OpenAI SDK

To meet developers’ needs for the OpenAI API ecosystem, our API now supports the OpenAI API format. With simple configuration, you can integrate MiniMax capabilities into the OpenAI API ecosystem.

MiniMax-M3.1-Flash-Preview is available only through M Plan and MiniMax Code for now.

Quick Start

1. Install OpenAI SDK

pip install openai

npm install openai

2. Configure Environment Variables

export OPENAI_BASE_URL=https://api.minimax.io/v1
export OPENAI_API_KEY=${YOUR_API_KEY}

3. Call API

Python

from openai import OpenAI

client = OpenAI()

response = client.chat.completions.create(
    model="MiniMax-M3.1-Flash-Preview",
    reasoning_effort="max",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hi, how are you?"},
    ],
)

print(f"Thinking:\n{response.choices[0].message.reasoning_content}\n")
print(f"Text:\n{response.choices[0].message.content}\n")

4. Important Note

In multi-turn function call conversations, the complete model response (i.e., the assistant message) must be append to the conversation history to maintain the continuity of the reasoning chain.

Append the full response_message object (including the tool_calls field) to the message history
- For native OpenAI API with MiniMax-M3.1-Flash-Preview MiniMax-M3 MiniMax-M2.7 MiniMax-M2.7-highspeed MiniMax-M2.5 MiniMax-M2.5-highspeed MiniMax-M2.1 MiniMax-M2.1-highspeed MiniMax-M2 models, the content field will contain <think> tag content, which must be preserved completely
- MiniMax-M3.1-Flash-Preview provides the model’s thinking content separately through the reasoning_content field, which must also be preserved completely

Supported Models

When using the OpenAI SDK, the following MiniMax models are supported:

Model Name	Context Window	Description
MiniMax-M3.1-Flash-Preview	1,000,000	Frontier multimodal coding model with 1M context window and tunable thinking depth
MiniMax-M3	1,000,000	Frontier multimodal coding model with 1M context window
MiniMax-M2.7	204,800	Beginning the journey of recursive self-improvement (output speed approximately 60 tps)
MiniMax-M2.7-highspeed	204,800	M2.7 Highspeed: Same performance, faster and more agile (output speed approximately 100 tps)
MiniMax-M2.5	204,800	Peak Performance. Ultimate Value. Master the Complex (output speed approximately 60 tps)
MiniMax-M2.5-highspeed	204,800	M2.5 highspeed: Same performance, faster and more agile (output speed approximately 100 tps)
MiniMax-M2.1	204,800	Powerful Multi-Language Programming Capabilities with Comprehensively Enhanced Programming Experience (output speed approximately 60 tps)
MiniMax-M2.1-highspeed	204,800	Faster and More Agile (output speed approximately 100 tps)
MiniMax-M2	204,800	Agentic capabilities, Advanced reasoning

For details on how tps (Tokens Per Second) is calculated, please refer to FAQ > About APIs.

For more model information, please refer to the standard MiniMax API documentation.

Multimodal Input

OpenAI-compatible Chat Completions support text, image, and video input for MiniMax-M3.1-Flash-Preview and MiniMax-M3. Use image_url content parts for images and video_url content parts for videos. The detail field accepts low, default, or high and defaults to default; max_long_side_pixel can be used to control the longest side. Images support JPEG, PNG, GIF, and WEBP. Videos support MP4, AVI, MOV, and MKV; fps defaults to 1 and accepts values from 0.2 to 5. URL or base64 videos can be up to 50 MB, images can be up to 10 MB, and the request body can be up to 64 MB. For larger videos, upload through the Files API and pass mm_file://{file_id}; Files API videos can be up to 512 MB. Image token usage depends on image size and content. Use this as a rough single-image heuristic; check response usage or token counting where available for exact usage:

`detail`	Rough single-image token usage
`low`	Usually a few hundred tokens, up to ~600
`default`	Often ~1k-3k tokens, up to ~5k
`high`	Often several thousand tokens, up to ~15k+

Python

response = client.chat.completions.create(
    model="MiniMax-M3.1-Flash-Preview",
    reasoning_effort="max",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Summarize what is happening here."},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/image.png",
                        "detail": "default",
                    },
                },
                {
                    "type": "video_url",
                    "video_url": {
                        "url": "mm_file://file_id",
                        "detail": "default",
                    },
                },
            ],
        }
    ],
)

MiniMax-M3.1-Flash-Preview / MiniMax-M3 Request Parameters

MiniMax-M3.1-Flash-Preview and MiniMax-M3 support these additional Chat Completions parameters through the OpenAI-compatible API:

Parameter	Description
`thinking`	Controls thinking. `type` can be `disabled` or `adaptive`; when omitted, thinking is on by default. `MiniMax-M3.1-Flash-Preview` always thinks and returns `400` if `disabled` is sent. For M2.x models, thinking cannot be disabled.
`reasoning_effort`	Thinking depth, effective for `MiniMax-M3.1-Flash-Preview` only. Accepts `low`, `medium`, `high`, `xhigh`, and `max`; higher levels think more thoroughly. Defaults to `max` when omitted. `none` is not supported.
`stream_options.include_usage`	When streaming, set to `true` to include token usage in the stream.
`max_tokens`	Legacy generation length limit. Thinking tokens count toward it too, so a value that is too small yields `finish_reason: "length"` with an empty `content`.
`max_completion_tokens`	Generation length limit; use this field for new integrations.
`temperature`	Sampling temperature. Range `[0, 2]`, default `1`.
`top_p`	Nucleus sampling. Range `[0, 1]`. Default `0.95` for `MiniMax-M3.1-Flash-Preview` and `MiniMax-M3`, and `0.9` for M2.x models.
`tools`	Function tool definitions.
`reasoning_split`	Output-format switch. When `true`, thinking content is separated into the `reasoning_content` field; when `false`, thinking stays inside `content` wrapped in `<think>` tags. `MiniMax-M3.1-Flash-Preview` does not currently support setting this parameter to `false`.
`service_tier`	Request admission tier. Supported values are `standard` and `priority`; if omitted, requests use `standard`. The `priority` price is 1.5 times the `standard` price and ensures priority admission so the request is processed ahead of other requests, leading to faster responses and fewer failures.

