voxtral-Mini-3B-2507 checkpoint?
This evidence refers to mistralai/Voxtral-Mini-3B-2507 at recorded revision 3060fe34b35ba5d44202ce9ff3c097642914f8f3, checked October 23, 2026. Repository metadata
Safetensors metadata records 4,676,271,104 stored parameters. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. Repository metadata
Recorded architecture class: VoxtralForConditionalGeneration. Repository metadata
Listed library: mistral-common. Check that library's version and model support before loading the weights. Repository metadata
Repository language labels: en, fr, de, es, it, pt, nl, and hi. These labels are not independent evaluations of language quality. Repository metadata
Repository access gate: false. This records the repository's gate setting when checked; licensing and use terms still apply. Repository metadata
What the configuration file says
The pinned config.json section text_config contains these values. Pinned configuration
max_position_embeddings- 131,072
torch_dtype- bfloat16
num_attention_heads- 32
num_key_value_heads- 8
num_hidden_layers- 30
hidden_size- 3,072
Configuration values describe the checkpoint and its implementation. In particular, max_position_embeddings, sliding_window and rope_scaling do not independently establish an API context limit, tested usable length or hardware requirement. Runtime, quantization, cache, batch size and input length affect deployment behavior.
Read the retrieved model card for setup and qualifications. Model card
Keep the exact version in view
Other Voxtral models from Mistral AI.
These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses.
Voxtral-Small-24B-2507
API · Open weights · 32,000 context tokens
The documented record
Specifications, with their sources.
A missing value remains unknown. Input limits, output limits and the total context window are separate measurements.
- Publisher
- Mistral AISource ↗
- Family
- VoxtralSource ↗
- Version
- 25.07Source ↗
- Availability
- DeprecatedSource ↗
- Access
- API · Open weightsSource ↗
- Inputs
- Text · AudioSource ↗
- Outputs
- TextSource ↗
- Context window
- 32,000 tokensSource ↗
- Maximum input
- Not documented
- Maximum output
- Not documented
- Knowledge cutoff
- Not documented
- Training-data cutoff
- Not documented
- Training completed
- Not documented
- Release date
- Jul 15, 2025Release date on Mistral model specification · day precisionSource ↗
- License
- Apache 2.0Source ↗
- Input price / 1M tokens
- Not documented
- Output price / 1M tokens
- Not documented
Read this with the numbers.
Official publisher model repository; listed status confirms a catalog entry, not a verified hosted API service. Lifecycle status refers to the Mistral API; publicly listed weights may remain usable under their license. Mistral context shorthand 32k is represented in nominal decimal tokens. Publisher repository evidence (2026-10-23): Published architecture metadata: VoxtralForConditionalGeneration. Repository library label: mistral-common. Model-card language labels: en, fr, de, es, it, pt, nl, hi; these labels are not evaluated proficiency scores. Published safetensors metadata counts 4,676,271,104 stored parameters; this is not an active-parameter count for mixture-of-experts models. Published text_config configuration: max_position_embeddings=131072; dtype=bfloat16; 30 hidden layers. Checkpoint configuration is not a verified hosted serving limit; context and output limits remain separate documented fields.
Model identifiers and aliases 1
mistralai/Voxtral-Mini-3B-2507
Follow the evidence
Official sources.
- Voxtral Mini specifications ↗docs.mistral.ai
- Voxtral-Mini-3B-2507 — official model card ↗huggingface.co
- Voxtral-Mini-3B-2507: official publisher repository metadata ↗huggingface.co
- Voxtral-Mini-3B-2507: publisher model card at revision 3060fe34b35b ↗huggingface.co
- Voxtral-Mini-3B-2507: published checkpoint configuration at revision 3060fe34b35b ↗huggingface.co