MiniMax M3.1 Flash — Think with more context
MiniMax M3.1 Flash is a reasoning model for text, image and video input. Work through documents, explain screenshots and continue tool conversations in one place.
- Text, images and video
- Always-on reasoning
- Function tools
- Automatic caching
Try MiniMax M3.1 Flash
Ask MiniMax M3.1 Flash a question. Inspect the request fields, or paste a complete conversation as JSON.
MiniMax-M3.1-FlashMiniMax M3.1 Flash per 1M tokens: $0.09 input · $0.36 output. Longer-context rates may apply.Blank fields are omitted. Use JSON for nested values.
Uses returned tokens and current rates; billing rounds the final amount.
MiniMax M3.1 Flash: a real response
MiniMax M3.1 Flash answered this arithmetic and translation check on October 20, 2026.
Please answer both questions briefly: 1. What is 17 multiplied by 23? 2. Translate 我们已经完成测试 into English.
1. 17 × 23 = 391 2. “我们已经完成测试” = “We have completed the tests.”
This single response used 231 input tokens, including 195 cached tokens, and 74 output tokens. It is an observed example, not a quality benchmark.
MiniMax M3.1 Flash pricing
MiniMax M3.1 Flash charges by input, output and cache usage. These rates come from the same current price settings used for billing.
The full input, including cache, chooses the price band for the whole request. Reasoning counts toward output. Example costs exclude cache savings.
| Category | ≤ 512,000 input tokensPrice · 1M tokens | > 512,000 input tokensPrice · 1M tokens |
|---|---|---|
| Input | $0.09 | $0.18 |
| Output, including reasoning | $0.36 | $0.72 |
| Cached input | $0.018 | $0.036 |
| Cache write | $0.09 | $0.18 |
Total input includes cache reads and writes. The selected tier applies to every token category in the request. Examples use the standard tier.
What is MiniMax M3.1 Flash?
MiniMax M3.1 Flash reads text, images and video, then returns text or function calls. Its million-token context can hold lengthy source material alongside instructions and conversation history.
MiniMax M3.1 Flash always reasons before answering. Choose the effort level for your task, leave enough output budget for the answer, and check important conclusions against the original material.
MiniMax M3.1 Flash produces text; it does not generate images, video or audio.
Use MiniMax M3.1 Flash your way
Keep a familiar request format while testing your own workload.
Connect MiniMax M3.1 Flash
Send your messages with a server-side key. Inspect the answer and usage before adding the model to a larger workflow.
- 1Create an API key.
- 2Copy a request from the docs.
- 3Check the result with your own data.
Build with MiniMax M3.1 Flash
Give your assistant the connection instructions. Review the request and estimated cost before it runs a paid test.
- 1Copy the setup instructions.
- 2Keep your key in an environment variable.
- 3Review before running.
What MiniMax M3.1 Flash can do
Bring the source material and a concrete question.
Read longer material
Ask MiniMax M3.1 Flash to compare sections of a report or trace a decision through meeting notes. Request quotes so you can verify the answer.
Explain visual evidence
Give MiniMax M3.1 Flash a screenshot or short clip alongside your question. Describe the detail you need instead of asking for an open-ended summary.
Continue a tool workflow
MiniMax M3.1 Flash can request a function call. Your application runs the function and returns its result; you remain in control of external actions.
Put MiniMax M3.1 Flash to work
Review a code change
Give MiniMax M3.1 Flash the relevant code, expected behavior and failing example. Ask for an explanation and a change you can test.
Draft a grounded reply
Use MiniMax M3.1 Flash with your support notes and product instructions. Check names, commitments and policy details before sending the draft.
Compare source documents
Have MiniMax M3.1 Flash separate agreements, contradictions and unanswered questions. Keep citations close to each claim so a reviewer can follow them.
Start with MiniMax M3.1 Flash
- 01
Add credit
Create an account and add the amount you need. Your credit does not expire.
- 02
Choose a format
Use Chat Completions, Messages or Responses with the exact MiniMax-M3.1-Flash model ID.
