We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
MiniMax: MiniMax-01
minimax/minimax-01Try MiniMax: MiniMax-01 now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
MiniMax: MiniMax-01 at a glance
- Input price is 56% lower than the median of 434 Text models.
- Context window of 1,000,192 tokens, enough for long documents and multi-turn conversations.
- Accepts images as input (vision).
- A typical request (1,000 input / 500 output tokens) costs about $0.00263.
About MiniMax: MiniMax-01
MiniMax-01 is a text generation model from MiniMax, released by the provider on 15 January 2025. It combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding into a single model, and it is built on 456 billion parameters, with 45.9 billion parameters activated per inference. On api14 it is listed under the text category with the model id minimax/minimax-01.
The model accepts text and images as input and produces text as output. Its context window is 1,000,192 tokens, and the maximum output is 900,172 tokens, so both very long inputs and very long generations are possible within the same request. The knowledge cutoff is 31 March 2024, which means anything after that date is outside what the model was trained on. Because images are an accepted input modality, the model can read visual content alongside text rather than being limited to text alone.
Those capabilities point to a few practical uses. Long document work is an obvious fit: contracts, research papers, codebases, transcripts or multi-file dumps can be supplied in a single context instead of being chunked and stitched back together. The large output ceiling also suits tasks that produce long results, such as extended summaries, report drafts or structured extraction across a large source. Image input extends this to mixed material, for example screenshots, diagrams or scanned pages that need to be described, transcribed or reasoned about together with accompanying text. General chat, question answering and text transformation are also within scope.
You call the model through api14's OpenAI-compatible API using the model id minimax/minimax-01. The supported request parameters are max_tokens, temperature and top_p. max_tokens controls the length of the generated output, temperature adjusts randomness, and top_p applies nucleus sampling. No other parameters are listed as supported, so requests should stay within those three alongside the standard messages input.
Two things are worth checking before committing. The knowledge cutoff of 31 March 2024 means the model has no built-in awareness of later events, so anything recent needs to be supplied in the prompt. Also, output is text only, so if a task requires generated images or audio, a different model is needed. For text and image-in, text-out work within the supported parameters, MiniMax-01 is a reasonable candidate.
How to call the MiniMax: MiniMax-01 API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "minimax/minimax-01".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "minimax/minimax-01",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
max_tokenstemperaturetop_pSpecifications
- Context length
- 1,000,192
- Max output
- 900,172
- Input
- text, image
- Output
- text
- Knowledge cutoff
- 2024-03-31
Requests on api14 · last 7 days
MiniMax: MiniMax-01: frequently asked questions
- How much does the MiniMax: MiniMax-01 API cost?
- MiniMax: MiniMax-01 costs Input $0.70 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of MiniMax: MiniMax-01?
- MiniMax: MiniMax-01 reads up to 1,000,192 tokens per request: prompt, history and documents together. It writes up to 900,172 output tokens per response.
- What can MiniMax: MiniMax-01 do?
- MiniMax: MiniMax-01 accepts text, image and returns text.
- How do I call MiniMax: MiniMax-01 from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "minimax/minimax-01". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to MiniMax: MiniMax-01?
- Comparable Text models at a similar price: Qwen: Qwen3 Coder 480B A35B, Google: Gemma 2 27B, Xiaomi: MiMo-V2.6-Pro. Each runs through the same API key, so switching is one string.
MiniMax: MiniMax-01 community
New topicThis community has no topics yet. Open the first one about MiniMax: MiniMax-01.