MiniMax · Official-source model record
MiniMax-M3
MiniMax · Version MiniMax-M3
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 MiniMax-M3
AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026.
What dates are documented for MiniMax-M3?
Release date: June 1, 2026. Source This is a release milestone, not a knowledge or training cutoff. The source labels this “Explicit model release-notes date.”
Neither a knowledge cutoff nor a training-data cutoff is established here. A release date, repository upload or filename cannot supply those missing dates.
Which MiniMax-M3 does this page describe?
MiniMax-M3 is a model record from MiniMax in the MiniMax family. Source
The recorded model identifier or checkpoint is MiniMax-M3. Use that exact identifier when checking documentation or a provider listing. Source
How can you access MiniMax-M3?
The catalog documents API and Open weights access for MiniMax-M3. Source 1 · Source 2 · Source 3
As of the catalog check, this version was listed as available. Source
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.
How much does MiniMax-M3 cost?
The recorded token rates for MiniMax-M3 are:
Rate conditions: Published standard USD per million tokens, uncached input; region, prompt length, caching and service-tier adjustments may apply. See official source. Source 1 · Source 2 · Source 3 · Source 4
Illustrative arithmetic: 10,000 input tokens plus 2,000 output tokens would cost US$0.0054 at those recorded rates. This assumes every token is billed at the displayed rate and excludes any cache, batch, tool, storage or tier adjustments; it is not a quote or measured usage.
Check the source's pricing conditions before budgeting. A token rate does not state the price of an app subscription or the full cost of running downloaded weights.
What are MiniMax-M3's context and output limits?
The documented context window is 1,000,000 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 can MiniMax-M3 receive and generate?
Documented inputs: text, image, and video. 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 MiniMax-M3?
The recorded license label is minimax-community. 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 MiniMax-M3 checkpoint?
This evidence refers to MiniMaxAI/MiniMax-M3 at recorded revision f0e1c1e04d40177e4673a22097036854f536e9c0, checked October 23, 2026. Repository metadata
Safetensors metadata records 427,040,140,160 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: MiniMaxM3SparseForConditionalGeneration. Repository metadata
Repository task tag: image-text-to-text. A task tag identifies a distribution category; it does not measure performance on that task. Repository metadata
Listed library: transformers. Check that library's version and model support before loading the weights. 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- 1,048,576
torch_dtype- bfloat16
num_attention_heads- 64
num_key_value_heads- 4
num_hidden_layers- 60
hidden_size- 6,144
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 MiniMax models from MiniMax.
These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses.
MiniMax-M3.1-Flash
API · Open weights · 1,000,000 context tokens
MiniMax-M1-40k
Open weights
MiniMax-M1-80k
Open weights
MiniMax-M2
Open weights
MiniMax-M2.1
Open weights
MiniMax-M2.5
API · Open weights
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
- MiniMaxSource ↗
- Family
- MiniMaxSource ↗
- Version
- MiniMax-M3Source ↗
- Availability
- AvailableSource ↗
- Access
- API · Open weightsSource 1 ↗Source 2 ↗Source 3 ↗
- Inputs
- Text · Image · VideoSource ↗
- Outputs
- TextSource ↗
- Context window
- 1,000,000 tokensSource ↗
- Maximum input
- Not documented
- Maximum output
- Not documented
- Knowledge cutoff
- Not documented
- Training-data cutoff
- Not documented
- Training completed
- Not documented
- Release date
- Jun 1, 2026Explicit model release-notes date · day precisionSource ↗
- License
- minimax-communitySource ↗
- Input price / 1M tokens
- $0.3Source ↗
- Output price / 1M tokens
- $1.2Source ↗
Read this with the numbers.
Official publisher weight listing; availability refers to this distribution, not a guaranteed hosted API. Base, SFT and research variants are identified by their exact published names. Official quantization/runtime variants are retained as aliases. Model-card body could not be retrieved; fields beyond the official inventory metadata remain unverified. M3 rates shown are standard prompts up to 512K; longer prompts and priority tier cost more. Text, image and video input are explicitly documented for both models on the Anthropic-compatible API; the separate AI SDK wrapper does not support video. Publisher repository evidence (2026-10-23): Publisher task label: image-text-to-text. Published architecture metadata: MiniMaxM3SparseForConditionalGeneration. Repository library label: transformers. Published safetensors metadata counts 427,040,140,160 stored parameters; this is not an active-parameter count for mixture-of-experts models. Published text_config configuration: max_position_embeddings=1048576; dtype=bfloat16; 60 hidden layers. Checkpoint configuration is not a verified hosted serving limit; context and output limits remain separate documented fields.
Published standard USD per million tokens, uncached input; region, prompt length, caching and service-tier adjustments may apply. See official source.
Model identifiers and aliases 3
MiniMax-M3MiniMaxAI/MiniMax-M3MiniMaxAI/MiniMax-M3-MXFP8
Follow the evidence
Official sources.
- MiniMax-M3 official model card ↗huggingface.co
- MiniMax Anthropic-compatible API: exact supported input modalities by model ↗platform.minimax.io
- models — official MiniMax documentation ↗platform.minimax.io
- Official MiniMax model documentation ↗platform.minimax.io
- MiniMax model release notes ↗platform.minimax.io
- MiniMax-M3: official publisher repository metadata ↗huggingface.co
- MiniMax-M3: publisher model card at revision f0e1c1e04d40 ↗huggingface.co
- MiniMax-M3: published checkpoint configuration at revision f0e1c1e04d40 ↗huggingface.co