- 03
Try a small task
Give MiniMax M3.1 Flash a question with an answer you can check. Set an output budget that allows for reasoning.
- 04
Inspect and continue
Review the MiniMax M3.1 Flash output and usage. Preserve the complete assistant and tool history when continuing the conversation in your own application.
MiniMax M3.1 Flash at a glance
Choose MiniMax M3.1 Flash by the inputs and controls your task needs.
- Context
- 1,000,000 tokens
- Visual input
- Images and video
- Thinking control
- Five effort levels; cannot be disabled
- Function execution
- Run by your application
These are documented model limits, not measured throughput or a promise of accuracy.
Before using MiniMax M3.1 Flash
Leave room for the answer
MiniMax M3.1 Flash shares its output budget between reasoning and answer text. A very small limit can end before any answer appears.
MiniMax M3.1 Flash input limits
Images can be up to 10 MB; URL or inline video can be up to 50 MB. The docs list supported formats and complete constraints.
MiniMax M3.1 Flash on SeedRouter
See the rates here
Compare MiniMax M3.1 Flash input, output and cache rates before you send a request. The pricing table updates from current billing settings.
Pay for usage
Use MiniMax M3.1 Flash from a prepaid balance. There is no monthly subscription, and failed requests are not charged.
Keep conversation history
Preserve MiniMax M3.1 Flash reasoning and tool-call fields when continuing. Removing them can change the context available for the next answer.
Verify your task
Test MiniMax M3.1 Flash on examples you know before relying on it. Review generated code and factual claims with appropriate checks.
Compare MiniMax M3.1 Flash with other models
See live prices and task-specific controls before choosing.
Call DeepSeek V4.1 Flash with the OpenAI or Anthropic SDK. 1M-token context, thinking on or off, image input, live peak and off-peak pricing and a playground.
View modelCall Kimi K3 with the OpenAI or Anthropic SDK. 1M-token context, always-on reasoning with low, high or max effort, live per-token pricing and a playground.
View modelCall Claude Fable 5 with the Anthropic or OpenAI SDK. Deep reasoning, 1M-token context, forced tool use, live per-token pricing and a playground to test it.
View modelCall Claude Fable 5.1 with the Anthropic or OpenAI SDK. Deep reasoning, 1M-token context, cheap cached reads, live pricing and a playground to try it today.
View modelTry Claude Haiku 5.5 for classification, extraction and summaries. See live token prices, test your prompts, and connect your app with the Messages API.
View modelCall Claude Opus 5.5 with the Anthropic or OpenAI SDK. 1M-token context, adaptive thinking, live per-token pricing and a playground you can try right now.
View modelMiniMax M3.1 Flash guides
Read MiniMax M3.1 Flash comparisons and decide what to test next.
MiniMax M3.1 Flash questions
What is MiniMax M3.1 Flash?+
MiniMax M3.1 Flash is a reasoning model that accepts text, images and video. It returns text or function calls, with a context window of one million tokens.
Is MiniMax M3.1 Flash free on SeedRouter?+
No. MiniMax M3.1 Flash uses prepaid credit at the rates above. You pay for token usage without a subscription. Failed requests are not charged.
Can MiniMax M3.1 Flash turn thinking off?+
No. MiniMax M3.1 Flash always reasons. The five effort settings range from low to max; max is the documented default. Reasoning tokens count toward the output budget.
Does MiniMax M3.1 Flash make videos?+
No. MiniMax M3.1 Flash can analyze video input and answer in text. For video generation, choose a video model from the model catalogue.
How does MiniMax M3.1 Flash caching work?+
MiniMax M3.1 Flash automatically checks eligible repeated prefixes of at least 512 tokens. A cache hit is not guaranteed. Inspect the returned usage to see what was cached.
How much does MiniMax M3.1 Flash cost?+
MiniMax M3.1 Flash currently starts at $0.09 / 1M input and $0.36 / 1M output. The longer-context band applies to the whole request when total input exceeds 512,000 tokens.
Try MiniMax M3.1 Flash on your own task
Give MiniMax M3.1 Flash a question you can verify. Review the answer and usage.