Thinking Control

The thinking parameter controls whether the model can emit thinking content. Behavior differs per model:

Model	`thinking` omitted	`{"type": "adaptive"}`	`{"type": "disabled"}`
`MiniMax-M3.1-Flash-Preview`	Thinking on	Thinking on	Returns `400` — thinking cannot be disabled
`MiniMax-M3`	Thinking on	Thinking on	Skips thinking and answers directly
M2.x	Thinking on	Thinking on	Accepted but ignored; thinking remains on

The error returned for thinking: {"type": "disabled"} or reasoning_effort: "none":

model "MiniMax-M3.1-Flash-Preview" requires adaptive thinking; thinking.type="disabled" (including reasoning.effort=none) is not allowed (2013)

Python

response = client.chat.completions.create(
    model="MiniMax-M3.1-Flash-Preview",
    reasoning_effort="max",
    messages=[{"role": "user", "content": "Hi, how are you?"}],
    extra_body={
        "thinking": {"type": "adaptive"},
    },
)

Thinking Depth Control (MiniMax-M3.1-Flash-Preview only)

MiniMax-M3.1-Flash-Preview supports tuning thinking depth with reasoning_effort, from low through medium, high, xhigh, to max. Higher levels make the model think more thoroughly, producing more thinking tokens at higher latency. When omitted, reasoning_effort defaults to max. none is not supported and returns 400.

Python

response = client.chat.completions.create(
    model="MiniMax-M3.1-Flash-Preview",
    reasoning_effort="max",
    messages=[{"role": "user", "content": "Hi, how are you?"}],
)

Examples

Streaming Response

Python

from openai import OpenAI

client = OpenAI()

print("Starting stream response...\n")
print("=" * 60)
print("Thinking Process:")
print("=" * 60)

stream = client.chat.completions.create(
    model="MiniMax-M3.1-Flash-Preview",
    reasoning_effort="max",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hi, how are you?"},
    ],
    stream=True,
)

reasoning_buffer = ""
text_buffer = ""

for chunk in stream:
    delta = chunk.choices[0].delta

    # Thinking arrives as incremental fragments on reasoning_content
    if getattr(delta, "reasoning_content", None):
        print(delta.reasoning_content, end="", flush=True)
        reasoning_buffer += delta.reasoning_content

    if delta.content:
        text_buffer += delta.content

print("\n" + "=" * 60)
print("Response Content:")
print("=" * 60)
print(f"{text_buffer}\n")

Tool Use & Interleaved Thinking

Learn how to use M3.1-Flash-Preview Tool Use and Interleaved Thinking capabilities with OpenAI SDK, please refer to the following documentation.

Tool Use & Interleaved Thinking

Learn how to leverage MiniMax-M3.1-Flash-Preview tool calling and interleaved thinking capabilities to enhance performance in complex tasks.

Important Notes

The temperature parameter range is [0, 2], recommended value: 1.0, values outside this range will return an error
Some OpenAI parameters (such as presence_penalty, frequency_penalty, logit_bias, etc.) will be ignored
Image and video inputs are supported by MiniMax-M3.1-Flash-Preview and MiniMax-M3 through OpenAI-compatible message content parts; audio input is not currently supported
The n parameter only supports value 1
The deprecated function_call is not supported, please use the tools parameter

Using the API

Text

Video

Speech

Image

Music

File

Models

Quick Start

1. Install OpenAI SDK

2. Configure Environment Variables

3. Call API

4. Important Note

Supported Models

Multimodal Input

MiniMax-M3.1-Flash-Preview / MiniMax-M3 Request Parameters

Thinking Control

Thinking Depth Control (MiniMax-M3.1-Flash-Preview only)

Examples

Streaming Response

Tool Use & Interleaved Thinking

Tool Use & Interleaved Thinking

Important Notes

​Quick Start

​1. Install OpenAI SDK

​2. Configure Environment Variables

​3. Call API

​4. Important Note

​Supported Models

​Multimodal Input

​MiniMax-M3.1-Flash-Preview / MiniMax-M3 Request Parameters

​Thinking Control

​Thinking Depth Control (MiniMax-M3.1-Flash-Preview only)

​Examples

​Streaming Response

​Tool Use & Interleaved Thinking

Tool Use & Interleaved Thinking

​Important Notes

Quick Start

1. Install OpenAI SDK

2. Configure Environment Variables

3. Call API

4. Important Note

Supported Models

Multimodal Input

MiniMax-M3.1-Flash-Preview / MiniMax-M3 Request Parameters

Thinking Control

Thinking Depth Control (MiniMax-M3.1-Flash-Preview only)

Examples

Streaming Response

Tool Use & Interleaved Thinking

Important Notes