MiniMax Cross-module and visual engineering review
MiniMax M3
Review cross-module changes and visual evidence without losing track of sources.
MiniMax presents M3 as a multimodal coding model. The TokenHot catalog lists a 1M context, text, image and video input, and text output.
- 1M catalog context
- Text output
- Published API example
The public example is text. The chat Playground accepts text and one new image per message. Confirm video request support and payload shape separately.
AI Chat
Send a prompt and see the response here.
MiniMax-M3Start a conversation with this model and ask follow-up questions.
USD /1M tokens
Pricing
| Group | Tier | Input | Output | Cache Read |
|---|---|---|---|---|
| default | ≤512K | $0.315 | $1.26 | $0.063 |
| default | >512K | $0.63 | $2.52 | $0.126 |
Public list prices are shown in USD. Final charges may vary by account group and usage tier.
Overview
What is MiniMax M3?
Start with a bounded task and source material you can verify. The scenarios below illustrate proposed workflows and review criteria.
Review a change across modules
A decision note on the change and its affected callers.
Document a UI defect from a still
A short defect checklist for a reviewer.
Review an ordered set of stills
An evidence note that distinguishes frame observations from timing claims.
From brief to deliverable
Put MiniMax M3 to work
Cross-module and visual engineering review
Review a change across modules
Keep each proposed change tied to a visible dependency.
- Tools you need
- Supplied source material and a reviewer who can check the originals.
- Keep in mind
- Check the draft against the source before acting on it.
View a task brief
Use the supplied material to produce a decision note on the change and its affected callers. Cite the evidence and label unknowns.
Cross-module and visual engineering review
Document a UI defect from a still
Write a visible-state report that can be reproduced from the source.
- Tools you need
- Supplied source material and a reviewer who can check the originals.
- Keep in mind
- Check the draft against the source before acting on it.
View a task brief
Use the supplied material to produce a short defect checklist for a reviewer. Cite the evidence and label unknowns.
Cross-module and visual engineering review
Review an ordered set of stills
Give a static board and cite the frame labels in the answer.
- Tools you need
- Supplied source material and a reviewer who can check the originals.
- Keep in mind
- Check the draft against the source before acting on it.
View a task brief
Use the supplied material to produce an evidence note that distinguishes frame observations from timing claims. Cite the evidence and label unknowns.
Capabilities in context
Key features
| Feature | What you get | Why it matters |
|---|---|---|
| Catalog route | MiniMax-M3 | Use the exact model ID when comparing results and costs. |
| Published request example | /v1/chat/completions | Start from the text example on the model page and confirm any media or optional settings for that endpoint. |
| Playground scope | Interactive chat | Text and one image per message. |
The model page and provider documentation describe different interfaces. Scenario art is illustrative and was not produced by the featured model. TokenHot model details and example · MiniMax M3 announcement
Audience & fit
Where MiniMax M3 fits
Review a change across modules
Keep each proposed change tied to a visible dependency.
Document a UI defect from a still
Write a visible-state report that can be reproduced from the source.
Review an ordered set of stills
Give a static board and cite the frame labels in the answer.
Cost context
Plan the cost of a useful result
Read the current table
Check the active TokenHot group and rates. Provider prices are separate.
Budget for review
Compare usable results per request and include retries and review time.
Use the current pricing table for available rates and account groups. Model IDs and prices come from TokenHot’s catalog; provider pricing and subscriptions are separate.
API
Code examples
curl --location --request POST 'https://api.tokenhot.ai/v1/chat/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
"model": "MiniMax-M3",
"messages": [
{
"role": "user",
"content": "What model are you"
}
]
}'FAQ
Frequently asked questions
What is MiniMax M3 best suited for?
MiniMax M3 is suited to the input, output, and capability types listed on this page. Test production workloads before choosing it for a critical system.
How is MiniMax M3 priced?
Pricing is shown in the pricing section above. Actual cost depends on usage volume, account group, and the request payload.
How can I call MiniMax M3?
Use the model ID shown above with one of the supported API protocols. Code examples are provided when usage data is available.
What is the TokenHot model ID?
Use MiniMax-M3.
Which API request does TokenHot show?
The current TokenHot model page shows a text request to /v1/chat/completions.
What does the Playground accept?
Send text and optionally attach one new image per message.
Can I attach a video in the chat Playground?
No. For a video-related question, attach one still image or paste a transcript.
Where do I check the price?
Use the current TokenHot pricing table for this exact model and check which account group applies.
Get started
Build with MiniMax M3
API